{"type": "node", "id": "axis:energy", "kind": "axis", "label": "Energy-proportional / carbon-aware ML", "url": "https://arxiv.org/list/cs.LG/recent", "source": "harvest", "axis": "energy", "layer": 1, "maps_to_surface": "energy"}
{"type": "node", "id": "surface:energy", "kind": "surface", "label": "SZL surface: energy", "url": "https://a-11-oy.com", "source": "szl-estate", "axis": "energy", "layer": 3, "maps_to_surface": "energy"}
{"type": "node", "id": "axis:quant", "kind": "axis", "label": "GPU efficiency & quantization", "url": "https://arxiv.org/list/cs.LG/recent", "source": "harvest", "axis": "quant", "layer": 1, "maps_to_surface": "energy"}
{"type": "node", "id": "axis:neuro", "kind": "axis", "label": "Neuromorphic / spiking neural networks", "url": "https://arxiv.org/list/cs.LG/recent", "source": "harvest", "axis": "neuro", "layer": 1, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "surface:neuromorphic", "kind": "surface", "label": "SZL surface: neuromorphic", "url": "https://a-11-oy.com", "source": "szl-estate", "axis": "neuro", "layer": 3, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "axis:defense", "kind": "axis", "label": "Counter-UAS / maritime domain awareness", "url": "https://arxiv.org/list/cs.LG/recent", "source": "harvest", "axis": "defense", "layer": 1}
{"type": "node", "id": "axis:fusion", "kind": "axis", "label": "Multi-sensor fusion", "url": "https://arxiv.org/list/cs.LG/recent", "source": "harvest", "axis": "fusion", "layer": 1}
{"type": "node", "id": "axis:pinn", "kind": "axis", "label": "Physics-informed neural networks", "url": "https://arxiv.org/list/cs.LG/recent", "source": "harvest", "axis": "pinn", "layer": 1, "maps_to_surface": "pinn"}
{"type": "node", "id": "surface:pinn", "kind": "surface", "label": "SZL surface: pinn", "url": "https://a-11-oy.com", "source": "szl-estate", "axis": "pinn", "layer": 3, "maps_to_surface": "pinn"}
{"type": "node", "id": "axis:qec", "kind": "axis", "label": "Topological QEC / error correction", "url": "https://arxiv.org/list/cs.LG/recent", "source": "harvest", "axis": "qec", "layer": 1, "maps_to_surface": "qhall"}
{"type": "node", "id": "surface:qhall", "kind": "surface", "label": "SZL surface: qhall", "url": "https://a-11-oy.com", "source": "szl-estate", "axis": "qec", "layer": 3, "maps_to_surface": "qhall"}
{"type": "node", "id": "axis:agents", "kind": "axis", "label": "Agentic frameworks & orchestration", "url": "https://arxiv.org/list/cs.LG/recent", "source": "harvest", "axis": "agents", "layer": 1}
{"type": "node", "id": "axis:worldmodel", "kind": "axis", "label": "World models", "url": "https://arxiv.org/list/cs.LG/recent", "source": "harvest", "axis": "worldmodel", "layer": 1, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "surface:worldmodel", "kind": "surface", "label": "SZL surface: worldmodel", "url": "https://a-11-oy.com", "source": "szl-estate", "axis": "worldmodel", "layer": 3, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "axis:flowmatch", "kind": "axis", "label": "Flow matching / generative", "url": "https://arxiv.org/list/cs.LG/recent", "source": "harvest", "axis": "flowmatch", "layer": 1, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "surface:flowmatch", "kind": "surface", "label": "SZL surface: flowmatch", "url": "https://a-11-oy.com", "source": "szl-estate", "axis": "flowmatch", "layer": 3, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "repo:microsoft/autogen", "kind": "repo", "label": "microsoft/autogen", "url": "https://github.com/microsoft/autogen", "source": "github", "axis": "agents", "layer": 0, "stars": 59549, "lang": "Python", "desc": "A programming framework for agentic AI"}
{"type": "node", "id": "repo:microsoft/ai-agents-for-beginners", "kind": "repo", "label": "microsoft/ai-agents-for-beginners", "url": "https://github.com/microsoft/ai-agents-for-beginners", "source": "github", "axis": "agents", "layer": 0, "stars": 68769, "lang": "Jupyter Notebook", "desc": "12 Lessons to Get Started Building AI Agents"}
{"type": "node", "id": "repo:JayZeeDesign/research-agents-3.0", "kind": "repo", "label": "JayZeeDesign/research-agents-3.0", "url": "https://github.com/JayZeeDesign/research-agents-3.0", "source": "github", "axis": "agents", "layer": 0, "stars": 457, "lang": "Python", "desc": "Autogen + GPTs - build a swarm AI researchers"}
{"type": "node", "id": "repo:victordibia/autogen-ui", "kind": "repo", "label": "victordibia/autogen-ui", "url": "https://github.com/victordibia/autogen-ui", "source": "github", "axis": "agents", "layer": 0, "stars": 999, "lang": "TypeScript", "desc": "Web UI for AutoGen (A Framework Multi-Agent LLM Applications)"}
{"type": "node", "id": "repo:AgentOps-AI/agentops", "kind": "repo", "label": "AgentOps-AI/agentops", "url": "https://github.com/AgentOps-AI/agentops", "source": "github", "axis": "agents", "layer": 0, "stars": 5684, "lang": "Python", "desc": "Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI"}
{"type": "node", "id": "repo:karthikvenkatesan-eaton/Autogen_GraphRAG_Ollama", "kind": "repo", "label": "karthikvenkatesan-eaton/Autogen_GraphRAG_Ollama", "url": "https://github.com/karthikvenkatesan-eaton/Autogen_GraphRAG_Ollama", "source": "github", "axis": "agents", "layer": 0, "stars": 845, "lang": "Python", "desc": "Microsoft's GraphRAG + AutoGen + Ollama + Chainlit = Fully Local & Free Multi-Agent RAG\u00a0Superbot"}
{"type": "node", "id": "repo:jaemil/agentsflow", "kind": "repo", "label": "jaemil/agentsflow", "url": "https://github.com/jaemil/agentsflow", "source": "github", "axis": "agents", "layer": 0, "stars": 350, "lang": "TypeScript", "desc": "Drag & drop UI to build and run a flow of autogen AI agents "}
{"type": "node", "id": "repo:Upsonic/Tiger", "kind": "repo", "label": "Upsonic/Tiger", "url": "https://github.com/Upsonic/Tiger", "source": "github", "axis": "agents", "layer": 0, "stars": 472, "lang": "Python", "desc": "Neuralink for your AI Agents - LangChain - Autogen - CrewAI"}
{"type": "node", "id": "repo:victordibia/designing-multiagent-systems", "kind": "repo", "label": "victordibia/designing-multiagent-systems", "url": "https://github.com/victordibia/designing-multiagent-systems", "source": "github", "axis": "agents", "layer": 0, "stars": 692, "lang": "Python", "desc": "Building LLM-Enabled Multi Agent Applications from Scratch"}
{"type": "node", "id": "repo:Andyinater/AutoGen_EnhancedAgents", "kind": "repo", "label": "Andyinater/AutoGen_EnhancedAgents", "url": "https://github.com/Andyinater/AutoGen_EnhancedAgents", "source": "github", "axis": "agents", "layer": 0, "stars": 116, "lang": "Python", "desc": "This repository holds enhanced Agents, built for the Microsoft AutoGen Framework. Debuting with a MemoryEnabledAgent with improvements in context/token control, portability, and PnP functionality."}
{"type": "node", "id": "repo:microsoft/spec-to-agents", "kind": "repo", "label": "microsoft/spec-to-agents", "url": "https://github.com/microsoft/spec-to-agents", "source": "github", "axis": "agents", "layer": 0, "stars": 110, "lang": "Python", "desc": "A multi-agent event planning workflow built with Microsoft Agent Framework - combining Semantic Kernel's enterprise orchestration with AutoGen's multi-agent patterns."}
{"type": "node", "id": "repo:rnadigital/agentcloud", "kind": "repo", "label": "rnadigital/agentcloud", "url": "https://github.com/rnadigital/agentcloud", "source": "github", "axis": "agents", "layer": 0, "stars": 685, "lang": "TypeScript", "desc": "Agent Cloud is like having your own GPT builder with a bunch extra goodies. The GUI features 1) RAG pipeline which can natively embed 260+ datasources 2) Create Conversational apps (like GPTs) 3) Create Multi Agent process automation apps ("}
{"type": "node", "id": "repo:ksm26/AI-Agentic-Design-Patterns-with-AutoGen", "kind": "repo", "label": "ksm26/AI-Agentic-Design-Patterns-with-AutoGen", "url": "https://github.com/ksm26/AI-Agentic-Design-Patterns-with-AutoGen", "source": "github", "axis": "agents", "layer": 0, "stars": 143, "lang": "Jupyter Notebook", "desc": "Learn to build and customize multi-agent systems using the AutoGen. The course teaches you to implement complex AI applications through agent collaboration and advanced design patterns."}
{"type": "node", "id": "repo:microsoft/magentic-ui", "kind": "repo", "label": "microsoft/magentic-ui", "url": "https://github.com/microsoft/magentic-ui", "source": "github", "axis": "agents", "layer": 0, "stars": 9941, "lang": "Python", "desc": "MagenticLite is an experimental agent that works across the browser and local file system"}
{"type": "node", "id": "repo:Repello-AI/Agent-Wiz", "kind": "repo", "label": "Repello-AI/Agent-Wiz", "url": "https://github.com/Repello-AI/Agent-Wiz", "source": "github", "axis": "agents", "layer": 0, "stars": 381, "lang": "Python", "desc": "A CLI tool for threat modeling and visualizing AI agents built using popular frameworks like LangGraph, AutoGen, CrewAI, and more."}
{"type": "node", "id": "repo:adamwlarson/ai-book-writer", "kind": "repo", "label": "adamwlarson/ai-book-writer", "url": "https://github.com/adamwlarson/ai-book-writer", "source": "github", "axis": "agents", "layer": 0, "stars": 392, "lang": "Python", "desc": "Experimenting with AutoGen to see if an entire book can be written with AI agents"}
{"type": "node", "id": "repo:JayZeeDesign/vision-agent-with-llava", "kind": "repo", "label": "JayZeeDesign/vision-agent-with-llava", "url": "https://github.com/JayZeeDesign/vision-agent-with-llava", "source": "github", "axis": "agents", "layer": 0, "stars": 75, "lang": "Python", "desc": "Agent with vision ability via llava & autogen"}
{"type": "node", "id": "repo:SageMindAI/autogen-agi", "kind": "repo", "label": "SageMindAI/autogen-agi", "url": "https://github.com/SageMindAI/autogen-agi", "source": "github", "axis": "agents", "layer": 0, "stars": 268, "lang": "Python", "desc": "AutoGen AGI: Advancing AI agents using AutoGen towards AGI capabilities. Explore advanced enhancements in group chat dynamics, decision-making, and complex task proficiency. Join our journey in shaping AI's future!"}
{"type": "node", "id": "repo:Azure-Samples/dream-team", "kind": "repo", "label": "Azure-Samples/dream-team", "url": "https://github.com/Azure-Samples/dream-team", "source": "github", "axis": "agents", "layer": 0, "stars": 237, "lang": "TypeScript", "desc": "This repo helps you to build a team of AI agents with Autogen"}
{"type": "node", "id": "repo:ag2ai/fastagency", "kind": "repo", "label": "ag2ai/fastagency", "url": "https://github.com/ag2ai/fastagency", "source": "github", "axis": "agents", "layer": 0, "stars": 544, "lang": "Python", "desc": "The fastest way to bring multi-agent workflows to production."}
{"type": "node", "id": "repo:crewAIInc/crewAI", "kind": "repo", "label": "crewAIInc/crewAI", "url": "https://github.com/crewAIInc/crewAI", "source": "github", "axis": "agents", "layer": 0, "stars": 55067, "lang": "Python", "desc": "Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together smoothly, tackling complex tasks."}
{"type": "node", "id": "repo:crewAIInc/crewAI-examples", "kind": "repo", "label": "crewAIInc/crewAI-examples", "url": "https://github.com/crewAIInc/crewAI-examples", "source": "github", "axis": "agents", "layer": 0, "stars": 6076, "lang": "Jupyter Notebook", "desc": "A collection of examples that show how to use CrewAI framework to automate workflows."}
{"type": "node", "id": "repo:crewAIInc/crewAI-tools", "kind": "repo", "label": "crewAIInc/crewAI-tools", "url": "https://github.com/crewAIInc/crewAI-tools", "source": "github", "axis": "agents", "layer": 0, "stars": 1455, "lang": "Python", "desc": "Extend the capabilities of your CrewAI agents with Tools"}
{"type": "node", "id": "repo:strnad/CrewAI-Studio", "kind": "repo", "label": "strnad/CrewAI-Studio", "url": "https://github.com/strnad/CrewAI-Studio", "source": "github", "axis": "agents", "layer": 0, "stars": 1309, "lang": "Python", "desc": "A user-friendly, multi-platform GUI for managing and running CrewAI agents and tasks. Supports Conda and virtual environments, no coding needed. "}
{"type": "node", "id": "repo:majacinka/crewai-experiments", "kind": "repo", "label": "majacinka/crewai-experiments", "url": "https://github.com/majacinka/crewai-experiments", "source": "github", "axis": "agents", "layer": 0, "stars": 1014, "lang": "Python", "desc": "Experiments with local as well as models available through an api"}
{"type": "node", "id": "repo:crewAIInc/awesome-crewai", "kind": "repo", "label": "crewAIInc/awesome-crewai", "url": "https://github.com/crewAIInc/awesome-crewai", "source": "github", "axis": "agents", "layer": 0, "stars": 502, "lang": "", "desc": "A curated list of open-source projects built by the CrewAI community. Discover, contribute, and extend the possibilities of AI agents with CrewAI."}
{"type": "node", "id": "repo:AbubakrChan/crewai-UI-business-product-launch", "kind": "repo", "label": "AbubakrChan/crewai-UI-business-product-launch", "url": "https://github.com/AbubakrChan/crewai-UI-business-product-launch", "source": "github", "axis": "agents", "layer": 0, "stars": 191, "lang": "Python", "desc": "Streamlit UI for crewai | crewai ui  "}
{"type": "node", "id": "repo:alexfazio/viral-clips-crew", "kind": "repo", "label": "alexfazio/viral-clips-crew", "url": "https://github.com/alexfazio/viral-clips-crew", "source": "github", "axis": "agents", "layer": 0, "stars": 758, "lang": "Python", "desc": "Your CrewAI Powered Video Editing Assistant"}
{"type": "node", "id": "repo:Eng-Elias/CrewAI-Visualizer", "kind": "repo", "label": "Eng-Elias/CrewAI-Visualizer", "url": "https://github.com/Eng-Elias/CrewAI-Visualizer", "source": "github", "axis": "agents", "layer": 0, "stars": 397, "lang": "TypeScript", "desc": "Interactive user interface for CrewAI package."}
{"type": "node", "id": "repo:NanGePlus/CrewAITest", "kind": "repo", "label": "NanGePlus/CrewAITest", "url": "https://github.com/NanGePlus/CrewAITest", "source": "github", "axis": "agents", "layer": 0, "stars": 331, "lang": "Python", "desc": "\u4f7f\u7528CrewAI+FastAPI\u642d\u5efa\u591aAgent\u534f\u4f5c\u5e94\u7528\u5e76\u5bf9\u5916\u63d0\u4f9bAPI\u670d\u52a1\uff0c\u540c\u65f6\u652f\u6301gpt\u3001\u56fd\u4ea7\u5927\u6a21\u578b\u3001Ollama\u672c\u5730\u5927\u6a21\u578b\u3002"}
{"type": "node", "id": "repo:bhancockio/crewai-updated-tutorial-hierarchical", "kind": "repo", "label": "bhancockio/crewai-updated-tutorial-hierarchical", "url": "https://github.com/bhancockio/crewai-updated-tutorial-hierarchical", "source": "github", "axis": "agents", "layer": 0, "stars": 179, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:liangdabiao/easy_investment_Agent_crewai", "kind": "repo", "label": "liangdabiao/easy_investment_Agent_crewai", "url": "https://github.com/liangdabiao/easy_investment_Agent_crewai", "source": "github", "axis": "agents", "layer": 0, "stars": 460, "lang": "Python", "desc": "\u57fa\u4e8eAKShare\u548cCrewAI\u7684A\u80a1\u667a\u80fd\u5206\u6790\u5e73\u53f0\uff0c\u901a\u8fc7\u591aAgent\u534f\u4f5c\u63d0\u4f9b\u4e13\u4e1a\u7684A\u80a1\u6295\u8d44\u5206\u6790\u3002  \ud83d\ude80 \u9879\u76ee\u7279\u8272 \ud83d\udcca \u5168\u9762\u7684A\u80a1\u6570\u636e\u5206\u6790\uff1a\u5b9e\u65f6\u884c\u60c5\u3001\u8d22\u52a1\u6570\u636e\u3001\u8d44\u91d1\u6d41\u5411\u3001\u5e02\u573a\u60c5\u7eea \ud83e\udd16 \u591aAgent\u534f\u4f5c\uff1a4\u4e2a\u4e13\u4e1a\u5316AI\u89d2\u8272\u534f\u540c\u5de5\u4f5c \ud83c\udde8\ud83c\uddf3 A\u80a1\u5e02\u573a\u7279\u8272\uff1a\u9488\u5bf9\u4e2d\u56fd\u80a1\u5e02\u7279\u70b9\u4f18\u5316\u5206\u6790 \ud83d\udcc8 \u4e13\u4e1a\u5206\u6790\u5de5\u5177\uff1a\u57fa\u4e8eAKShare\u7684\u4e13\u4e1a\u6570\u636e\u6e90 \ud83c\udfaf \u667a\u80fd\u6295\u8d44\u5efa\u8bae\uff1a\u7efc\u5408\u5206\u6790\u63d0\u4f9b\u6295\u8d44\u51b3\u7b56\u53c2\u8003"}
{"type": "node", "id": "repo:alexfazio/crewAI-quickstart", "kind": "repo", "label": "alexfazio/crewAI-quickstart", "url": "https://github.com/alexfazio/crewAI-quickstart", "source": "github", "axis": "agents", "layer": 0, "stars": 421, "lang": "Jupyter Notebook", "desc": "A collection of notebooks, cookbooks, and recipes showcasing fun and effective ways to use CrewAI's agentic workflow implementations and tools."}
{"type": "node", "id": "repo:bhancockio/automate-youtube-with-crewai", "kind": "repo", "label": "bhancockio/automate-youtube-with-crewai", "url": "https://github.com/bhancockio/automate-youtube-with-crewai", "source": "github", "axis": "agents", "layer": 0, "stars": 173, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:kid0317/crewai_mas_demo", "kind": "repo", "label": "kid0317/crewai_mas_demo", "url": "https://github.com/kid0317/crewai_mas_demo", "source": "github", "axis": "agents", "layer": 0, "stars": 141, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:definitive-io/crewai-groq", "kind": "repo", "label": "definitive-io/crewai-groq", "url": "https://github.com/definitive-io/crewai-groq", "source": "github", "axis": "agents", "layer": 0, "stars": 105, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:alejandro-ao/crewai-crash-course", "kind": "repo", "label": "alejandro-ao/crewai-crash-course", "url": "https://github.com/alejandro-ao/crewai-crash-course", "source": "github", "axis": "agents", "layer": 0, "stars": 84, "lang": "Python", "desc": "Tutorial: Introduction to CrewAI"}
{"type": "node", "id": "repo:tonykipkemboi/crewai-gmail-automation", "kind": "repo", "label": "tonykipkemboi/crewai-gmail-automation", "url": "https://github.com/tonykipkemboi/crewai-gmail-automation", "source": "github", "axis": "agents", "layer": 0, "stars": 194, "lang": "Python", "desc": "Multi-agent system that automates Gmail inbox management: categorizes emails, applies labels, and generates contextual responses using CrewAI"}
{"type": "node", "id": "repo:bhancockio/nextjs-crewai-basic-tutorial", "kind": "repo", "label": "bhancockio/nextjs-crewai-basic-tutorial", "url": "https://github.com/bhancockio/nextjs-crewai-basic-tutorial", "source": "github", "axis": "agents", "layer": 0, "stars": 140, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:bhancockio/crewai-rag-deep-dive", "kind": "repo", "label": "bhancockio/crewai-rag-deep-dive", "url": "https://github.com/bhancockio/crewai-rag-deep-dive", "source": "github", "axis": "agents", "layer": 0, "stars": 152, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:tom-doerr/dspy_nodes", "kind": "repo", "label": "tom-doerr/dspy_nodes", "url": "https://github.com/tom-doerr/dspy_nodes", "source": "github", "axis": "agents", "layer": 0, "stars": 202, "lang": "Python", "desc": "WIP - Allows you to create DSPy pipelines using ComfyUI"}
{"type": "node", "id": "repo:OmidZamani/dspy-skills", "kind": "repo", "label": "OmidZamani/dspy-skills", "url": "https://github.com/OmidZamani/dspy-skills", "source": "github", "axis": "agents", "layer": 0, "stars": 112, "lang": "Python", "desc": "Collection of Claude Skills for DSPy framework - program language models, optimize prompts, and build RAG pipelines systematically"}
{"type": "node", "id": "repo:neoxelox/dspy-inspector", "kind": "repo", "label": "neoxelox/dspy-inspector", "url": "https://github.com/neoxelox/dspy-inspector", "source": "github", "axis": "agents", "layer": 0, "stars": 45, "lang": "Python", "desc": "DSPy program/pipeline inspector widget for Jupyter/VSCode Notebooks."}
{"type": "node", "id": "repo:iliazlobin/dspy-research", "kind": "repo", "label": "iliazlobin/dspy-research", "url": "https://github.com/iliazlobin/dspy-research", "source": "github", "axis": "agents", "layer": 0, "stars": 10, "lang": "Jupyter Notebook", "desc": "Experiments with DSPy \u2014 declarative, trainable LLM pipelines. Notebooks and demos for evaluating, composing, and optimizing LLM workflows (code-gen, company valuation, market analysis)."}
{"type": "node", "id": "repo:DerwenAI/strwythura", "kind": "repo", "label": "DerwenAI/strwythura", "url": "https://github.com/DerwenAI/strwythura", "source": "github", "axis": "agents", "layer": 0, "stars": 229, "lang": "Python", "desc": "Strwythura: construct an entity-resolved knowledge graph from structured data sources and unstructured content sources, implementing an ontology pipeline, plus context engineering for optimizing AI application outcomes within a specific dom"}
{"type": "node", "id": "repo:o6-webwork/dspy-mlflow", "kind": "repo", "label": "o6-webwork/dspy-mlflow", "url": "https://github.com/o6-webwork/dspy-mlflow", "source": "github", "axis": "agents", "layer": 0, "stars": 0, "lang": "", "desc": "2-week research spike: DSPy programmatic prompting + MLflow lifecycle tracking for Text-to-ESQL pipeline"}
{"type": "node", "id": "repo:aelaguiz/langdspy", "kind": "repo", "label": "aelaguiz/langdspy", "url": "https://github.com/aelaguiz/langdspy", "source": "github", "axis": "agents", "layer": 0, "stars": 7, "lang": "Python", "desc": "Declarative prompting and optimization for LangChain-style pipelines. Enterprise ready."}
{"type": "node", "id": "repo:vardhanam/qdrant_dspy", "kind": "repo", "label": "vardhanam/qdrant_dspy", "url": "https://github.com/vardhanam/qdrant_dspy", "source": "github", "axis": "agents", "layer": 0, "stars": 9, "lang": "Jupyter Notebook", "desc": "Designing a RAG pipeline using Gemma-2b, DSPy, and Qdrant"}
{"type": "node", "id": "repo:avnlp/dspy-opt", "kind": "repo", "label": "avnlp/dspy-opt", "url": "https://github.com/avnlp/dspy-opt", "source": "github", "axis": "agents", "layer": 0, "stars": 10, "lang": "Python", "desc": "Advanced RAG pipeline optimization framework using DSPy. Implements modular RAG pipelines with Query-Rewriting, Sub-Query Decomposition, and Hybrid Search via Weaviate. Automates prompt tuning and few-shot selection using GEPA, SIMBA, MIPRO"}
{"type": "node", "id": "repo:jesk2/dspy-coded", "kind": "repo", "label": "jesk2/dspy-coded", "url": "https://github.com/jesk2/dspy-coded", "source": "github", "axis": "agents", "layer": 0, "stars": 5, "lang": "Python", "desc": "implementations of DSPy programmed pipelines "}
{"type": "node", "id": "repo:thememium/dspy-auto-gepa", "kind": "repo", "label": "thememium/dspy-auto-gepa", "url": "https://github.com/thememium/dspy-auto-gepa", "source": "github", "axis": "agents", "layer": 0, "stars": 9, "lang": "Python", "desc": "AutoGEPA automates the tedious parts of setting up a DSPy optimization pipeline: converting raw data into dspy.Examples, generating a metric file with an LLM, splitting datasets, running baselines, and training with GEPA."}
{"type": "node", "id": "repo:ajkumar-13/Dspy-practice", "kind": "repo", "label": "ajkumar-13/Dspy-practice", "url": "https://github.com/ajkumar-13/Dspy-practice", "source": "github", "axis": "agents", "layer": 0, "stars": 1, "lang": "Python", "desc": "From your first dspy.Predict to enterprise deployment. A comprehensive guide to building programmatic language model pipelines with DSPy,  RLMs, and Reinforcement Learning. Why it works: It hits the high-value technical keywords (RLM, Reinf"}
{"type": "node", "id": "repo:ruvnet/onnx-agent", "kind": "repo", "label": "ruvnet/onnx-agent", "url": "https://github.com/ruvnet/onnx-agent", "source": "github", "axis": "agents", "layer": 0, "stars": 22, "lang": "Python", "desc": "A complete set of requirements\u2014covering UX, CLI, and code\u2014that builds on the previous pipeline for training and optimizing ONNX models with test\u2011time compute methods using DSPy. This document specifies user stories, command\u2010line interface a"}
{"type": "node", "id": "repo:nafew-azim/AUTODSPy", "kind": "repo", "label": "nafew-azim/AUTODSPy", "url": "https://github.com/nafew-azim/AUTODSPy", "source": "github", "axis": "agents", "layer": 0, "stars": 10, "lang": "Jupyter Notebook", "desc": "RL-driven framework that composes modular DSPy pipelines and teleprompters to improve LLM reasoning (experiments use GPT-2)."}
{"type": "node", "id": "repo:kmad/dspy-extraction-skill", "kind": "repo", "label": "kmad/dspy-extraction-skill", "url": "https://github.com/kmad/dspy-extraction-skill", "source": "github", "axis": "agents", "layer": 0, "stars": 2, "lang": "", "desc": "A Claude Code skill for building DSPy extraction, classification, and analysis pipelines"}
{"type": "node", "id": "repo:bhushang19/dspy-rlm-long-docs-demo", "kind": "repo", "label": "bhushang19/dspy-rlm-long-docs-demo", "url": "https://github.com/bhushang19/dspy-rlm-long-docs-demo", "source": "github", "axis": "agents", "layer": 0, "stars": 3, "lang": "Python", "desc": "Practical DSPy RLM demo for extracting structured fields from long documents using Python REPL reasoning, Azure OpenAI, and Markdown-based PDF pipelines."}
{"type": "node", "id": "repo:xanmendelsohn/LLM-Programs-DSPy", "kind": "repo", "label": "xanmendelsohn/LLM-Programs-DSPy", "url": "https://github.com/xanmendelsohn/LLM-Programs-DSPy", "source": "github", "axis": "agents", "layer": 0, "stars": 0, "lang": "Python", "desc": "DSPy LLM Pipelines"}
{"type": "node", "id": "repo:iamtushar04/dspy_pipeline", "kind": "repo", "label": "iamtushar04/dspy_pipeline", "url": "https://github.com/iamtushar04/dspy_pipeline", "source": "github", "axis": "agents", "layer": 0, "stars": 0, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:jaydayal-ai/news-dspy-pipeline", "kind": "repo", "label": "jaydayal-ai/news-dspy-pipeline", "url": "https://github.com/jaydayal-ai/news-dspy-pipeline", "source": "github", "axis": "agents", "layer": 0, "stars": 0, "lang": "Python", "desc": "DSPy pipeline that optimizes a news-summarization prompt using newsdata.io as the data source."}
{"type": "node", "id": "repo:purohit08/RAG-DSPy-Pipeline", "kind": "repo", "label": "purohit08/RAG-DSPy-Pipeline", "url": "https://github.com/purohit08/RAG-DSPy-Pipeline", "source": "github", "axis": "agents", "layer": 0, "stars": 0, "lang": "Python", "desc": "Shows the RAG and DSPY Pipeline with chunking"}
{"type": "node", "id": "repo:langchain-ai/langchain", "kind": "repo", "label": "langchain-ai/langchain", "url": "https://github.com/langchain-ai/langchain", "source": "github", "axis": "agents", "layer": 0, "stars": 141179, "lang": "Python", "desc": "The agent engineering platform."}
{"type": "node", "id": "repo:datawhalechina/llm-universe", "kind": "repo", "label": "datawhalechina/llm-universe", "url": "https://github.com/datawhalechina/llm-universe", "source": "github", "axis": "agents", "layer": 0, "stars": 13421, "lang": "Jupyter Notebook", "desc": "\u672c\u9879\u76ee\u662f\u4e00\u4e2a\u9762\u5411\u5c0f\u767d\u5f00\u53d1\u8005\u7684\u5927\u6a21\u578b\u5e94\u7528\u5f00\u53d1\u6559\u7a0b\uff0c\u5728\u7ebf\u9605\u8bfb\u5730\u5740\uff1ahttps://datawhalechina.github.io/llm-universe/"}
{"type": "node", "id": "repo:langchain4j/langchain4j", "kind": "repo", "label": "langchain4j/langchain4j", "url": "https://github.com/langchain4j/langchain4j", "source": "github", "axis": "agents", "layer": 0, "stars": 12541, "lang": "Java", "desc": "LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agent"}
{"type": "node", "id": "repo:tmc/langchaingo", "kind": "repo", "label": "tmc/langchaingo", "url": "https://github.com/tmc/langchaingo", "source": "github", "axis": "agents", "layer": 0, "stars": 9508, "lang": "Go", "desc": "LangChain for Go, the easiest way to write LLM-based programs in Go"}
{"type": "node", "id": "repo:daveebbelaar/langchain-experiments", "kind": "repo", "label": "daveebbelaar/langchain-experiments", "url": "https://github.com/daveebbelaar/langchain-experiments", "source": "github", "axis": "agents", "layer": 0, "stars": 1139, "lang": "Jupyter Notebook", "desc": "Building Apps with LLMs"}
{"type": "node", "id": "repo:chatchat-space/Langchain-Chatchat", "kind": "repo", "label": "chatchat-space/Langchain-Chatchat", "url": "https://github.com/chatchat-space/Langchain-Chatchat", "source": "github", "axis": "agents", "layer": 0, "stars": 38265, "lang": "Python", "desc": "Langchain-Chatchat\uff08\u539fLangchain-ChatGLM\uff09\u57fa\u4e8e Langchain \u4e0e ChatGLM, Qwen \u4e0e Llama \u7b49\u8bed\u8a00\u6a21\u578b\u7684 RAG \u4e0e Agent \u5e94\u7528 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain "}
{"type": "node", "id": "repo:kyrolabs/awesome-langchain", "kind": "repo", "label": "kyrolabs/awesome-langchain", "url": "https://github.com/kyrolabs/awesome-langchain", "source": "github", "axis": "agents", "layer": 0, "stars": 9442, "lang": "", "desc": "\ud83d\ude0e Awesome list of tools and projects with the awesome LangChain framework"}
{"type": "node", "id": "repo:codebasics/langchain", "kind": "repo", "label": "codebasics/langchain", "url": "https://github.com/codebasics/langchain", "source": "github", "axis": "agents", "layer": 0, "stars": 195, "lang": "Jupyter Notebook", "desc": "Tutorial for langchain LLM library"}
{"type": "node", "id": "repo:patterns-ai-core/langchainrb", "kind": "repo", "label": "patterns-ai-core/langchainrb", "url": "https://github.com/patterns-ai-core/langchainrb", "source": "github", "axis": "agents", "layer": 0, "stars": 1989, "lang": "Ruby", "desc": "Build LLM-powered applications in Ruby"}
{"type": "node", "id": "repo:brainlid/langchain", "kind": "repo", "label": "brainlid/langchain", "url": "https://github.com/brainlid/langchain", "source": "github", "axis": "agents", "layer": 0, "stars": 1176, "lang": "Elixir", "desc": "Elixir implementation of a LangChain style framework that lets Elixir projects integrate with and leverage LLMs."}
{"type": "node", "id": "repo:kaushikb11/awesome-llm-agents", "kind": "repo", "label": "kaushikb11/awesome-llm-agents", "url": "https://github.com/kaushikb11/awesome-llm-agents", "source": "github", "axis": "agents", "layer": 0, "stars": 1525, "lang": "Python", "desc": "A curated list of awesome LLM agents frameworks."}
{"type": "node", "id": "repo:davidmigloz/langchain_dart", "kind": "repo", "label": "davidmigloz/langchain_dart", "url": "https://github.com/davidmigloz/langchain_dart", "source": "github", "axis": "agents", "layer": 0, "stars": 682, "lang": "Dart", "desc": "Build LLM-powered Dart/Flutter applications."}
{"type": "node", "id": "repo:onlyphantom/llm-python", "kind": "repo", "label": "onlyphantom/llm-python", "url": "https://github.com/onlyphantom/llm-python", "source": "github", "axis": "agents", "layer": 0, "stars": 923, "lang": "Jupyter Notebook", "desc": "Large Language Models (LLMs) tutorials & sample scripts, ft. langchain, openai, llamaindex, gpt, chromadb & pinecone"}
{"type": "node", "id": "repo:zilliztech/GPTCache", "kind": "repo", "label": "zilliztech/GPTCache", "url": "https://github.com/zilliztech/GPTCache", "source": "github", "axis": "agents", "layer": 0, "stars": 8088, "lang": "Python", "desc": "Semantic cache for LLMs. Fully integrated with LangChain and llama_index. "}
{"type": "node", "id": "repo:quarkiverse/quarkus-langchain4j", "kind": "repo", "label": "quarkiverse/quarkus-langchain4j", "url": "https://github.com/quarkiverse/quarkus-langchain4j", "source": "github", "axis": "agents", "layer": 0, "stars": 308, "lang": "Java", "desc": "Quarkus Langchain4j extension"}
{"type": "node", "id": "repo:huangjia2019/langchain-in-action", "kind": "repo", "label": "huangjia2019/langchain-in-action", "url": "https://github.com/huangjia2019/langchain-in-action", "source": "github", "axis": "agents", "layer": 0, "stars": 760, "lang": "Python", "desc": "Practical LangChain patterns and implementations for real-world LLM applications. \u6781\u5ba2\u65f6\u95f4\uff1aLangChain\u5b9e\u6218\u8bfe - \u8fd9\u662fLangChain\u6846\u67b6\u65e9\u671f\u8bbe\u8ba1\u7684\u4e00\u7cfb\u5217\u91cd\u70b9\u6a21\u5757\u7684\u76f4\u63a5\u800c\u6e05\u6670\u7684\u793a\u4f8b\u548c\u8bb2\u89e3\u3002\u968f\u7740LangChain\u7684\u5feb\u901f\u6f14\u8fdb\uff0c\u6709\u4e9b\u4ee3\u7801\u9700\u8981\u5b89\u88c5\u65b0\u7684\u7248\u672c\u8fdb\u884c\u8fed\u4ee3\u3002\u5e0c\u671b\u5927\u5bb6\u5728\u5feb\u901f\u6d4f\u89c8\u8bfe\u7a0b\u6982\u5ff5\uff08\u4ecd\u6709\u4ef7\u503c\uff09\u7684\u540c\u65f6\uff0c\u81ea\u884c\u5b66\u4e60LangChain\u6700\u65b0\u7684\u4ee3\u7801\u548c\u8fdb\u5c55\u3002"}
{"type": "node", "id": "repo:bragai/bRAG-langchain", "kind": "repo", "label": "bragai/bRAG-langchain", "url": "https://github.com/bragai/bRAG-langchain", "source": "github", "axis": "agents", "layer": 0, "stars": 4136, "lang": "Jupyter Notebook", "desc": "Everything you need to know to build your own RAG application"}
{"type": "node", "id": "repo:intel/ipex-llm", "kind": "repo", "label": "intel/ipex-llm", "url": "https://github.com/intel/ipex-llm", "source": "github", "axis": "agents", "layer": 0, "stars": 8860, "lang": "Python", "desc": "Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamles"}
{"type": "node", "id": "repo:alphasecio/langchain-examples", "kind": "repo", "label": "alphasecio/langchain-examples", "url": "https://github.com/alphasecio/langchain-examples", "source": "github", "axis": "agents", "layer": 0, "stars": 549, "lang": "Python", "desc": "A collection of apps powered by the LangChain LLM framework."}
{"type": "node", "id": "repo:X-D-Lab/LangChain-ChatGLM-Webui", "kind": "repo", "label": "X-D-Lab/LangChain-ChatGLM-Webui", "url": "https://github.com/X-D-Lab/LangChain-ChatGLM-Webui", "source": "github", "axis": "agents", "layer": 0, "stars": 3315, "lang": "Python", "desc": "\u57fa\u4e8eLangChain\u548cChatGLM-6B\u7b49\u7cfb\u5217LLM\u7684\u9488\u5bf9\u672c\u5730\u77e5\u8bc6\u5e93\u7684\u81ea\u52a8\u95ee\u7b54"}
{"type": "node", "id": "repo:langchain-ai/langgraph", "kind": "repo", "label": "langchain-ai/langgraph", "url": "https://github.com/langchain-ai/langgraph", "source": "github", "axis": "agents", "layer": 0, "stars": 36686, "lang": "Python", "desc": "Build resilient agents."}
{"type": "node", "id": "repo:google-gemini/gemini-fullstack-langgraph-quickstart", "kind": "repo", "label": "google-gemini/gemini-fullstack-langgraph-quickstart", "url": "https://github.com/google-gemini/gemini-fullstack-langgraph-quickstart", "source": "github", "axis": "agents", "layer": 0, "stars": 18245, "lang": "Jupyter Notebook", "desc": "Get started with building Fullstack Agents using Gemini 2.5 and LangGraph"}
{"type": "node", "id": "repo:langgraph4j/langgraph4j", "kind": "repo", "label": "langgraph4j/langgraph4j", "url": "https://github.com/langgraph4j/langgraph4j", "source": "github", "axis": "agents", "layer": 0, "stars": 1799, "lang": "Java", "desc": "\ud83d\ude80 LangGraph for Java. A library for develop AI Agentic Architectures in the Java ecosystem. Designed to work smoothly with both Langchain4j and Spring AI."}
{"type": "node", "id": "repo:langchain-ai/langgraphjs", "kind": "repo", "label": "langchain-ai/langgraphjs", "url": "https://github.com/langchain-ai/langgraphjs", "source": "github", "axis": "agents", "layer": 0, "stars": 3093, "lang": "TypeScript", "desc": "Framework to build resilient language agents as graphs."}
{"type": "node", "id": "repo:mayooear/ai-pdf-chatbot-langchain", "kind": "repo", "label": "mayooear/ai-pdf-chatbot-langchain", "url": "https://github.com/mayooear/ai-pdf-chatbot-langchain", "source": "github", "axis": "agents", "layer": 0, "stars": 16565, "lang": "TypeScript", "desc": "AI PDF chatbot agent built with LangChain & LangGraph "}
{"type": "node", "id": "repo:langchain-ai/langgraph-example", "kind": "repo", "label": "langchain-ai/langgraph-example", "url": "https://github.com/langchain-ai/langgraph-example", "source": "github", "axis": "agents", "layer": 0, "stars": 512, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:harishneel1/langgraph", "kind": "repo", "label": "harishneel1/langgraph", "url": "https://github.com/harishneel1/langgraph", "source": "github", "axis": "agents", "layer": 0, "stars": 223, "lang": "Jupyter Notebook", "desc": ""}
{"type": "node", "id": "repo:emarco177/langgraph-course", "kind": "repo", "label": "emarco177/langgraph-course", "url": "https://github.com/emarco177/langgraph-course", "source": "github", "axis": "agents", "layer": 0, "stars": 609, "lang": "", "desc": "Hands-on LangGraph course repo for building production-grade LLM agents with Agentic RAG, ReAct, and reflection workflows."}
{"type": "node", "id": "repo:vonzosten/awesome-LangGraph", "kind": "repo", "label": "vonzosten/awesome-LangGraph", "url": "https://github.com/vonzosten/awesome-LangGraph", "source": "github", "axis": "agents", "layer": 0, "stars": 1890, "lang": "JavaScript", "desc": "An index of the LangChain + LangGraph ecosystem: concepts, projects, tools, templates, and guides for LLM & multi-agent apps."}
{"type": "node", "id": "repo:krishnaik06/Agentic-LanggraphCrash-course", "kind": "repo", "label": "krishnaik06/Agentic-LanggraphCrash-course", "url": "https://github.com/krishnaik06/Agentic-LanggraphCrash-course", "source": "github", "axis": "agents", "layer": 0, "stars": 174, "lang": "Jupyter Notebook", "desc": ""}
{"type": "node", "id": "repo:langchain-ai/new-langgraph-project", "kind": "repo", "label": "langchain-ai/new-langgraph-project", "url": "https://github.com/langchain-ai/new-langgraph-project", "source": "github", "axis": "agents", "layer": 0, "stars": 280, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:langchain-ai/langgraph-supervisor-py", "kind": "repo", "label": "langchain-ai/langgraph-supervisor-py", "url": "https://github.com/langchain-ai/langgraph-supervisor-py", "source": "github", "axis": "agents", "layer": 0, "stars": 1618, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:wassim249/fastapi-langgraph-agent-production-ready-template", "kind": "repo", "label": "wassim249/fastapi-langgraph-agent-production-ready-template", "url": "https://github.com/wassim249/fastapi-langgraph-agent-production-ready-template", "source": "github", "axis": "agents", "layer": 0, "stars": 2485, "lang": "Python", "desc": "A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agent services."}
{"type": "node", "id": "repo:langchain-ai/langgraph-swarm-py", "kind": "repo", "label": "langchain-ai/langgraph-swarm-py", "url": "https://github.com/langchain-ai/langgraph-swarm-py", "source": "github", "axis": "agents", "layer": 0, "stars": 1536, "lang": "Python", "desc": "For your multi-agent needs"}
{"type": "node", "id": "repo:braincrew-lab/langgraph-mcp-agents", "kind": "repo", "label": "braincrew-lab/langgraph-mcp-agents", "url": "https://github.com/braincrew-lab/langgraph-mcp-agents", "source": "github", "axis": "agents", "layer": 0, "stars": 709, "lang": "Python", "desc": "LangGraph-powered ReAct agent with Model Context Protocol (MCP) integration. A Streamlit web interface for dynamically configuring, deploying, and interacting with AI agents capable of accessing various data sources and APIs through MCP too"}
{"type": "node", "id": "repo:BrandPeng/Langchain1.0-Langgraph1.0-Learning", "kind": "repo", "label": "BrandPeng/Langchain1.0-Langgraph1.0-Learning", "url": "https://github.com/BrandPeng/Langchain1.0-Langgraph1.0-Learning", "source": "github", "axis": "agents", "layer": 0, "stars": 571, "lang": "Python", "desc": "\u8fd9\u662f\u4e00\u4e2a LangChain 1.0 \u548c LangGraph 1.0 \u7684\u5b66\u4e60\u4ed3\u5e93\uff0c\u5b66\u4e60\u5982\u4f55\u8fdb\u884cagent\u5f00\u53d1\uff0c\u6db5\u76d6\u4ece\u57fa\u7840\u6982\u5ff5\u5230\u5b9e\u6218\u9879\u76ee\u7684\u5b8c\u6574\u5b66\u4e60\u8def\u5f84\u3002"}
{"type": "node", "id": "repo:langchain-ai/react-agent", "kind": "repo", "label": "langchain-ai/react-agent", "url": "https://github.com/langchain-ai/react-agent", "source": "github", "axis": "agents", "layer": 0, "stars": 789, "lang": "Python", "desc": "LangGraph template for a simple ReAct agent"}
{"type": "node", "id": "repo:LangChain-OpenTutorial/LangChain-OpenTutorial", "kind": "repo", "label": "LangChain-OpenTutorial/LangChain-OpenTutorial", "url": "https://github.com/LangChain-OpenTutorial/LangChain-OpenTutorial", "source": "github", "axis": "agents", "layer": 0, "stars": 1088, "lang": "Jupyter Notebook", "desc": "LangChain, LangGraph Open Tutorial for everyone!"}
{"type": "node", "id": "repo:langchain-ai/langgraph-101", "kind": "repo", "label": "langchain-ai/langgraph-101", "url": "https://github.com/langchain-ai/langgraph-101", "source": "github", "axis": "agents", "layer": 0, "stars": 505, "lang": "Jupyter Notebook", "desc": "Learn about the fundamentals of LangGraph through a series of notebooks"}
{"type": "node", "id": "repo:campusx-official/langgraph-tutorials", "kind": "repo", "label": "campusx-official/langgraph-tutorials", "url": "https://github.com/campusx-official/langgraph-tutorials", "source": "github", "axis": "agents", "layer": 0, "stars": 204, "lang": "Jupyter Notebook", "desc": "Codes related to my LangGraph playlist"}
{"type": "node", "id": "repo:FoundationAgents/MetaGPT", "kind": "repo", "label": "FoundationAgents/MetaGPT", "url": "https://github.com/FoundationAgents/MetaGPT", "source": "github", "axis": "agents", "layer": 0, "stars": 69241, "lang": "Python", "desc": "\ud83c\udf1f The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming"}
{"type": "node", "id": "repo:datawhalechina/hugging-multi-agent", "kind": "repo", "label": "datawhalechina/hugging-multi-agent", "url": "https://github.com/datawhalechina/hugging-multi-agent", "source": "github", "axis": "agents", "layer": 0, "stars": 1402, "lang": "CSS", "desc": "A tutorial based on MetaGPT to quickly help you understand the concept of agent and muti-agent and get started with coding development. \u57fa\u4e8eMetaGPT\u7684\u591a\u667a\u80fd\u4f53\u5165\u95e8\u4e0e\u5f00\u53d1\u6559\u7a0b"}
{"type": "node", "id": "repo:geekan/MetaGPT-docs", "kind": "repo", "label": "geekan/MetaGPT-docs", "url": "https://github.com/geekan/MetaGPT-docs", "source": "github", "axis": "agents", "layer": 0, "stars": 108, "lang": "Vue", "desc": ""}
{"type": "node", "id": "repo:NanGePlus/MetaGPTTest", "kind": "repo", "label": "NanGePlus/MetaGPTTest", "url": "https://github.com/NanGePlus/MetaGPTTest", "source": "github", "axis": "agents", "layer": 0, "stars": 43, "lang": "Python", "desc": "\u5f00\u6e90\u591aAgent\u667a\u80fd\u4f53\u534f\u4f5c\u6846\u67b6MetaGPT\u6838\u5fc3\u6982\u5ff5\u4ecb\u7ecd\u53ca\u76f8\u5173\u6848\u4f8b\u6d4b\u8bd5"}
{"type": "node", "id": "repo:qianyouliang/MetaGPT-Learn", "kind": "repo", "label": "qianyouliang/MetaGPT-Learn", "url": "https://github.com/qianyouliang/MetaGPT-Learn", "source": "github", "axis": "agents", "layer": 0, "stars": 46, "lang": "Jupyter Notebook", "desc": "\u8fd9\u4e2a\u4ed3\u5e93\u4e3b\u8981\u7528\u4e8e\u8bb0\u5f55\u4ee5MetaGPT\u4e3a\u57fa\u7840\u7684Agent\u5f00\u53d1\u7406\u8bba\u5b66\u4e60\u8bb0\u5f55 "}
{"type": "node", "id": "repo:FoundationAgents/MetaGPT-Ext", "kind": "repo", "label": "FoundationAgents/MetaGPT-Ext", "url": "https://github.com/FoundationAgents/MetaGPT-Ext", "source": "github", "axis": "agents", "layer": 0, "stars": 9, "lang": "", "desc": "MetaGPT Extension Repo"}
{"type": "node", "id": "repo:Ori-Replication/MetaGPT_webui", "kind": "repo", "label": "Ori-Replication/MetaGPT_webui", "url": "https://github.com/Ori-Replication/MetaGPT_webui", "source": "github", "axis": "agents", "layer": 0, "stars": 18, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:FSoft-AI4Code/AgileCoder", "kind": "repo", "label": "FSoft-AI4Code/AgileCoder", "url": "https://github.com/FSoft-AI4Code/AgileCoder", "source": "github", "axis": "agents", "layer": 0, "stars": 463, "lang": "Python", "desc": "[FORGE 2025] Incorporating Agile methodology into agents to create complex real-world softwares"}
{"type": "node", "id": "repo:Lin-A1/novel-agent", "kind": "repo", "label": "Lin-A1/novel-agent", "url": "https://github.com/Lin-A1/novel-agent", "source": "github", "axis": "agents", "layer": 0, "stars": 13, "lang": "Python", "desc": "metagpt\u5b9e\u73b0\u591aagent workflow\u751f\u6210\u5c0f\u8bf4"}
{"type": "node", "id": "repo:andrepimenta/metagpt-app", "kind": "repo", "label": "andrepimenta/metagpt-app", "url": "https://github.com/andrepimenta/metagpt-app", "source": "github", "axis": "agents", "layer": 0, "stars": 5, "lang": "TypeScript", "desc": "Frontend for MetaGPT"}
{"type": "node", "id": "repo:kemeny/PongGame", "kind": "repo", "label": "kemeny/PongGame", "url": "https://github.com/kemeny/PongGame", "source": "github", "axis": "agents", "layer": 0, "stars": 14, "lang": "Python", "desc": "A game of pong made by MetaGPT and ChatGPT Code Interpreter"}
{"type": "node", "id": "repo:startino/aitino", "kind": "repo", "label": "startino/aitino", "url": "https://github.com/startino/aitino", "source": "github", "axis": "agents", "layer": 0, "stars": 90, "lang": "Python", "desc": "Aitino is a platform that allows for the creation of crews of AI Agents to help you automate tasks and solve complex problems."}
{"type": "node", "id": "repo:scmpevatrons/ai-chatverse", "kind": "repo", "label": "scmpevatrons/ai-chatverse", "url": "https://github.com/scmpevatrons/ai-chatverse", "source": "github", "axis": "agents", "layer": 0, "stars": 19, "lang": "Python", "desc": "A streamlit application to play with LLM Models"}
{"type": "node", "id": "repo:FoundationAgents/MetaGPT-App", "kind": "repo", "label": "FoundationAgents/MetaGPT-App", "url": "https://github.com/FoundationAgents/MetaGPT-App", "source": "github", "axis": "agents", "layer": 0, "stars": 1, "lang": "", "desc": "MetaGPT Application Repo"}
{"type": "node", "id": "repo:vivy-yi/awesome-agent-orchestration", "kind": "repo", "label": "vivy-yi/awesome-agent-orchestration", "url": "https://github.com/vivy-yi/awesome-agent-orchestration", "source": "github", "axis": "agents", "layer": 0, "stars": 22, "lang": "", "desc": "\u2b50 Curated list of AI Agent frameworks: AutoGen, CrewAI, MetaGPT, LangGraph, Swarms. Multi-Agent Systems, Swarm Intelligence, A2A Protocol, MCP Protocol. LLM Agents, Agentic AI, Agent Workflows."}
{"type": "node", "id": "repo:alitrack/QuickStart-MetaGPT", "kind": "repo", "label": "alitrack/QuickStart-MetaGPT", "url": "https://github.com/alitrack/QuickStart-MetaGPT", "source": "github", "axis": "agents", "layer": 0, "stars": 5, "lang": "Shell", "desc": "Nothing but MetaGPT QuickStart"}
{"type": "node", "id": "repo:time1527/TeaChat", "kind": "repo", "label": "time1527/TeaChat", "url": "https://github.com/time1527/TeaChat", "source": "github", "axis": "agents", "layer": 0, "stars": 3, "lang": "Python", "desc": "LangChain + MetaGPT RAG"}
{"type": "node", "id": "repo:cerberuswilliam/MetaGPT", "kind": "repo", "label": "cerberuswilliam/MetaGPT", "url": "https://github.com/cerberuswilliam/MetaGPT", "source": "github", "axis": "agents", "layer": 0, "stars": 1, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:minhnn-tiny/MetaGPT_examples", "kind": "repo", "label": "minhnn-tiny/MetaGPT_examples", "url": "https://github.com/minhnn-tiny/MetaGPT_examples", "source": "github", "axis": "agents", "layer": 0, "stars": 3, "lang": "Python", "desc": "Some examples come from MetaGPT framework."}
{"type": "node", "id": "repo:evanshlom/MetaGPT-app", "kind": "repo", "label": "evanshlom/MetaGPT-app", "url": "https://github.com/evanshlom/MetaGPT-app", "source": "github", "axis": "agents", "layer": 0, "stars": 1, "lang": "Python", "desc": "Dashboard metadata chatbot for executive officers to retrieve information and guidance to desired information, for corporation with many dashboards, using data dictionaries to connect source information among all dashboards."}
{"type": "node", "id": "repo:microsoft/agent-framework", "kind": "repo", "label": "microsoft/agent-framework", "url": "https://github.com/microsoft/agent-framework", "source": "github", "axis": "agents", "layer": 0, "stars": 11922, "lang": "Python", "desc": "A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET."}
{"type": "node", "id": "repo:Ingenimax/agent-sdk-go", "kind": "repo", "label": "Ingenimax/agent-sdk-go", "url": "https://github.com/Ingenimax/agent-sdk-go", "source": "github", "axis": "agents", "layer": 0, "stars": 579, "lang": "Go", "desc": "A powerful Go framework for building production-ready AI agents!"}
{"type": "node", "id": "repo:polyuiislab/infiAgent", "kind": "repo", "label": "polyuiislab/infiAgent", "url": "https://github.com/polyuiislab/infiAgent", "source": "github", "axis": "agents", "layer": 0, "stars": 1181, "lang": "Python", "desc": "Build your own Cowork, AI Scientist and other SoTA Agents just by editing config files. Support anthropic skills. An infinite-horizon agent framework designed for long-running, complex tasks."}
{"type": "node", "id": "repo:e2b-dev/awesome-ai-sdks", "kind": "repo", "label": "e2b-dev/awesome-ai-sdks", "url": "https://github.com/e2b-dev/awesome-ai-sdks", "source": "github", "axis": "agents", "layer": 0, "stars": 1197, "lang": "", "desc": "A database of SDKs, frameworks, libraries, and tools for creating, monitoring, debugging and deploying autonomous AI agents"}
{"type": "node", "id": "repo:aws/bedrock-agentcore-sdk-python", "kind": "repo", "label": "aws/bedrock-agentcore-sdk-python", "url": "https://github.com/aws/bedrock-agentcore-sdk-python", "source": "github", "axis": "agents", "layer": 0, "stars": 738, "lang": "Python", "desc": "Python SDK for transforming any AI agent into a production-ready application. Framework-agnostic primitives for runtime, memory, authentication, and tools with AWS-managed infrastructure."}
{"type": "node", "id": "repo:raga-ai-hub/RagaAI-Catalyst", "kind": "repo", "label": "raga-ai-hub/RagaAI-Catalyst", "url": "https://github.com/raga-ai-hub/RagaAI-Catalyst", "source": "github", "axis": "agents", "layer": 0, "stars": 16145, "lang": "Python", "desc": "Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced analytics with timeline and execution graph "}
{"type": "node", "id": "repo:symbolica-ai/agentica-python-sdk", "kind": "repo", "label": "symbolica-ai/agentica-python-sdk", "url": "https://github.com/symbolica-ai/agentica-python-sdk", "source": "github", "axis": "agents", "layer": 0, "stars": 181, "lang": "Python", "desc": "The official Python SDK for the Agentica agent framework from Symbolica"}
{"type": "node", "id": "repo:PaddlePaddle/ERNIE-SDK", "kind": "repo", "label": "PaddlePaddle/ERNIE-SDK", "url": "https://github.com/PaddlePaddle/ERNIE-SDK", "source": "github", "axis": "agents", "layer": 0, "stars": 376, "lang": "Jupyter Notebook", "desc": "ERNIE Bot Agent is a Large Language Model (LLM) Agent Framework, powered by the advanced capabilities of ERNIE Bot and the platform resources of Baidu AI Studio."}
{"type": "node", "id": "repo:openserv-labs/sdk", "kind": "repo", "label": "openserv-labs/sdk", "url": "https://github.com/openserv-labs/sdk", "source": "github", "axis": "agents", "layer": 0, "stars": 134, "lang": "TypeScript", "desc": "A powerful TypeScript framework for building non-deterministic AI agents with advanced cognitive capabilities like reasoning, decision-making, and inter-agent collaboration within the OpenServ platform. Built with strong typing, extensible "}
{"type": "node", "id": "repo:cacheplane/angular-agent-framework", "kind": "repo", "label": "cacheplane/angular-agent-framework", "url": "https://github.com/cacheplane/angular-agent-framework", "source": "github", "axis": "agents", "layer": 0, "stars": 100, "lang": "TypeScript", "desc": "Angular SDK for Building Agentic Apps + Generative UI"}
{"type": "node", "id": "repo:NapthaAI/naptha-sdk", "kind": "repo", "label": "NapthaAI/naptha-sdk", "url": "https://github.com/NapthaAI/naptha-sdk", "source": "github", "axis": "agents", "layer": 0, "stars": 179, "lang": "Python", "desc": "Naptha is a framework and infrastructure for developing and running multi-agent systems at scale with heterogeneous models, architectures and data"}
{"type": "node", "id": "repo:symbolica-ai/agentica-typescript-sdk", "kind": "repo", "label": "symbolica-ai/agentica-typescript-sdk", "url": "https://github.com/symbolica-ai/agentica-typescript-sdk", "source": "github", "axis": "agents", "layer": 0, "stars": 65, "lang": "TypeScript", "desc": "The official TypeScript SDK for the Agentica agent framework from Symbolica"}
{"type": "node", "id": "repo:sslava/ai-sdk-agents", "kind": "repo", "label": "sslava/ai-sdk-agents", "url": "https://github.com/sslava/ai-sdk-agents", "source": "github", "axis": "agents", "layer": 0, "stars": 209, "lang": "TypeScript", "desc": "A flexible toolkit for building, running, and managing AI-powered agents - built on top of the Vercel AI SDK. Integrates smoothly with your favorite frameworks."}
{"type": "node", "id": "repo:sentient-engineering/sentient", "kind": "repo", "label": "sentient-engineering/sentient", "url": "https://github.com/sentient-engineering/sentient", "source": "github", "axis": "agents", "layer": 0, "stars": 569, "lang": "Python", "desc": "the framework/ sdk that lets you build browser controlling agents in 3 lines of code. join chat @ https://discord.gg/umgnyQU2K8"}
{"type": "node", "id": "repo:atomicstrata/atomicmemory", "kind": "repo", "label": "atomicstrata/atomicmemory", "url": "https://github.com/atomicstrata/atomicmemory", "source": "github", "axis": "agents", "layer": 0, "stars": 434, "lang": "TypeScript", "desc": "Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins."}
{"type": "node", "id": "repo:hybroai/a2a-adapter", "kind": "repo", "label": "hybroai/a2a-adapter", "url": "https://github.com/hybroai/a2a-adapter", "source": "github", "axis": "agents", "layer": 0, "stars": 89, "lang": "Python", "desc": "Open Source A2A Protocol Adapter SDK for Different Agent Frameworks"}
{"type": "node", "id": "repo:maker-community/ElectronBot.DotNet", "kind": "repo", "label": "maker-community/ElectronBot.DotNet", "url": "https://github.com/maker-community/ElectronBot.DotNet", "source": "github", "axis": "agents", "layer": 0, "stars": 206, "lang": "C#", "desc": "\u4e00\u4e2a\u4e3aElectronBot\u673a\u5668\u4eba\u548c\u701a\u6587\u952e\u76d8\uff08HelloWorldKeyboard\uff09\u5f00\u53d1\u7684\u4e0a\u4f4d\u673a\u8f6f\u4ef6\uff08\u5305\u542b\u673a\u5668\u4ebaUSB\u64cd\u4f5cSDK\u548c\u701a\u6587\u952e\u76d8HID\u64cd\u4f5cSDK\uff09\uff0c\u91c7\u7528Windows App SDK\u6846\u67b6\u7f16\u5199\u754c\u9762\u3002   A host computer software developed for ElectronBot robots (including robot USB operation SDK), using the Windows App SDK framework to "}
{"type": "node", "id": "repo:chrispangg/deepagentsdk", "kind": "repo", "label": "chrispangg/deepagentsdk", "url": "https://github.com/chrispangg/deepagentsdk", "source": "github", "axis": "agents", "layer": 0, "stars": 126, "lang": "TypeScript", "desc": "A Deep Agent Harness framework built with Vercel's AI SDK v6"}
{"type": "node", "id": "repo:coleam00/evolution-of-ai-agents", "kind": "repo", "label": "coleam00/evolution-of-ai-agents", "url": "https://github.com/coleam00/evolution-of-ai-agents", "source": "github", "axis": "agents", "layer": 0, "stars": 37, "lang": "Python", "desc": "Three working examples showing how AI agent development evolved - from traditional RAG to batteries-included SDKs and skill-based frameworks"}
{"type": "node", "id": "repo:huggingface/agents-course", "kind": "repo", "label": "huggingface/agents-course", "url": "https://github.com/huggingface/agents-course", "source": "github", "axis": "agents", "layer": 0, "stars": 29873, "lang": "MDX", "desc": "This repository contains the Hugging Face Agents Course. "}
{"type": "node", "id": "repo:ALucek/smolagents-guide", "kind": "repo", "label": "ALucek/smolagents-guide", "url": "https://github.com/ALucek/smolagents-guide", "source": "github", "axis": "agents", "layer": 0, "stars": 50, "lang": "Jupyter Notebook", "desc": "A walk through HuggingFace smolagents"}
{"type": "node", "id": "repo:sinanuozdemir/oreilly-huggingface-tour", "kind": "repo", "label": "sinanuozdemir/oreilly-huggingface-tour", "url": "https://github.com/sinanuozdemir/oreilly-huggingface-tour", "source": "github", "axis": "agents", "layer": 0, "stars": 70, "lang": "Jupyter Notebook", "desc": "A Crash Course in Hugging Face"}
{"type": "node", "id": "repo:mstrYoda/llm-agents-example", "kind": "repo", "label": "mstrYoda/llm-agents-example", "url": "https://github.com/mstrYoda/llm-agents-example", "source": "github", "axis": "agents", "layer": 0, "stars": 41, "lang": "Python", "desc": "An example repository to use HuggingFace smolagents, Phidata and CrewAI frameworks with local LLMs"}
{"type": "node", "id": "repo:aniemerg/smolcc", "kind": "repo", "label": "aniemerg/smolcc", "url": "https://github.com/aniemerg/smolcc", "source": "github", "axis": "agents", "layer": 0, "stars": 41, "lang": "Python", "desc": "A lightweight code assistant with tool-using capabilities built on HuggingFace's smolagents."}
{"type": "node", "id": "repo:Snowflake-Labs/sfguide-build-agentic-workflows-with-huggingface-smolagents-in-snowflake", "kind": "repo", "label": "Snowflake-Labs/sfguide-build-agentic-workflows-with-huggingface-smolagents-in-snowflake", "url": "https://github.com/Snowflake-Labs/sfguide-build-agentic-workflows-with-huggingface-smolagents-in-snowflake", "source": "github", "axis": "agents", "layer": 0, "stars": 7, "lang": "Jupyter Notebook", "desc": ""}
{"type": "node", "id": "repo:chiarapaglioni/GAIA-agents", "kind": "repo", "label": "chiarapaglioni/GAIA-agents", "url": "https://github.com/chiarapaglioni/GAIA-agents", "source": "github", "axis": "agents", "layer": 0, "stars": 4, "lang": "Python", "desc": "Final project for the Hugging Face AI Agents course testing smolagents on the GAIA benchmark"}
{"type": "node", "id": "repo:antunsz/smolagents-crew", "kind": "repo", "label": "antunsz/smolagents-crew", "url": "https://github.com/antunsz/smolagents-crew", "source": "github", "axis": "agents", "layer": 0, "stars": 12, "lang": "Python", "desc": "A framework to orchestrate multiple AI agents, enabling them to collaborate efficiently through smart threading, dependency management, context sharing, and distributed execution via a built-in swarm system. Built on top of smolagents, it a"}
{"type": "node", "id": "repo:rizome-dev/go-smolagents", "kind": "repo", "label": "rizome-dev/go-smolagents", "url": "https://github.com/rizome-dev/go-smolagents", "source": "github", "axis": "agents", "layer": 0, "stars": 3, "lang": "Go", "desc": "\ud83e\udd17 huggingface/smolagents, but pure go"}
{"type": "node", "id": "repo:VladKha/drone-agent", "kind": "repo", "label": "VladKha/drone-agent", "url": "https://github.com/VladKha/drone-agent", "source": "github", "axis": "agents", "layer": 0, "stars": 3, "lang": "Python", "desc": "Drone autonomy powered by Generative AI (HuggingFace smolagents + Google Gemini)"}
{"type": "node", "id": "repo:botextractai/ai-huggingface-smolagents", "kind": "repo", "label": "botextractai/ai-huggingface-smolagents", "url": "https://github.com/botextractai/ai-huggingface-smolagents", "source": "github", "axis": "agents", "layer": 0, "stars": 2, "lang": "Python", "desc": "Code Agents with the HuggingFace Smolagents AI Agent Framework"}
{"type": "node", "id": "repo:kazemihabib/Huggingface-Agents-Course-Marimo-Edition", "kind": "repo", "label": "kazemihabib/Huggingface-Agents-Course-Marimo-Edition", "url": "https://github.com/kazemihabib/Huggingface-Agents-Course-Marimo-Edition", "source": "github", "axis": "agents", "layer": 0, "stars": 6, "lang": "Jupyter Notebook", "desc": "Marimo versions of HuggingFace's Agents course notebooks."}
{"type": "node", "id": "repo:albertovalverde/huggingface-smolagents", "kind": "repo", "label": "albertovalverde/huggingface-smolagents", "url": "https://github.com/albertovalverde/huggingface-smolagents", "source": "github", "axis": "agents", "layer": 0, "stars": 2, "lang": "Python", "desc": "A multi-agent system leveraging Hugging Face's smolagents to automate content creation by coordinating research, writing, and editing tasks through collaborative AI agents."}
{"type": "node", "id": "repo:yusuf-eren/smolagents.js", "kind": "repo", "label": "yusuf-eren/smolagents.js", "url": "https://github.com/yusuf-eren/smolagents.js", "source": "github", "axis": "agents", "layer": 0, "stars": 5, "lang": "TypeScript", "desc": "Unofficial TypeScript/Node.js port of HuggingFace's smolagents \u2014 run LLM-powered agents with tool calling, streaming, and code execution in just a few lines."}
{"type": "node", "id": "repo:TheColonyCC/smolagents-colony", "kind": "repo", "label": "TheColonyCC/smolagents-colony", "url": "https://github.com/TheColonyCC/smolagents-colony", "source": "github", "axis": "agents", "layer": 0, "stars": 0, "lang": "Python", "desc": "smolagents tools for The Colony (thecolony.cc) \u2014 give any HuggingFace agent the ability to search, read, write, and interact on the AI agent internet"}
{"type": "node", "id": "repo:Sakeeb91/text2sql-agent", "kind": "repo", "label": "Sakeeb91/text2sql-agent", "url": "https://github.com/Sakeeb91/text2sql-agent", "source": "github", "axis": "agents", "layer": 0, "stars": 4, "lang": "Python", "desc": "Self-correcting AI agent for natural language to SQL using HuggingFace smolagents and ReAct framework"}
{"type": "node", "id": "repo:SqwareInfotechLearn/SmolAgents-Huggingface", "kind": "repo", "label": "SqwareInfotechLearn/SmolAgents-Huggingface", "url": "https://github.com/SqwareInfotechLearn/SmolAgents-Huggingface", "source": "github", "axis": "agents", "layer": 0, "stars": 2, "lang": "Jupyter Notebook", "desc": "SmolAgents is a Python-based framework that allows you to create AI agents capable of handling various tasks, such as basic Q&A, web searches, image generation, and downloading the most popular models from the Hugging Face Hub. This reposit"}
{"type": "node", "id": "repo:anjijava16/huggingface_smolagents_utils", "kind": "repo", "label": "anjijava16/huggingface_smolagents_utils", "url": "https://github.com/anjijava16/huggingface_smolagents_utils", "source": "github", "axis": "agents", "layer": 0, "stars": 0, "lang": "Python", "desc": "smolagents "}
{"type": "node", "id": "repo:virtualramblas/gromacs_smolagent", "kind": "repo", "label": "virtualramblas/gromacs_smolagent", "url": "https://github.com/virtualramblas/gromacs_smolagent", "source": "github", "axis": "agents", "layer": 0, "stars": 10, "lang": "Python", "desc": "An HF's Smolagent to automate molecular dynamics simulations using GROMACS."}
{"type": "node", "id": "repo:gm-gus/test-smolagents", "kind": "repo", "label": "gm-gus/test-smolagents", "url": "https://github.com/gm-gus/test-smolagents", "source": "github", "axis": "agents", "layer": 0, "stars": 0, "lang": "", "desc": "testing smolagents of HuggingFace"}
{"type": "node", "id": "repo:semanticarchitectures/interceptorDroneSim", "kind": "repo", "label": "semanticarchitectures/interceptorDroneSim", "url": "https://github.com/semanticarchitectures/interceptorDroneSim", "source": "github", "axis": "defense", "layer": 0, "stars": 5, "lang": "Python", "desc": "Counter-UAS interceptor drone engagement simulation \u2014 full kill chain from detection through intercept"}
{"type": "node", "id": "repo:ParagonTechnologies/cuas-drone-detection", "kind": "repo", "label": "ParagonTechnologies/cuas-drone-detection", "url": "https://github.com/ParagonTechnologies/cuas-drone-detection", "source": "github", "axis": "defense", "layer": 0, "stars": 2, "lang": "Python", "desc": "Multi-sensor fusion system for counter-UAS drone detection"}
{"type": "node", "id": "repo:Soussi-Aymen/drone-detection-frontend", "kind": "repo", "label": "Soussi-Aymen/drone-detection-frontend", "url": "https://github.com/Soussi-Aymen/drone-detection-frontend", "source": "github", "axis": "defense", "layer": 0, "stars": 0, "lang": "JavaScript", "desc": "This repository contains the single-page application (SPA) frontend for the Counter-UAS (C-UAS) system. It serves as the users primary interface for real-time situational awareness."}
{"type": "node", "id": "repo:mohamesb/AI-Powered-Drone-Detection-System", "kind": "repo", "label": "mohamesb/AI-Powered-Drone-Detection-System", "url": "https://github.com/mohamesb/AI-Powered-Drone-Detection-System", "source": "github", "axis": "defense", "layer": 0, "stars": 0, "lang": "Python", "desc": "A full-stack project demonstrating AI-powered drone detection inspired by counter-UAS defense systems."}
{"type": "node", "id": "repo:GerardGz/autonomous-drone-landing-risk-detection", "kind": "repo", "label": "GerardGz/autonomous-drone-landing-risk-detection", "url": "https://github.com/GerardGz/autonomous-drone-landing-risk-detection", "source": "github", "axis": "defense", "layer": 0, "stars": 0, "lang": "Python", "desc": "Computer Vision based counter-uas threat detection system, which utilizes a custom cnn and public datasets."}
{"type": "node", "id": "repo:Soussi-Aymen/drone-detection-backend", "kind": "repo", "label": "Soussi-Aymen/drone-detection-backend", "url": "https://github.com/Soussi-Aymen/drone-detection-backend", "source": "github", "axis": "defense", "layer": 0, "stars": 1, "lang": "TypeScript", "desc": "This repository contains the backend orchestration layer for the Counter-UAS (C-UAS) Human-Machine Interface (HMI) system, focused on providing real-time threat detection awareness to individual users at the edge."}
{"type": "node", "id": "repo:cognis-digital/uaslog", "kind": "repo", "label": "cognis-digital/uaslog", "url": "https://github.com/cognis-digital/uaslog", "source": "github", "axis": "defense", "layer": 0, "stars": 0, "lang": "Python", "desc": "Counter-UAS telemetry/log analyzer that flags drone-detection events, RF bands, and track anomalies."}
{"type": "node", "id": "repo:mr-fool/volumetric-drone-detection", "kind": "repo", "label": "mr-fool/volumetric-drone-detection", "url": "https://github.com/mr-fool/volumetric-drone-detection", "source": "github", "axis": "defense", "layer": 0, "stars": 0, "lang": "Python", "desc": "Simulation framework for real-time volumetric 3D detection, tracking, and engagement of multi-drone swarms, with advanced sensor array modeling, detection range analysis, and publication-ready visualizations for counter-UAS research."}
{"type": "node", "id": "repo:Suliman8/SkyShield", "kind": "repo", "label": "Suliman8/SkyShield", "url": "https://github.com/Suliman8/SkyShield", "source": "github", "axis": "defense", "layer": 0, "stars": 0, "lang": "HTML", "desc": "RF-Based Drone Detection, Payload Analysis & Threat Classification System - Affordable open-source Counter-UAS research"}
{"type": "node", "id": "repo:JiyounRoth/Drone_RF_Detection_FPGA", "kind": "repo", "label": "JiyounRoth/Drone_RF_Detection_FPGA", "url": "https://github.com/JiyounRoth/Drone_RF_Detection_FPGA", "source": "github", "axis": "defense", "layer": 0, "stars": 0, "lang": "Python", "desc": "This project implements a high-performance RF Signal Detection pipeline on an FPGA specifically designed for Portabel/Handheld Counter-UAS (Unmanned Aircraft Systems) Hardware. The design focuses on real-time drone signal identification whi"}
{"type": "node", "id": "repo:Sayeh-1337/meshkah", "kind": "repo", "label": "Sayeh-1337/meshkah", "url": "https://github.com/Sayeh-1337/meshkah", "source": "github", "axis": "defense", "layer": 0, "stars": 0, "lang": "Python", "desc": "meshkah is an academic Counter-UAS (CUAS) prototype that fuses RGB, thermal, RF, and acoustic detections to estimate and track drone position in 3D. It integrates ROS 2 Jazzy, Gazebo Harmonic, and ArduPilot SITL, supports automated flight s"}
{"type": "node", "id": "repo:doguilmak/Drone-Detection-YOLOv11x", "kind": "repo", "label": "doguilmak/Drone-Detection-YOLOv11x", "url": "https://github.com/doguilmak/Drone-Detection-YOLOv11x", "source": "github", "axis": "defense", "layer": 0, "stars": 80, "lang": "Jupyter Notebook", "desc": "Real-time drone detection and tracking using YOLOv11x with heatmap visualization. Trained on custom UAV dataset, optimized for small, fast-moving targets."}
{"type": "node", "id": "repo:monemati/PX4-ROS2-Gazebo-YOLOv8", "kind": "repo", "label": "monemati/PX4-ROS2-Gazebo-YOLOv8", "url": "https://github.com/monemati/PX4-ROS2-Gazebo-YOLOv8", "source": "github", "axis": "defense", "layer": 0, "stars": 384, "lang": "Python", "desc": "Aerial Object Detection using a Drone with PX4 Autopilot and ROS 2. PX4 SITL and Gazebo Garden used for Simulation. YOLOv8 used for Object Detection."}
{"type": "node", "id": "repo:wish44165/YOLOv12-BoT-SORT-ReID", "kind": "repo", "label": "wish44165/YOLOv12-BoT-SORT-ReID", "url": "https://github.com/wish44165/YOLOv12-BoT-SORT-ReID", "source": "github", "axis": "defense", "layer": 0, "stars": 192, "lang": "Python", "desc": "\ud83d\udd25 CVPR 2025 (Nashville TN) - The 4th Anti-UAV Workshop & Challenge \ud83e\udd49"}
{"type": "node", "id": "repo:MrZilinXiao/DroneObjectDetection", "kind": "repo", "label": "MrZilinXiao/DroneObjectDetection", "url": "https://github.com/MrZilinXiao/DroneObjectDetection", "source": "github", "axis": "defense", "layer": 0, "stars": 57, "lang": "Python", "desc": "(Outdated) A UAV object detection system based on YOLOv3, providing an interactive interface and `VisDrone2018` training scheme."}
{"type": "node", "id": "repo:alebal123bal/khadas_yolov8n_multithread", "kind": "repo", "label": "alebal123bal/khadas_yolov8n_multithread", "url": "https://github.com/alebal123bal/khadas_yolov8n_multithread", "source": "github", "axis": "defense", "layer": 0, "stars": 79, "lang": "C++", "desc": "Real-time YOLOv8n UAV detection on the RK3588S NPU | saturates the sensor at 46 FPS | ~140 MB RAM | fully hardware-accelerated (ISP+RGA+NPU) | on-device LLM scene summaries"}
{"type": "node", "id": "repo:2178568050/AntiUAV_Improved_Based_on-YOLOv11", "kind": "repo", "label": "2178568050/AntiUAV_Improved_Based_on-YOLOv11", "url": "https://github.com/2178568050/AntiUAV_Improved_Based_on-YOLOv11", "source": "github", "axis": "defense", "layer": 0, "stars": 39, "lang": "Python", "desc": "\u590d\u73b0\u5357\u4eac\u7406\u5de5\u5927\u5b66\u4e00\u7bc7\u8bba\u6587\uff1aA Lightweight Anti-Unmanned Aerial Vehicle Detection Method Based on Improved YOLOv11"}
{"type": "node", "id": "repo:aiesst/UAV_PyTorch_YOLOv3", "kind": "repo", "label": "aiesst/UAV_PyTorch_YOLOv3", "url": "https://github.com/aiesst/UAV_PyTorch_YOLOv3", "source": "github", "axis": "defense", "layer": 0, "stars": 25, "lang": "Python", "desc": ":jack_o_lantern:Implementation of YOLOv3 about uav detection in PyTorch"}
{"type": "node", "id": "repo:larics/synthetic-UAV", "kind": "repo", "label": "larics/synthetic-UAV", "url": "https://github.com/larics/synthetic-UAV", "source": "github", "axis": "defense", "layer": 0, "stars": 21, "lang": "", "desc": "Sim2air: synthetic texture-invariant dataset for object detection of UAVs"}
{"type": "node", "id": "repo:takzen/yolo-military-drone-detection", "kind": "repo", "label": "takzen/yolo-military-drone-detection", "url": "https://github.com/takzen/yolo-military-drone-detection", "source": "github", "axis": "defense", "layer": 0, "stars": 23, "lang": "Python", "desc": "Real-time military drone detection system using YOLO11. Detects Shahed-136, Lancet, Orlan-10, and other UAVs with 94.8% mAP50 accuracy. Features Streamlit interface with overlay statistics, video processing, and webcam monitoring. Trained o"}
{"type": "node", "id": "repo:anasbadawy/YOLOv3-Object-Detection", "kind": "repo", "label": "anasbadawy/YOLOv3-Object-Detection", "url": "https://github.com/anasbadawy/YOLOv3-Object-Detection", "source": "github", "axis": "defense", "layer": 0, "stars": 13, "lang": "Python", "desc": "This project implements a real-time image and video UAVs(unmanned aerial vehicle) detection classifier using a new trained yolov3 model."}
{"type": "node", "id": "repo:jashswayam/Automating-Tree-Counting-through-UAVs-and-YOLOv5-Object-Detection", "kind": "repo", "label": "jashswayam/Automating-Tree-Counting-through-UAVs-and-YOLOv5-Object-Detection", "url": "https://github.com/jashswayam/Automating-Tree-Counting-through-UAVs-and-YOLOv5-Object-Detection", "source": "github", "axis": "defense", "layer": 0, "stars": 4, "lang": "Jupyter Notebook", "desc": "This repository presents an innovative approach to automate tree counting using YOLOv5, a high-performing object detection model, coupled with high-resolution UAV imagery. By leveraging the power of deep learning, our algorithm intelligent"}
{"type": "node", "id": "repo:dmdobrea/shieldUAV", "kind": "repo", "label": "dmdobrea/shieldUAV", "url": "https://github.com/dmdobrea/shieldUAV", "source": "github", "axis": "defense", "layer": 0, "stars": 7, "lang": "Python", "desc": "This repository was developed in the context of the Pervasive AI Developer Contest with AMD "}
{"type": "node", "id": "repo:anhuipl2010/SOD-YOLO", "kind": "repo", "label": "anhuipl2010/SOD-YOLO", "url": "https://github.com/anhuipl2010/SOD-YOLO", "source": "github", "axis": "defense", "layer": 0, "stars": 37, "lang": "", "desc": "SOD-YOLO (Small Object Detection YOLO) builds upon the foundational YOLOv8 model to address the unique challenges of detecting small objects in complex backgrounds typical of UAV imagery. This repository contains the code for the model, inc"}
{"type": "node", "id": "repo:Xjh-UCAS/YoloOW", "kind": "repo", "label": "Xjh-UCAS/YoloOW", "url": "https://github.com/Xjh-UCAS/YoloOW", "source": "github", "axis": "defense", "layer": 0, "stars": 13, "lang": "Python", "desc": "YoloOW: A Spatial Scale Adaptive Real-time Object Detection Neural Network for Open Water Search and Rescue from UAV Aerial Imagery"}
{"type": "node", "id": "repo:MartinMohammed/object-tracking-yolo-v8-mil", "kind": "repo", "label": "MartinMohammed/object-tracking-yolo-v8-mil", "url": "https://github.com/MartinMohammed/object-tracking-yolo-v8-mil", "source": "github", "axis": "defense", "layer": 0, "stars": 17, "lang": "Python", "desc": "Object Tracking of UAVs utilizing YOLOv8 model for detection and classification and utilizing the Multiple Instance Learning (MIL) tracker for object tracking."}
{"type": "node", "id": "repo:lawlawCodes/MCA-YOLO", "kind": "repo", "label": "lawlawCodes/MCA-YOLO", "url": "https://github.com/lawlawCodes/MCA-YOLO", "source": "github", "axis": "defense", "layer": 0, "stars": 4, "lang": "Jupyter Notebook", "desc": "A Robust and Efficient Multi-Scenario Object Detection Network on Edge Device for UAV"}
{"type": "node", "id": "repo:solawen/anti-uav-yolov11-det", "kind": "repo", "label": "solawen/anti-uav-yolov11-det", "url": "https://github.com/solawen/anti-uav-yolov11-det", "source": "github", "axis": "defense", "layer": 0, "stars": 1, "lang": "Python", "desc": "Yolov11 uav detection using anti-uav dataset"}
{"type": "node", "id": "repo:v1taaa/YOLOv8-UAV-detection", "kind": "repo", "label": "v1taaa/YOLOv8-UAV-detection", "url": "https://github.com/v1taaa/YOLOv8-UAV-detection", "source": "github", "axis": "defense", "layer": 0, "stars": 6, "lang": "Python", "desc": "\u6bd5\u8bbe\uff0c\u65e0\u4eba\u673a\u68c0\u6d4b\uff08UAV Detection\uff09\uff0cYOLOv8s\uff0cPyQt5\u7cfb\u7edf\u8f6f\u4ef6\u8bbe\u8ba1\u5b9e\u73b0\uff0c\u65e0\u4eba\u673a\u6570\u636e\u96c6\uff08UAV DATASETS\uff09"}
{"type": "node", "id": "repo:iremustek/uav-object-detection-yolov5x", "kind": "repo", "label": "iremustek/uav-object-detection-yolov5x", "url": "https://github.com/iremustek/uav-object-detection-yolov5x", "source": "github", "axis": "defense", "layer": 0, "stars": 7, "lang": "Jupyter Notebook", "desc": "UAV Object Detection using transfer learning with YOLOv5x"}
{"type": "node", "id": "repo:GuccIceCream/yolov8", "kind": "repo", "label": "GuccIceCream/yolov8", "url": "https://github.com/GuccIceCream/yolov8", "source": "github", "axis": "defense", "layer": 0, "stars": 9, "lang": "", "desc": "Enhanced YOLOv8 for Small-Object Detection in Multiscale UAV Imagery: Innovations in Detection Accuracy and Efficiency"}
{"type": "node", "id": "repo:wi5nuu/SENTINEL-X-X-Domain-Threat-Fusion-Platform", "kind": "repo", "label": "wi5nuu/SENTINEL-X-X-Domain-Threat-Fusion-Platform", "url": "https://github.com/wi5nuu/SENTINEL-X-X-Domain-Threat-Fusion-Platform", "source": "github", "axis": "defense", "layer": 0, "stars": 23, "lang": "Python", "desc": "SENTINEL-X adalah proof-of-concept platform yang dikembangkan sebagai simulasi dan demonstrasi konsep untuk sistem threat intelligence dan monitoring multi-domain. Proyek ini berawal dari ide untuk membuat platform yang bisa mengintegrasika"}
{"type": "node", "id": "repo:a-for-aarushi/PS-09---AI-tools-for-Maritime-Domain-Awareness-", "kind": "repo", "label": "a-for-aarushi/PS-09---AI-tools-for-Maritime-Domain-Awareness-", "url": "https://github.com/a-for-aarushi/PS-09---AI-tools-for-Maritime-Domain-Awareness-", "source": "github", "axis": "defense", "layer": 0, "stars": 1, "lang": "Python", "desc": "End-to-end AI solution for Maritime Domain Awareness featuring vessel detection from EO/SAR imagery, length-width-heading estimation, AIS correlation, vessel classification, and path interpolation/prediction. Fully dockerized pipeline with "}
{"type": "node", "id": "repo:Alexdim620/Deep-Learning---Increasing-Maritime-Domain-Awareness-Using-Spatio-temporal-Sequencial-Data", "kind": "repo", "label": "Alexdim620/Deep-Learning---Increasing-Maritime-Domain-Awareness-Using-Spatio-temporal-Sequencial-Data", "url": "https://github.com/Alexdim620/Deep-Learning---Increasing-Maritime-Domain-Awareness-Using-Spatio-temporal-Sequencial-Data", "source": "github", "axis": "defense", "layer": 0, "stars": 0, "lang": "Jupyter Notebook", "desc": "AIS January data for port classification and ETA estimation using a multi-task LSTM model with spatio-temporal sequential features, preprocessing, and trajectory segmentation."}
{"type": "node", "id": "repo:Iberasa3/Carcosa", "kind": "repo", "label": "Iberasa3/Carcosa", "url": "https://github.com/Iberasa3/Carcosa", "source": "github", "axis": "defense", "layer": 0, "stars": 0, "lang": "", "desc": "Detecting illegal maritime activity by cross-referencing real-time satellite detections with AIS broadcasts. Built to combat IUU (Illegal, Unreported, and Unregulated) fishing and enhance maritime domain awareness."}
{"type": "node", "id": "repo:aousabdo/watchstander", "kind": "repo", "label": "aousabdo/watchstander", "url": "https://github.com/aousabdo/watchstander", "source": "github", "axis": "defense", "layer": 0, "stars": 0, "lang": "TypeScript", "desc": "Maritime domain awareness for the Southeast Coast + Caribbean, built from 100% public data. AIS gaps, loitering, and rendezvous detection. Built by OCEANS LLC, Jacksonville."}
{"type": "node", "id": "repo:AndrewKritikos/ais_anomaly_detection", "kind": "repo", "label": "AndrewKritikos/ais_anomaly_detection", "url": "https://github.com/AndrewKritikos/ais_anomaly_detection", "source": "github", "axis": "defense", "layer": 0, "stars": 1, "lang": "Python", "desc": "This real-time anomaly detection system exposes deceptive shipping practices utilized by the 'shadow fleet' for illicit operations. By processing live AIS telemetry from the Strait of Malacca, it mathematically flags GPS spoofing and 'Dark "}
{"type": "node", "id": "repo:jeeva20-AquaSentinel/Jeeva-R--Sea-Guard-AI", "kind": "repo", "label": "jeeva20-AquaSentinel/Jeeva-R--Sea-Guard-AI", "url": "https://github.com/jeeva20-AquaSentinel/Jeeva-R--Sea-Guard-AI", "source": "github", "axis": "defense", "layer": 0, "stars": 0, "lang": "Jupyter Notebook", "desc": "Real-time Maritime Domain Awareness system that processes AIS data, SAR imagery, and vessel tracking streams to detect illegal fishing, smuggling, and dark vessel activity. It leverages big data pipelines and machine learning to model norma"}
{"type": "node", "id": "repo:JunshengFu/tracking-with-Extended-Kalman-Filter", "kind": "repo", "label": "JunshengFu/tracking-with-Extended-Kalman-Filter", "url": "https://github.com/JunshengFu/tracking-with-Extended-Kalman-Filter", "source": "github", "axis": "defense", "layer": 0, "stars": 827, "lang": "C++", "desc": "Object (e.g Pedestrian, vehicles) tracking by Extended Kalman Filter (EKF), with  fused data from both lidar and radar sensors."}
{"type": "node", "id": "repo:ZHOUYI1023/awesome-radar-perception", "kind": "repo", "label": "ZHOUYI1023/awesome-radar-perception", "url": "https://github.com/ZHOUYI1023/awesome-radar-perception", "source": "github", "axis": "defense", "layer": 0, "stars": 1865, "lang": "", "desc": " A curated list of radar datasets, detection, tracking and fusion"}
{"type": "node", "id": "repo:amyworrall/QuickRadar", "kind": "repo", "label": "amyworrall/QuickRadar", "url": "https://github.com/amyworrall/QuickRadar", "source": "github", "axis": "defense", "layer": 0, "stars": 531, "lang": "Objective-C", "desc": "Mac app to simplify posting bug reports to Apple's Radar bug tracking system."}
{"type": "node", "id": "repo:BLE-Research-Group/MetaRadar", "kind": "repo", "label": "BLE-Research-Group/MetaRadar", "url": "https://github.com/BLE-Research-Group/MetaRadar", "source": "github", "axis": "defense", "layer": 0, "stars": 1456, "lang": "Kotlin", "desc": "A tool for BLE environment monitoring. Find and track Bluetooth devices around, and get notified when the target device is detected."}
{"type": "node", "id": "repo:Research-and-Project/mmWave_radar_tracking", "kind": "repo", "label": "Research-and-Project/mmWave_radar_tracking", "url": "https://github.com/Research-and-Project/mmWave_radar_tracking", "source": "github", "axis": "defense", "layer": 0, "stars": 161, "lang": "MATLAB", "desc": "object tracking based on millimeter wave radar"}
{"type": "node", "id": "repo:radarlabs/react-native-radar", "kind": "repo", "label": "radarlabs/react-native-radar", "url": "https://github.com/radarlabs/react-native-radar", "source": "github", "axis": "defense", "layer": 0, "stars": 197, "lang": "Objective-C", "desc": "React Native module for Radar, the widely-used geofencing and location tracking platform"}
{"type": "node", "id": "repo:ThasianX/SpotifyRadar", "kind": "repo", "label": "ThasianX/SpotifyRadar", "url": "https://github.com/ThasianX/SpotifyRadar", "source": "github", "axis": "defense", "layer": 0, "stars": 644, "lang": "Swift", "desc": "Allows users to pull in new song releases from their favorite artists and provides users with important metrics like their top tracks, top artists, and recently played tracks, queryable by time range."}
{"type": "node", "id": "repo:JunshengFu/tracking-with-Unscented-Kalman-Filter", "kind": "repo", "label": "JunshengFu/tracking-with-Unscented-Kalman-Filter", "url": "https://github.com/JunshengFu/tracking-with-Unscented-Kalman-Filter", "source": "github", "axis": "defense", "layer": 0, "stars": 171, "lang": "C++", "desc": "Object (e.g Pedestrian, biker, vehicles) tracking by Unscented Kalman Filter (UKF), with  fused data from both lidar and radar sensors."}
{"type": "node", "id": "repo:radarlabs/radar-sdk-ios", "kind": "repo", "label": "radarlabs/radar-sdk-ios", "url": "https://github.com/radarlabs/radar-sdk-ios", "source": "github", "axis": "defense", "layer": 0, "stars": 78, "lang": "Objective-C", "desc": "iOS SDK for Radar, the widely-used geofencing and location tracking platform"}
{"type": "node", "id": "repo:radarlabs/radar-sdk-android", "kind": "repo", "label": "radarlabs/radar-sdk-android", "url": "https://github.com/radarlabs/radar-sdk-android", "source": "github", "axis": "defense", "layer": 0, "stars": 96, "lang": "Kotlin", "desc": "Android SDK for Radar, the widely-used geofencing and location tracking platform"}
{"type": "node", "id": "repo:XiangyuDing/Radar-Detecting-and-Tracking", "kind": "repo", "label": "XiangyuDing/Radar-Detecting-and-Tracking", "url": "https://github.com/XiangyuDing/Radar-Detecting-and-Tracking", "source": "github", "axis": "defense", "layer": 0, "stars": 61, "lang": "Matlab", "desc": "ECE 2595 Radar Signal Processing Projects"}
{"type": "node", "id": "repo:duckduckgo/tracker-radar-detector", "kind": "repo", "label": "duckduckgo/tracker-radar-detector", "url": "https://github.com/duckduckgo/tracker-radar-detector", "source": "github", "axis": "defense", "layer": 0, "stars": 210, "lang": "JavaScript", "desc": "Code used to build a Tracker Radar data set from raw crawl data."}
{"type": "node", "id": "repo:duckduckgo/tracker-radar-wiki", "kind": "repo", "label": "duckduckgo/tracker-radar-wiki", "url": "https://github.com/duckduckgo/tracker-radar-wiki", "source": "github", "axis": "defense", "layer": 0, "stars": 81, "lang": "JavaScript", "desc": "Generation scripts and source for Tracker Radar Wiki"}
{"type": "node", "id": "repo:elsbrock/hetzner-radar", "kind": "repo", "label": "elsbrock/hetzner-radar", "url": "https://github.com/elsbrock/hetzner-radar", "source": "github", "axis": "defense", "layer": 0, "stars": 345, "lang": "TypeScript", "desc": "\ud83d\udd75\ufe0fTrack prices of the Hetzner dedicated server auction"}
{"type": "node", "id": "repo:LJacksonPan/RaTrack", "kind": "repo", "label": "LJacksonPan/RaTrack", "url": "https://github.com/LJacksonPan/RaTrack", "source": "github", "axis": "defense", "layer": 0, "stars": 218, "lang": "Python", "desc": "[ICRA2024] RaTrack: Moving Object Detection and Tracking with 4D Radar Point Cloud"}
{"type": "node", "id": "repo:radarlabs/radar-sdk-js", "kind": "repo", "label": "radarlabs/radar-sdk-js", "url": "https://github.com/radarlabs/radar-sdk-js", "source": "github", "axis": "defense", "layer": 0, "stars": 52, "lang": "TypeScript", "desc": "Web JavaScript SDK for Radar, the widely-used geofencing and location tracking platform"}
{"type": "node", "id": "repo:dhananjaymenon/SpeedRadar-OpenCV-", "kind": "repo", "label": "dhananjaymenon/SpeedRadar-OpenCV-", "url": "https://github.com/dhananjaymenon/SpeedRadar-OpenCV-", "source": "github", "axis": "defense", "layer": 0, "stars": 55, "lang": "Python", "desc": "This code focusses on Object Tracking and Speed Estimation of vehicles passing by a road."}
{"type": "node", "id": "repo:thkruz/keeptrack.space", "kind": "repo", "label": "thkruz/keeptrack.space", "url": "https://github.com/thkruz/keeptrack.space", "source": "github", "axis": "defense", "layer": 0, "stars": 1521, "lang": "TypeScript", "desc": "\ud83c\udf0e\ud83d\udce1 TypeScript Astrodynamics Software for Non-Engineers. 3D Visualization of satellite data and the sensors that track them."}
{"type": "node", "id": "repo:drpwchen/paper-radar", "kind": "repo", "label": "drpwchen/paper-radar", "url": "https://github.com/drpwchen/paper-radar", "source": "github", "axis": "defense", "layer": 0, "stars": 68, "lang": "Python", "desc": "\u8ad6\u6587\u5b78\u7fd2\u96f7\u9054 \u2014 a personal literature-tracking & learning radar: dozens of journal/PubMed feeds \u2192 interest-scored \u2192 private Cloudflare-Access web triage \u2192 flows into your notes"}
{"type": "node", "id": "repo:radarlabs/flutter-radar", "kind": "repo", "label": "radarlabs/flutter-radar", "url": "https://github.com/radarlabs/flutter-radar", "source": "github", "axis": "defense", "layer": 0, "stars": 29, "lang": "Java", "desc": "Flutter package for Radar, the widely-used geofencing and location tracking platform"}
{"type": "node", "id": "repo:micropython-IMU/micropython-fusion", "kind": "repo", "label": "micropython-IMU/micropython-fusion", "url": "https://github.com/micropython-IMU/micropython-fusion", "source": "github", "axis": "defense", "layer": 0, "stars": 345, "lang": "Python", "desc": "Sensor fusion calculating yaw, pitch and roll from the outputs of motion tracking devices"}
{"type": "node", "id": "repo:Fusion-Goettingen/ExtendedObjectTracking", "kind": "repo", "label": "Fusion-Goettingen/ExtendedObjectTracking", "url": "https://github.com/Fusion-Goettingen/ExtendedObjectTracking", "source": "github", "axis": "defense", "layer": 0, "stars": 93, "lang": "MATLAB", "desc": "Sensor Data Fusion Group"}
{"type": "node", "id": "repo:bernwang/latte", "kind": "repo", "label": "bernwang/latte", "url": "https://github.com/bernwang/latte", "source": "github", "axis": "defense", "layer": 0, "stars": 450, "lang": "Python", "desc": "LATTE: Accelerating LiDAR Point Cloud Annotation via Sensor Fusion, One-Click Annotation, and Tracking"}
{"type": "node", "id": "repo:aleksandrkim61/EagerMOT", "kind": "repo", "label": "aleksandrkim61/EagerMOT", "url": "https://github.com/aleksandrkim61/EagerMOT", "source": "github", "axis": "defense", "layer": 0, "stars": 440, "lang": "Python", "desc": "Official code for \"EagerMOT: 3D Multi-Object Tracking via Sensor Fusion\" [ICRA 2021]"}
{"type": "node", "id": "repo:TUMFTM/FusionTracking", "kind": "repo", "label": "TUMFTM/FusionTracking", "url": "https://github.com/TUMFTM/FusionTracking", "source": "github", "axis": "defense", "layer": 0, "stars": 100, "lang": "Python", "desc": "Multi-Modal Sensor Fusion and Object Tracking for Autonomous Racing"}
{"type": "node", "id": "repo:thp/psmoveapi", "kind": "repo", "label": "thp/psmoveapi", "url": "https://github.com/thp/psmoveapi", "source": "github", "axis": "defense", "layer": 0, "stars": 525, "lang": "C", "desc": "Cross-platform library for 6DoF tracking of the PS Move Motion Controller. Sensor fusion, computer vision, ambient display (LED orb)."}
{"type": "node", "id": "repo:UditBhaskar19/OBJECT_TRACKING_MULTI_SENSOR_FUSION", "kind": "repo", "label": "UditBhaskar19/OBJECT_TRACKING_MULTI_SENSOR_FUSION", "url": "https://github.com/UditBhaskar19/OBJECT_TRACKING_MULTI_SENSOR_FUSION", "source": "github", "axis": "defense", "layer": 0, "stars": 63, "lang": "MATLAB", "desc": "Sensor Fusion for Target Tracking"}
{"type": "node", "id": "repo:ptiwari0664/SensorFusionNanoDegree", "kind": "repo", "label": "ptiwari0664/SensorFusionNanoDegree", "url": "https://github.com/ptiwari0664/SensorFusionNanoDegree", "source": "github", "axis": "defense", "layer": 0, "stars": 59, "lang": "C++", "desc": "Learn to detect obstacles in lidar point clouds through clustering and segmentation, apply thresholds and filters to radar data in order to accurately track objects, and augment your perception by projecting camera images into three dimensi"}
{"type": "node", "id": "repo:walkerbrown/sfnd-3d-object-tracking", "kind": "repo", "label": "walkerbrown/sfnd-3d-object-tracking", "url": "https://github.com/walkerbrown/sfnd-3d-object-tracking", "source": "github", "axis": "defense", "layer": 0, "stars": 17, "lang": "C++", "desc": "Sensor Fusion, Project 3: 3D Object Tracking "}
{"type": "node", "id": "repo:palaghias/SensorFusion", "kind": "repo", "label": "palaghias/SensorFusion", "url": "https://github.com/palaghias/SensorFusion", "source": "github", "axis": "defense", "layer": 0, "stars": 29, "lang": "Matlab", "desc": "This project performs sensor fusion to track a mobile device's orientation. The data utilised are from three sensors: a) Accelerometer, b) Magnetic Field, d) Gyroscope. The sensor fusion is executed off-line. This project basically ports co"}
{"type": "node", "id": "repo:yrlu/orientation_tracking-unscented_kalman_filter", "kind": "repo", "label": "yrlu/orientation_tracking-unscented_kalman_filter", "url": "https://github.com/yrlu/orientation_tracking-unscented_kalman_filter", "source": "github", "axis": "defense", "layer": 0, "stars": 66, "lang": "Matlab", "desc": "Implemented Unscented Kalman Filter (UKF) for orientation tracking. Sensors fusion of accelerometer, and gyroscope"}
{"type": "node", "id": "repo:max-kazak/SensorFusion", "kind": "repo", "label": "max-kazak/SensorFusion", "url": "https://github.com/max-kazak/SensorFusion", "source": "github", "axis": "defense", "layer": 0, "stars": 24, "lang": "C++", "desc": "Combining sensor inputs from camera/lidar/radar to detect, track moving vehicles and estimate their speed and direction."}
{"type": "node", "id": "repo:salmoshu/IndoorFusionNav", "kind": "repo", "label": "salmoshu/IndoorFusionNav", "url": "https://github.com/salmoshu/IndoorFusionNav", "source": "github", "axis": "defense", "layer": 0, "stars": 126, "lang": "Python", "desc": "An open-source project for accurate indoor pedestrian localization using WiFi, PDR, and EKF fusion. It combines WiFi signals, step tracking, and sensor fusion for reliable positioning in GPS-denied environments."}
{"type": "node", "id": "repo:Ram-Godavarthi/Sensor_Fusion_3D_Object_Tracking_Lidar-Camera", "kind": "repo", "label": "Ram-Godavarthi/Sensor_Fusion_3D_Object_Tracking_Lidar-Camera", "url": "https://github.com/Ram-Godavarthi/Sensor_Fusion_3D_Object_Tracking_Lidar-Camera", "source": "github", "axis": "defense", "layer": 0, "stars": 35, "lang": "C++", "desc": "Collision Avoidance System with Camera and Lidar - Track an Object in 3D Space - Object Detection with YOLO - Descriptors and Keypoint Matching"}
{"type": "node", "id": "repo:Autoferry/sensor_fusion_dataset", "kind": "repo", "label": "Autoferry/sensor_fusion_dataset", "url": "https://github.com/Autoferry/sensor_fusion_dataset", "source": "github", "axis": "defense", "layer": 0, "stars": 19, "lang": "", "desc": "Benchmark dataset for maritime multi-sensor, multi-target tracking"}
{"type": "node", "id": "repo:AbdullahGM1/l2i_fusion_detection", "kind": "repo", "label": "AbdullahGM1/l2i_fusion_detection", "url": "https://github.com/AbdullahGM1/l2i_fusion_detection", "source": "github", "axis": "defense", "layer": 0, "stars": 53, "lang": "C++", "desc": " This ROS2 package integrates data from a 360-degree lidar and a camera to achieve enhanced object tracking through sensor fusion. "}
{"type": "node", "id": "repo:srnand/Object-Tracking-and-State-Prediction-with-Unscented-and-Extended-Kalman-Filters", "kind": "repo", "label": "srnand/Object-Tracking-and-State-Prediction-with-Unscented-and-Extended-Kalman-Filters", "url": "https://github.com/srnand/Object-Tracking-and-State-Prediction-with-Unscented-and-Extended-Kalman-Filters", "source": "github", "axis": "defense", "layer": 0, "stars": 65, "lang": "Python", "desc": "Radar and Lidar Sensor Fusion using Simple, Extended, and Unscented Kalman Filter for Object Tracking and State Prediction."}
{"type": "node", "id": "repo:mzahana/smart_track", "kind": "repo", "label": "mzahana/smart_track", "url": "https://github.com/mzahana/smart_track", "source": "github", "axis": "defense", "layer": 0, "stars": 44, "lang": "Python", "desc": "A Kalman Filter-Guided Sensor Fusion For Robust Object Tracking in Dynamic Environments using RGB-Depth-LiDAR sensors"}
{"type": "node", "id": "repo:Southparketeer/SLAM-Large-Dense-Scene-Real-Time-3D-Reconstruction", "kind": "repo", "label": "Southparketeer/SLAM-Large-Dense-Scene-Real-Time-3D-Reconstruction", "url": "https://github.com/Southparketeer/SLAM-Large-Dense-Scene-Real-Time-3D-Reconstruction", "source": "github", "axis": "defense", "layer": 0, "stars": 38, "lang": "C++", "desc": "GPU based real-time camera tracking, volumetric fusion and volume rendering system. Addressed updating the map with moving sensor and the static sensors."}
{"type": "node", "id": "repo:studian/SFND_P4_3D_Object_Tracking", "kind": "repo", "label": "studian/SFND_P4_3D_Object_Tracking", "url": "https://github.com/studian/SFND_P4_3D_Object_Tracking", "source": "github", "axis": "defense", "layer": 0, "stars": 9, "lang": "Makefile", "desc": "Udacity, Sensor Fusion, Project of SFND_3D_Object_Tracking"}
{"type": "node", "id": "repo:sufirehman/carbon-aware-ml-scheduler", "kind": "repo", "label": "sufirehman/carbon-aware-ml-scheduler", "url": "https://github.com/sufirehman/carbon-aware-ml-scheduler", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 15, "lang": "Python", "desc": "A carbon-aware ML training scheduling system that optimises machine learning workloads using real-time UK grid carbon intensity data. It simulates ML training, finds optimal low-carbon execution windows, and visualises carbon savings throug"}
{"type": "node", "id": "repo:ksm26/Carbon-Aware-Computing-for-GenAI-Developers", "kind": "repo", "label": "ksm26/Carbon-Aware-Computing-for-GenAI-Developers", "url": "https://github.com/ksm26/Carbon-Aware-Computing-for-GenAI-Developers", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 9, "lang": "Jupyter Notebook", "desc": "Learn to optimize machine learning tasks for environmental sustainability. Discover how to use real-time electricity data and low-carbon energy sources for model training and inference, reducing the carbon footprint of your cloud operations"}
{"type": "node", "id": "repo:boringlee24/sc23-clover", "kind": "repo", "label": "boringlee24/sc23-clover", "url": "https://github.com/boringlee24/sc23-clover", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 4, "lang": "Python", "desc": "Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference Service"}
{"type": "node", "id": "repo:atharvchaudhari2907-code/CarbonQuest", "kind": "repo", "label": "atharvchaudhari2907-code/CarbonQuest", "url": "https://github.com/atharvchaudhari2907-code/CarbonQuest", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "JavaScript", "desc": "AI Sustainability Assistant is a smart web platform that analyzes lifestyle data to calculate carbon footprint and suggests personalized eco-friendly actions. The system combines web development, data analysis, and machine learning to encou"}
{"type": "node", "id": "repo:UdayKurla/Carbon-Aware-Optimistic-Machine-Learning-Framework-CAOMLF-", "kind": "repo", "label": "UdayKurla/Carbon-Aware-Optimistic-Machine-Learning-Framework-CAOMLF-", "url": "https://github.com/UdayKurla/Carbon-Aware-Optimistic-Machine-Learning-Framework-CAOMLF-", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:nirtutac123/Carbon-Aware-Comparison-of-Machine-Learning-Models", "kind": "repo", "label": "nirtutac123/Carbon-Aware-Comparison-of-Machine-Learning-Models", "url": "https://github.com/nirtutac123/Carbon-Aware-Comparison-of-Machine-Learning-Models", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Jupyter Notebook", "desc": ""}
{"type": "node", "id": "repo:yellelieder/carbon-aware-prediction-api", "kind": "repo", "label": "yellelieder/carbon-aware-prediction-api", "url": "https://github.com/yellelieder/carbon-aware-prediction-api", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "Carbon Aware Time Shifiting. Machine learning API to encounter carbon intensity into execution of energy intensive processes. "}
{"type": "node", "id": "repo:ahmadrezadehghan/Carbon-Aware-Machine-Learning-for-Energy-Efficient-Quantum-Data-Centers", "kind": "repo", "label": "ahmadrezadehghan/Carbon-Aware-Machine-Learning-for-Energy-Efficient-Quantum-Data-Centers", "url": "https://github.com/ahmadrezadehghan/Carbon-Aware-Machine-Learning-for-Energy-Efficient-Quantum-Data-Centers", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "Joint Optimization of Workload Scheduling and Cooling"}
{"type": "node", "id": "repo:Mayur-zope07/Carbon-Aware-Lifestyle-Optimizer", "kind": "repo", "label": "Mayur-zope07/Carbon-Aware-Lifestyle-Optimizer", "url": "https://github.com/Mayur-zope07/Carbon-Aware-Lifestyle-Optimizer", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "A web-based AI application that analyzes individual lifestyle data to calculate, predict, and reduce personal carbon emissions through visualization, machine learning, and personalized recommendations."}
{"type": "node", "id": "repo:THESARTHAKGOEL/eco-ops", "kind": "repo", "label": "THESARTHAKGOEL/eco-ops", "url": "https://github.com/THESARTHAKGOEL/eco-ops", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "Carbon-Aware Machine Learning Framework with Automated Emission Enforcement"}
{"type": "node", "id": "repo:vernekaradarsh/CarbonAware_CropPrediction_using_DevOps", "kind": "repo", "label": "vernekaradarsh/CarbonAware_CropPrediction_using_DevOps", "url": "https://github.com/vernekaradarsh/CarbonAware_CropPrediction_using_DevOps", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "A Carbon-Aware DevOps framework designed to optimize energy efficiency in AI-driven crop yield prediction. This project implements GreenOps principles to minimize the environmental footprint of machine learning pipelines while maintaining h"}
{"type": "node", "id": "repo:USD-AI-ResearchLab/ai-care", "kind": "repo", "label": "USD-AI-ResearchLab/ai-care", "url": "https://github.com/USD-AI-ResearchLab/ai-care", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "AI-CARE: Carbon-Aware Reporting and Evaluation for Machine Learning Models"}
{"type": "node", "id": "repo:marknash22/Carbon-Aware-Scheduling-in-Cloud-Data-Centres-Using-Machine-Learning-project-for-my-masters-degree", "kind": "repo", "label": "marknash22/Carbon-Aware-Scheduling-in-Cloud-Data-Centres-Using-Machine-Learning-project-for-my-masters-degree", "url": "https://github.com/marknash22/Carbon-Aware-Scheduling-in-Cloud-Data-Centres-Using-Machine-Learning-project-for-my-masters-degree", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Java", "desc": "During October 2025 until January 2026, the project in general runs through three phases of experiments and shows an investigation of the effectiveness of carbon aware scheduling. The items uploaded here are two of the phases that I did on "}
{"type": "node", "id": "repo:ramanaa-dev/ecotrack-ai-carbon-footprint-platform", "kind": "repo", "label": "ramanaa-dev/ecotrack-ai-carbon-footprint-platform", "url": "https://github.com/ramanaa-dev/ecotrack-ai-carbon-footprint-platform", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "JavaScript", "desc": "AI-powered Carbon Footprint Awareness Platform built with React, Flask, PostgreSQL and Machine Learning."}
{"type": "node", "id": "repo:Meena-0726/Green-AI-Sustainability-Framework", "kind": "repo", "label": "Meena-0726/Green-AI-Sustainability-Framework", "url": "https://github.com/Meena-0726/Green-AI-Sustainability-Framework", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Jupyter Notebook", "desc": "Carbon-aware machine learning benchmarking framework evaluating predictive performance alongside energy consumption and CO\u2082 emissions."}
{"type": "node", "id": "repo:Harshada2012/Carbon_Footprint_Optimization", "kind": "repo", "label": "Harshada2012/Carbon_Footprint_Optimization", "url": "https://github.com/Harshada2012/Carbon_Footprint_Optimization", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Jupyter Notebook", "desc": "A machine learning\u2013based project that analyzes carbon emission data and predicts future emissions to promote sustainability, green skills, and data-driven environmental awareness."}
{"type": "node", "id": "repo:HRNBEnninful/Feasibility-Aware-ML-Energy-Materials", "kind": "repo", "label": "HRNBEnninful/Feasibility-Aware-ML-Energy-Materials", "url": "https://github.com/HRNBEnninful/Feasibility-Aware-ML-Energy-Materials", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Jupyter Notebook", "desc": "Feasibility-aware analysis of latent representations learned by multitask machine-learning models for electrochemical energy materials. The framework reveals domain structure, transferability limits, and data-supported performance regimes a"}
{"type": "node", "id": "repo:Farhan-Fadillah/household_carbon_predictor", "kind": "repo", "label": "Farhan-Fadillah/household_carbon_predictor", "url": "https://github.com/Farhan-Fadillah/household_carbon_predictor", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "Developed a machine learning model to predict household carbon emissions based on lifestyle and  consumption patterns. The project aimed to raise awareness of environmental impact at the household  level and provide personalized recommendat"}
{"type": "node", "id": "repo:Farhanfadillah99/household_carbon_predictor", "kind": "repo", "label": "Farhanfadillah99/household_carbon_predictor", "url": "https://github.com/Farhanfadillah99/household_carbon_predictor", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "Developed a machine learning model to predict household carbon emissions based on lifestyle and consumption patterns. The project aimed to raise awareness of environmental impact at the household level and provide personalized recommendatio"}
{"type": "node", "id": "repo:avi1822/carbon_calculator", "kind": "repo", "label": "avi1822/carbon_calculator", "url": "https://github.com/avi1822/carbon_calculator", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "", "desc": "Carbon Cost Calculator is a machine learning-powered web application that estimates the carbon emissions and environmental cost of a vehicle based on its fuel type, engine size, and mileage. Built using Python, Streamlit, and MySQL, it help"}
{"type": "node", "id": "repo:climatechange-ai-tutorials/tracking-ml-emissions", "kind": "repo", "label": "climatechange-ai-tutorials/tracking-ml-emissions", "url": "https://github.com/climatechange-ai-tutorials/tracking-ml-emissions", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 5, "lang": "Jupyter Notebook", "desc": "Learn how to measure a machine learning model's carbon footprint and practice strategies that can help shrink the energy involved in training these models."}
{"type": "node", "id": "repo:pramanik-souvik/multimodal-facebook-hateful-meme-detection", "kind": "repo", "label": "pramanik-souvik/multimodal-facebook-hateful-meme-detection", "url": "https://github.com/pramanik-souvik/multimodal-facebook-hateful-meme-detection", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Jupyter Notebook", "desc": "Multimodal meme hate detection using VLMs and Fusion Approaches, with training evaluation and carbon emission tracking via CodeCarbon."}
{"type": "node", "id": "repo:AryaStark13/CMU-BNY-Datathon", "kind": "repo", "label": "AryaStark13/CMU-BNY-Datathon", "url": "https://github.com/AryaStark13/CMU-BNY-Datathon", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Jupyter Notebook", "desc": "CarbonLens - Track Carbon Emissions of Training AI Models"}
{"type": "node", "id": "repo:Pm023/CarbonIQ", "kind": "repo", "label": "Pm023/CarbonIQ", "url": "https://github.com/Pm023/CarbonIQ", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 1, "lang": "Python", "desc": "CarbonIQ \ud83c\udf0d is a Python desktop app that estimates the energy consumption and CO\u2082 emissions of ML model training. Compare multiple models, view animated charts, and export detailed PDF reports to track your AI projects\u2019 environmental impact\u2014"}
{"type": "node", "id": "repo:izzulroslan/GreenModel-AI-Carbon-Emission-Tracker", "kind": "repo", "label": "izzulroslan/GreenModel-AI-Carbon-Emission-Tracker", "url": "https://github.com/izzulroslan/GreenModel-AI-Carbon-Emission-Tracker", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "GreenModel: AI Carbon Emission Tracker is a user-friendly Streamlit platform that helps users train machine learning models while tracking their carbon emissions in real time. It promotes sustainable AI development by using the CodeCarbon l"}
{"type": "node", "id": "repo:RohitSah13/Eco-Ops-Green-Computing-Analytics-", "kind": "repo", "label": "RohitSah13/Eco-Ops-Green-Computing-Analytics-", "url": "https://github.com/RohitSah13/Eco-Ops-Green-Computing-Analytics-", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "Eco-Ops is a carbon-aware ML framework that tracks energy usage and CO\u2082 emissions during model training. It uses CodeCarbon and Streamlit to provide benchmarking, visualization, and sustainability analysis for machine learning models."}
{"type": "node", "id": "repo:yjwong1999/Twin-TD3", "kind": "repo", "label": "yjwong1999/Twin-TD3", "url": "https://github.com/yjwong1999/Twin-TD3", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 174, "lang": "Python", "desc": "[IEEE WCNC] Deep Reinforcement Learning for Secrecy Energy-Efficient UAV Communication with Reconfigurable Intelligent Surfaces"}
{"type": "node", "id": "repo:BIT-MCS/DRL-EC3", "kind": "repo", "label": "BIT-MCS/DRL-EC3", "url": "https://github.com/BIT-MCS/DRL-EC3", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 148, "lang": "Python", "desc": "[JSAC 2018] Energy-Efficient UAV Control for Effective and Fair Communication Coverage: A Deep Reinforcement Learning Approach"}
{"type": "node", "id": "repo:BIT-MCS/DRL-eFresh", "kind": "repo", "label": "BIT-MCS/DRL-eFresh", "url": "https://github.com/BIT-MCS/DRL-eFresh", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 62, "lang": "Python", "desc": "[TMC 2023] Delay-Sensitive Energy-Efficient UAV Crowdsensing by Deep Reinforcement Learning"}
{"type": "node", "id": "repo:ahmadfaisal9900/Multi-Agent-Deep-Reinforcement-Learning-for-Energy-Efficient-RIS-Assisted-CoMP-NOMA-Networks", "kind": "repo", "label": "ahmadfaisal9900/Multi-Agent-Deep-Reinforcement-Learning-for-Energy-Efficient-RIS-Assisted-CoMP-NOMA-Networks", "url": "https://github.com/ahmadfaisal9900/Multi-Agent-Deep-Reinforcement-Learning-for-Energy-Efficient-RIS-Assisted-CoMP-NOMA-Networks", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 13, "lang": "Python", "desc": "The official repository for the paper with the same name."}
{"type": "node", "id": "repo:youxch/Inverse-design-of-patch-antennas", "kind": "repo", "label": "youxch/Inverse-design-of-patch-antennas", "url": "https://github.com/youxch/Inverse-design-of-patch-antennas", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 161, "lang": "Python", "desc": "This repository hosts a simple demonstration of a deep learning approach for the inverse design of patch antennas. The goal is to explore energy-efficient designs and to significantly reduce simulation cost compared to conventional methods."}
{"type": "node", "id": "repo:BIT-MCS/DRL-DisasterVC", "kind": "repo", "label": "BIT-MCS/DRL-DisasterVC", "url": "https://github.com/BIT-MCS/DRL-DisasterVC", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 19, "lang": "Python", "desc": "[KDD 2021] Energy-Efficient 3D Vehicular Crowdsourcing for Disaster Response by Distributed Deep Reinforcement Learning"}
{"type": "node", "id": "repo:BIT-MCS/e-Divert", "kind": "repo", "label": "BIT-MCS/e-Divert", "url": "https://github.com/BIT-MCS/e-Divert", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 29, "lang": "Python", "desc": "[TMC 2021] Distributed and Energy-Efficient Mobile Crowdsensing with Charging Stations by Deep Reinforcement Learning"}
{"type": "node", "id": "repo:Geraldine-Winston/Energy-Efficient-Building-Design-Recommendations-using-deep-reinforcement-learning.", "kind": "repo", "label": "Geraldine-Winston/Energy-Efficient-Building-Design-Recommendations-using-deep-reinforcement-learning.", "url": "https://github.com/Geraldine-Winston/Energy-Efficient-Building-Design-Recommendations-using-deep-reinforcement-learning.", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 26, "lang": "", "desc": "This project develops a deep reinforcement learning agent to recommend energy-efficient building designs by optimizing parameters like window size, insulation thickness, and HVAC setpoints, aiming to minimize energy consumption and enhance "}
{"type": "node", "id": "repo:dhivyadharsi/Actor-Critic-Deep-Reinforcement-Learning-for-UAV-Assisted-MEC", "kind": "repo", "label": "dhivyadharsi/Actor-Critic-Deep-Reinforcement-Learning-for-UAV-Assisted-MEC", "url": "https://github.com/dhivyadharsi/Actor-Critic-Deep-Reinforcement-Learning-for-UAV-Assisted-MEC", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 29, "lang": "Python", "desc": "Actor-Critic Deep Reinforcement Learning for Energy-Efficient and Delay-Aware Task Offloading in UAV-Assisted Mobile Edge Computing."}
{"type": "node", "id": "repo:BIT-MCS/Edics", "kind": "repo", "label": "BIT-MCS/Edics", "url": "https://github.com/BIT-MCS/Edics", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 15, "lang": "Python", "desc": "[JSAC 2019] Energy-Efficient Distributed Mobile Crowd Sensing: A Deep Learning Approach"}
{"type": "node", "id": "repo:GodeWithWind/GNN4SCMU", "kind": "repo", "label": "GodeWithWind/GNN4SCMU", "url": "https://github.com/GodeWithWind/GNN4SCMU", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 15, "lang": "", "desc": "Deep Learning for Energy Efficient Beamforming in MU-MISO Networks: A GAT-based Approach"}
{"type": "node", "id": "repo:ULudo/DRL-Building-Energy-Ctr", "kind": "repo", "label": "ULudo/DRL-Building-Energy-Ctr", "url": "https://github.com/ULudo/DRL-Building-Energy-Ctr", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 30, "lang": "Python", "desc": "Harness the power of deep reinforcement learning to optimize your Home Energy Management System (HEMS). Our tailored agent, trained on the CoSES ProHMo Modelica framework, efficiently controls a building's heat pump and thermal storage valv"}
{"type": "node", "id": "repo:mehrshaad/DeepRL-Offloading-MEC", "kind": "repo", "label": "mehrshaad/DeepRL-Offloading-MEC", "url": "https://github.com/mehrshaad/DeepRL-Offloading-MEC", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 11, "lang": "Python", "desc": "Deep Reinforcement Learning for Energy-Efficient Computation Offloading in Mobile-Edge Computing"}
{"type": "node", "id": "repo:solgaardlab/photonicbackprop", "kind": "repo", "label": "solgaardlab/photonicbackprop", "url": "https://github.com/solgaardlab/photonicbackprop", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 6, "lang": "Jupyter Notebook", "desc": "Data and code for the paper \"Experimentally realized \\textit{in situ} backpropagation for deep learning in energy-efficient nanophotonic neural networks\""}
{"type": "node", "id": "repo:BIT-MCS/jPPO-ConvNTM", "kind": "repo", "label": "BIT-MCS/jPPO-ConvNTM", "url": "https://github.com/BIT-MCS/jPPO-ConvNTM", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 18, "lang": "Python", "desc": "[INFOCOM 2020] Energy-Efficient UAV Crowdsensing with Multiple Charging Stations by Deep Learning"}
{"type": "node", "id": "repo:BIT-MCS/DRL-CEWS", "kind": "repo", "label": "BIT-MCS/DRL-CEWS", "url": "https://github.com/BIT-MCS/DRL-CEWS", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 18, "lang": "Python", "desc": "[ICDE 2020] Curiosity-Driven Energy-Efficient Worker Scheduling in Vehicular Crowdsourcing: A Deep Reinforcement Learning Approach"}
{"type": "node", "id": "repo:NM001007/IST-DFRL-Base-Station-Sleep-Control", "kind": "repo", "label": "NM001007/IST-DFRL-Base-Station-Sleep-Control", "url": "https://github.com/NM001007/IST-DFRL-Base-Station-Sleep-Control", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 7, "lang": "Python", "desc": "The Decentralized Federated Deep Reinforcement Learning Framework for Energy Efficient Base Station Sleep Control"}
{"type": "node", "id": "repo:danielflood/fpga-eeg", "kind": "repo", "label": "danielflood/fpga-eeg", "url": "https://github.com/danielflood/fpga-eeg", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 8, "lang": "Jupyter Notebook", "desc": "A reproduction of the paper \"FPGA-based Deep-Learning Accelerators for Energy Efficient Motor Imagery EEG classification\"."}
{"type": "node", "id": "repo:dataclergy/Forecasting-Hourly-Energy-Consumption-with-Python", "kind": "repo", "label": "dataclergy/Forecasting-Hourly-Energy-Consumption-with-Python", "url": "https://github.com/dataclergy/Forecasting-Hourly-Energy-Consumption-with-Python", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 4, "lang": "Jupyter Notebook", "desc": "The energy sector is one of the largest and most important sectors out there. The ability to efficiently forecast hourly energy consumption plays an important role on how energy is distributed and consumed. Deep learning algorithms have pla"}
{"type": "node", "id": "repo:Ishaniiitb/Memristor_based_Custom_Deep_Spiking_Neural_Network", "kind": "repo", "label": "Ishaniiitb/Memristor_based_Custom_Deep_Spiking_Neural_Network", "url": "https://github.com/Ishaniiitb/Memristor_based_Custom_Deep_Spiking_Neural_Network", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 5, "lang": "Jupyter Notebook", "desc": "This project implements a memristor-based deep Spiking Neural Network (SNN) in Python, using Leaky Integrate-and-Fire neurons with adaptive thresholds and STDP learning for energy-efficient neuromorphic computing. It trains and tests on the"}
{"type": "node", "id": "repo:AI4Green/AI4Green", "kind": "repo", "label": "AI4Green/AI4Green", "url": "https://github.com/AI4Green/AI4Green", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 29, "lang": "JavaScript", "desc": "AI4Green is an Electronic Laboratory Notebook which combines data storage and sharing while promoting green and sustainable chemistry."}
{"type": "node", "id": "repo:soham2002/GreenRoots", "kind": "repo", "label": "soham2002/GreenRoots", "url": "https://github.com/soham2002/GreenRoots", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 3, "lang": "Jupyter Notebook", "desc": "GreenRoots: An AI/ML project dedicated to promoting mangrove sustainability and fostering community engagement in mangrove conservation efforts."}
{"type": "node", "id": "repo:Rishabhmannu/amazon-greencart-hackathon", "kind": "repo", "label": "Rishabhmannu/amazon-greencart-hackathon", "url": "https://github.com/Rishabhmannu/amazon-greencart-hackathon", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 58, "lang": "TypeScript", "desc": "AI-powered sustainable e-commerce platform with EarthScore ratings, group buying via DBSCAN clustering, and multi-agent chatbot. Gamifies eco-friendly shopping with real-time carbon tracking, achievements, and community bulk purchasing. Bui"}
{"type": "node", "id": "repo:NaiveNinjas/greenforce", "kind": "repo", "label": "NaiveNinjas/greenforce", "url": "https://github.com/NaiveNinjas/greenforce", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "TypeScript", "desc": "GreenForce is an AI-powered sustainability assistant that helps organizations automate and coordinate environmental workflows aligned with the UN Sustainable Development Goals (SDGs 7, 12 and 13)."}
{"type": "node", "id": "repo:mwakidenis/Green-AI", "kind": "repo", "label": "mwakidenis/Green-AI", "url": "https://github.com/mwakidenis/Green-AI", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 12, "lang": "TypeScript", "desc": "\ud83c\udf31 Green- AI-Powered Waste-to-Energy Platform Transform waste into sustainable energy using advanced AI technology. GreenTech combines real-time monitoring, predictive analytics, and community engagement to optimize waste processing and "}
{"type": "node", "id": "repo:Pampaj7/GreenAI", "kind": "repo", "label": "Pampaj7/GreenAI", "url": "https://github.com/Pampaj7/GreenAI", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 6, "lang": "HTML", "desc": "This repository is a companion page for the revision at the 9th International Workshop on Green and Sustainable Software (GREENS\u201925)"}
{"type": "node", "id": "repo:Deepsayan-Das/Green-Lens", "kind": "repo", "label": "Deepsayan-Das/Green-Lens", "url": "https://github.com/Deepsayan-Das/Green-Lens", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 2, "lang": "JavaScript", "desc": "An AI & Blockchain sustainability platform. Track eco-actions, get ML-verified rewards (Green Tokens), and support real-world NGOs. [React, Node.js, Python, Solidity, Document AI]"}
{"type": "node", "id": "repo:ErnestMunyoki/Green-Path", "kind": "repo", "label": "ErnestMunyoki/Green-Path", "url": "https://github.com/ErnestMunyoki/Green-Path", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "AI-Powered sustainability tracker "}
{"type": "node", "id": "repo:fredsta98/GreenChain", "kind": "repo", "label": "fredsta98/GreenChain", "url": "https://github.com/fredsta98/GreenChain", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 3, "lang": "", "desc": "Blockchain-Driven Carbon Management integrates blockchain for transparency, automated credit systems, XRC-20 tokens for carbon trading, AI predective analysis, pooling tokens, reward system, user-friendly interfaces, incentives, compliance,"}
{"type": "node", "id": "repo:tholewis/green-software-engineer", "kind": "repo", "label": "tholewis/green-software-engineer", "url": "https://github.com/tholewis/green-software-engineer", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 13, "lang": "", "desc": "A green software AI skill + agent for AI projects to have a Green Software Sustainability expert in your app."}
{"type": "node", "id": "repo:Tharshananth/BankEase-AI", "kind": "repo", "label": "Tharshananth/BankEase-AI", "url": "https://github.com/Tharshananth/BankEase-AI", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 1, "lang": "Jupyter Notebook", "desc": "The Green Finance Optimization Platform uses AI to optimize investments in sustainable projects, focusing on ESG impact and providing decision-making\u00a0insights."}
{"type": "node", "id": "repo:mahoutukaisali/GreenOps-Tracker", "kind": "repo", "label": "mahoutukaisali/GreenOps-Tracker", "url": "https://github.com/mahoutukaisali/GreenOps-Tracker", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 7, "lang": "Jinja", "desc": "This project has been created to participate \"Cisco AI & Sustainability Code Challenge\" contest."}
{"type": "node", "id": "repo:GDGC-MET/AiForGreenerPlanet-VibeCoding", "kind": "repo", "label": "GDGC-MET/AiForGreenerPlanet-VibeCoding", "url": "https://github.com/GDGC-MET/AiForGreenerPlanet-VibeCoding", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "", "desc": "Our daily choices significantly impact the environment, but it's often hard to track and maintain sustainable habits. This challenge is about using AI to empower individuals with tools that promote eco-friendly living. Choose a project belo"}
{"type": "node", "id": "repo:RosalieJA/Academic_Project_GreenAI_Sustainable_Ressources_4_GreenComputing", "kind": "repo", "label": "RosalieJA/Academic_Project_GreenAI_Sustainable_Ressources_4_GreenComputing", "url": "https://github.com/RosalieJA/Academic_Project_GreenAI_Sustainable_Ressources_4_GreenComputing", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 3, "lang": "Python", "desc": "Student project from UTC providing solutions to assess carbon emissions and reduce costs in modern AI projects."}
{"type": "node", "id": "repo:hameembaba/Project---Creating-a-website-on-title-Green-Scape-Mapping-the-air-quality-for-sustainable-living", "kind": "repo", "label": "hameembaba/Project---Creating-a-website-on-title-Green-Scape-Mapping-the-air-quality-for-sustainable-living", "url": "https://github.com/hameembaba/Project---Creating-a-website-on-title-Green-Scape-Mapping-the-air-quality-for-sustainable-living", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 2, "lang": "HTML", "desc": ""}
{"type": "node", "id": "repo:jsnbyxyjsj/Green-Chain-PLI-Hackathon-2.0", "kind": "repo", "label": "jsnbyxyjsj/Green-Chain-PLI-Hackathon-2.0", "url": "https://github.com/jsnbyxyjsj/Green-Chain-PLI-Hackathon-2.0", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "", "desc": "Blockchain-Driven Carbon Management integrates blockchain for transparency, automated credit systems, XRC-20 tokens for carbon trading, AI predictions, user-friendly interfaces, incentives, compliance, and public awareness. Revolutionizing "}
{"type": "node", "id": "repo:saurabh-singh-rajput/Green-AI-Resources", "kind": "repo", "label": "saurabh-singh-rajput/Green-AI-Resources", "url": "https://github.com/saurabh-singh-rajput/Green-AI-Resources", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 3, "lang": "", "desc": "A curated collection of research, tools, and best practices for environmentally sustainable AI development and deployment."}
{"type": "node", "id": "repo:KOSASIH/ecopulse-platform", "kind": "repo", "label": "KOSASIH/ecopulse-platform", "url": "https://github.com/KOSASIH/ecopulse-platform", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 7, "lang": "Python", "desc": "A comprehensive, AI-driven green energy solution integrating renewable energy sources, IoT, data analytics, and sustainable infrastructure management."}
{"type": "node", "id": "repo:greenfit-ai/greenfit-ai", "kind": "repo", "label": "greenfit-ai/greenfit-ai", "url": "https://github.com/greenfit-ai/greenfit-ai", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 4, "lang": "Python", "desc": "Find out about sustainability in your favorite sport clothing brands, in just one click!"}
{"type": "node", "id": "repo:anashanishaaban/GreenSync", "kind": "repo", "label": "anashanishaaban/GreenSync", "url": "https://github.com/anashanishaaban/GreenSync", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "JavaScript", "desc": "greensync is a decentralized ai platform that distributes computation across user devices, reducing reliance on energy-hungry cloud servers. users earn green coins based on their computational contributions, incentivizing sustainable ai pro"}
{"type": "node", "id": "repo:Aayush-Ankit/ml-inference-benchmarks", "kind": "repo", "label": "Aayush-Ankit/ml-inference-benchmarks", "url": "https://github.com/Aayush-Ankit/ml-inference-benchmarks", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 4, "lang": "Lua", "desc": "GPU and CPU measurements for ML inference workloads for power, latency and throughput"}
{"type": "node", "id": "repo:jchuahtacc/ml-gpu-power", "kind": "repo", "label": "jchuahtacc/ml-gpu-power", "url": "https://github.com/jchuahtacc/ml-gpu-power", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Jupyter Notebook", "desc": "Machine Learning GPU Power Measurement on Chameleon Cloud"}
{"type": "node", "id": "repo:kathanpanchal/ml-inference-benchmarks", "kind": "repo", "label": "kathanpanchal/ml-inference-benchmarks", "url": "https://github.com/kathanpanchal/ml-inference-benchmarks", "source": "github", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Lua", "desc": "GPU and CPU measurements for ML inference workloads for power, latency and throughput"}
{"type": "node", "id": "repo:jy0205/Pyramid-Flow", "kind": "repo", "label": "jy0205/Pyramid-Flow", "url": "https://github.com/jy0205/Pyramid-Flow", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 3196, "lang": "Python", "desc": "[ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling"}
{"type": "node", "id": "repo:yuvraj108c/ComfyUI-FLOAT", "kind": "repo", "label": "yuvraj108c/ComfyUI-FLOAT", "url": "https://github.com/yuvraj108c/ComfyUI-FLOAT", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 267, "lang": "Python", "desc": "Generative Motion Latent Flow Matching for Audio-driven Talking Portrait"}
{"type": "node", "id": "repo:BioinfoMachineLearning/FlowDock", "kind": "repo", "label": "BioinfoMachineLearning/FlowDock", "url": "https://github.com/BioinfoMachineLearning/FlowDock", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 139, "lang": "Python", "desc": "A geometric flow matching model for generative protein-ligand docking and affinity prediction. (ISMB 2025)"}
{"type": "node", "id": "repo:deepbrainai-research/float", "kind": "repo", "label": "deepbrainai-research/float", "url": "https://github.com/deepbrainai-research/float", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 484, "lang": "Python", "desc": "[ICCV 2025] Official Pytorch Implementation of FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait."}
{"type": "node", "id": "repo:m1balcerak/EnergyMatching", "kind": "repo", "label": "m1balcerak/EnergyMatching", "url": "https://github.com/m1balcerak/EnergyMatching", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 217, "lang": "Jupyter Notebook", "desc": "[NeurIPS 2025] Official repository for \"Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling\" "}
{"type": "node", "id": "repo:smsharma/minified-generative-models", "kind": "repo", "label": "smsharma/minified-generative-models", "url": "https://github.com/smsharma/minified-generative-models", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 141, "lang": "Jupyter Notebook", "desc": "Bare-bones implementations of some generative models in Jax: diffusion, normalizing flows, consistency models, flow matching, (beta)-VAEs, etc"}
{"type": "node", "id": "repo:LukasMosser/DeepFlow", "kind": "repo", "label": "LukasMosser/DeepFlow", "url": "https://github.com/LukasMosser/DeepFlow", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 35, "lang": "MATLAB", "desc": "Pytorch implementation of \"DeepFlow: History Matching in the Space of Deep Generative Models\""}
{"type": "node", "id": "repo:amorehead/awesome-generative-flows", "kind": "repo", "label": "amorehead/awesome-generative-flows", "url": "https://github.com/amorehead/awesome-generative-flows", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 43, "lang": "", "desc": "Awesome papers related to generative flow matching and its applications in bioinformatics. (Nature Machine Intelligence)"}
{"type": "node", "id": "repo:sp-uhh/streamfm", "kind": "repo", "label": "sp-uhh/streamfm", "url": "https://github.com/sp-uhh/streamfm", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 48, "lang": "Python", "desc": "Real-Time Streamable Generative Speech Restoration with Flow Matching"}
{"type": "node", "id": "repo:alexjli/proteinzen", "kind": "repo", "label": "alexjli/proteinzen", "url": "https://github.com/alexjli/proteinzen", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 27, "lang": "Python", "desc": "All-atom generative protein design using SE(3) flow matching"}
{"type": "node", "id": "repo:MurrellGroup/Flowfusion.jl", "kind": "repo", "label": "MurrellGroup/Flowfusion.jl", "url": "https://github.com/MurrellGroup/Flowfusion.jl", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 40, "lang": "Julia", "desc": "Unifying flow matching and diffusion on Riemannian manifolds and discrete spaces, for generative deep learning."}
{"type": "node", "id": "repo:aleksandrinvictor/flow-matching", "kind": "repo", "label": "aleksandrinvictor/flow-matching", "url": "https://github.com/aleksandrinvictor/flow-matching", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 23, "lang": "Python", "desc": "Simple reimplementation of Flow Matching for Generative Modeling (https://arxiv.org/abs/2210.02747) paper in PyTorch"}
{"type": "node", "id": "repo:MizuhoAOKI/jax_generative_models", "kind": "repo", "label": "MizuhoAOKI/jax_generative_models", "url": "https://github.com/MizuhoAOKI/jax_generative_models", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 66, "lang": "Python", "desc": "Minimal JAX implementation unifying Diffusion and Flow Matching algorithms as alternative strategies for transporting data distributions."}
{"type": "node", "id": "repo:mrjoness/Flow-Back", "kind": "repo", "label": "mrjoness/Flow-Back", "url": "https://github.com/mrjoness/Flow-Back", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 12, "lang": "Python", "desc": "Generative backmapping of coarse-grained molecular systems using an equivariant graph neural network and flow-matching"}
{"type": "node", "id": "repo:pedrocurvo/follow-the-mean", "kind": "repo", "label": "pedrocurvo/follow-the-mean", "url": "https://github.com/pedrocurvo/follow-the-mean", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 22, "lang": "Python", "desc": "Follow the Mean: controlling flow-matching generative models by shifting endpoint means with reference examples"}
{"type": "node", "id": "repo:BLEACH366/P2DFlow", "kind": "repo", "label": "BLEACH366/P2DFlow", "url": "https://github.com/BLEACH366/P2DFlow", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 43, "lang": "Python", "desc": "P2DFlow: A Protein Ensemble Generative Model with SE(3) Flow Matching"}
{"type": "node", "id": "repo:willisma/diffuse_nnx", "kind": "repo", "label": "willisma/diffuse_nnx", "url": "https://github.com/willisma/diffuse_nnx", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 150, "lang": "Python", "desc": "A comprehensive JAX/NNX library for diffusion and flow matching generative algorithms, featuring DiT (Diffusion Transformer) and its variants as the primary backbone with support for ImageNet training and various sampling strategies."}
{"type": "node", "id": "repo:g4vrel/CFM", "kind": "repo", "label": "g4vrel/CFM", "url": "https://github.com/g4vrel/CFM", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 45, "lang": "Python", "desc": "A minimal PyTorch implementation of Flow Matching for Generative Modeling."}
{"type": "node", "id": "repo:tesfaldet/genpt", "kind": "repo", "label": "tesfaldet/genpt", "url": "https://github.com/tesfaldet/genpt", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 24, "lang": "Python", "desc": "Official repo for \"Generative Point Tracking with Flow Matching\"."}
{"type": "node", "id": "repo:AI4Science-WestlakeU/FourierFlow", "kind": "repo", "label": "AI4Science-WestlakeU/FourierFlow", "url": "https://github.com/AI4Science-WestlakeU/FourierFlow", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 17, "lang": "Python", "desc": "FourierFlow: Frequency-aware Flow Matching for Generative Turbulence Modeling"}
{"type": "node", "id": "repo:gnobitab/RectifiedFlow", "kind": "repo", "label": "gnobitab/RectifiedFlow", "url": "https://github.com/gnobitab/RectifiedFlow", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 1621, "lang": "Python", "desc": "Official Implementation of Rectified Flow (ICLR2023 Spotlight)"}
{"type": "node", "id": "repo:feizc/FluxMusic", "kind": "repo", "label": "feizc/FluxMusic", "url": "https://github.com/feizc/FluxMusic", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 1713, "lang": "Python", "desc": "Text-to-Music Generation with Rectified Flow Transformers"}
{"type": "node", "id": "repo:VAST-AI-Research/TripoSG", "kind": "repo", "label": "VAST-AI-Research/TripoSG", "url": "https://github.com/VAST-AI-Research/TripoSG", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 1711, "lang": "Python", "desc": "TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models"}
{"type": "node", "id": "repo:TongTong313/rectified-flow", "kind": "repo", "label": "TongTong313/rectified-flow", "url": "https://github.com/TongTong313/rectified-flow", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 631, "lang": "Python", "desc": "\u4ece\u96f6\u624b\u6413Flow Matching\uff08Rectified Flow\uff09"}
{"type": "node", "id": "repo:gnobitab/InstaFlow", "kind": "repo", "label": "gnobitab/InstaFlow", "url": "https://github.com/gnobitab/InstaFlow", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 1409, "lang": "Python", "desc": ":zap: InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)"}
{"type": "node", "id": "repo:magic-research/piecewise-rectified-flow", "kind": "repo", "label": "magic-research/piecewise-rectified-flow", "url": "https://github.com/magic-research/piecewise-rectified-flow", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 538, "lang": "Jupyter Notebook", "desc": "PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)"}
{"type": "node", "id": "repo:lqiang67/rectified-flow", "kind": "repo", "label": "lqiang67/rectified-flow", "url": "https://github.com/lqiang67/rectified-flow", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 296, "lang": "Python", "desc": "code based for rectified flow"}
{"type": "node", "id": "repo:lucidrains/rectified-flow-pytorch", "kind": "repo", "label": "lucidrains/rectified-flow-pytorch", "url": "https://github.com/lucidrains/rectified-flow-pytorch", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 475, "lang": "Python", "desc": "Implementation of rectified flow and some of its followup research / improvements in Pytorch"}
{"type": "node", "id": "repo:cloneofsimo/minRF", "kind": "repo", "label": "cloneofsimo/minRF", "url": "https://github.com/cloneofsimo/minRF", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 638, "lang": "Jupyter Notebook", "desc": "Minimal implementation of scalable rectified flow transformers, based on SD3's approach"}
{"type": "node", "id": "repo:LituRout/RF-Inversion", "kind": "repo", "label": "LituRout/RF-Inversion", "url": "https://github.com/LituRout/RF-Inversion", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 477, "lang": "Python", "desc": "Rectified Flow Inversion (RF-Inversion) - ICLR 2025"}
{"type": "node", "id": "repo:ohayonguy/PMRF", "kind": "repo", "label": "ohayonguy/PMRF", "url": "https://github.com/ohayonguy/PMRF", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 751, "lang": "Python", "desc": "[ICLR 2025] Official implementation of Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration"}
{"type": "node", "id": "repo:GradientSpaces/Rectified-Point-Flow", "kind": "repo", "label": "GradientSpaces/Rectified-Point-Flow", "url": "https://github.com/GradientSpaces/Rectified-Point-Flow", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 195, "lang": "Python", "desc": "[NeurIPS 2025, Spotlight] Rectified Point Flow: Generic Point Cloud Pose Estimation"}
{"type": "node", "id": "repo:X-LANCE/VoiceFlow-TTS", "kind": "repo", "label": "X-LANCE/VoiceFlow-TTS", "url": "https://github.com/X-LANCE/VoiceFlow-TTS", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 375, "lang": "Python", "desc": "[ICASSP 2024] This is the official code for \"VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching\""}
{"type": "node", "id": "repo:HolmesShuan/FireFlow-Fast-Inversion-of-Rectified-Flow-for-Image-Semantic-Editing", "kind": "repo", "label": "HolmesShuan/FireFlow-Fast-Inversion-of-Rectified-Flow-for-Image-Semantic-Editing", "url": "https://github.com/HolmesShuan/FireFlow-Fast-Inversion-of-Rectified-Flow-for-Image-Semantic-Editing", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 294, "lang": "Python", "desc": "[ICML2025] An 8-step inversion and 8-step editing process works effectively with the FLUX-dev model. (3x speedup with results that are comparable or even superior to baseline methods)"}
{"type": "node", "id": "repo:jacklishufan/OmniFlows", "kind": "repo", "label": "jacklishufan/OmniFlows", "url": "https://github.com/jacklishufan/OmniFlows", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 132, "lang": "Jupyter Notebook", "desc": "The official implementation of OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows"}
{"type": "node", "id": "repo:EternalEvan/FlowIE", "kind": "repo", "label": "EternalEvan/FlowIE", "url": "https://github.com/EternalEvan/FlowIE", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 153, "lang": "Python", "desc": "[CVPR 2024 oral]This repository contains the official implementation of \"FlowIE: Efficient Image Enhancement via Rectified Flow\""}
{"type": "node", "id": "repo:wangjiangshan0725/RF-Solver-Edit", "kind": "repo", "label": "wangjiangshan0725/RF-Solver-Edit", "url": "https://github.com/wangjiangshan0725/RF-Solver-Edit", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 637, "lang": "Python", "desc": "[\ud83d\ude80ICML 2025] \"Taming Rectified Flow for Inversion and Editing\"  Using FLUX and HunyuanVideo for image and video editing!"}
{"type": "node", "id": "repo:feifeiobama/RectifID", "kind": "repo", "label": "feifeiobama/RectifID", "url": "https://github.com/feifeiobama/RectifID", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 129, "lang": "Jupyter Notebook", "desc": "[NeurIPS 2024] RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance"}
{"type": "node", "id": "repo:UNITES-Lab/FlowTS", "kind": "repo", "label": "UNITES-Lab/FlowTS", "url": "https://github.com/UNITES-Lab/FlowTS", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 31, "lang": "Python", "desc": "FlowTS: Time Series Generation via Recti\ufb01ed Flow"}
{"type": "node", "id": "repo:Pur1zumu/RIFT-SVC", "kind": "repo", "label": "Pur1zumu/RIFT-SVC", "url": "https://github.com/Pur1zumu/RIFT-SVC", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 64, "lang": "Python", "desc": "Implementation of RIFT-SVC, a singing voice conversion model based on Rectified Flow Transformer."}
{"type": "node", "id": "repo:malbergo/stochastic-interpolants", "kind": "repo", "label": "malbergo/stochastic-interpolants", "url": "https://github.com/malbergo/stochastic-interpolants", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 216, "lang": "Jupyter Notebook", "desc": ""}
{"type": "node", "id": "repo:dongzhuoyao/awesome-flow-matching", "kind": "repo", "label": "dongzhuoyao/awesome-flow-matching", "url": "https://github.com/dongzhuoyao/awesome-flow-matching", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 684, "lang": "", "desc": "A summary of related works about flow matching, stochastic interpolants"}
{"type": "node", "id": "repo:interpolants/forecasting", "kind": "repo", "label": "interpolants/forecasting", "url": "https://github.com/interpolants/forecasting", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 20, "lang": "Jupyter Notebook", "desc": "Code for the paper: Probabilistic Forecasting with Stochastic Interpolants and Follmer Processes (generative AI for forecasting)"}
{"type": "node", "id": "repo:nmboffi/jax-interpolants", "kind": "repo", "label": "nmboffi/jax-interpolants", "url": "https://github.com/nmboffi/jax-interpolants", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 41, "lang": "Python", "desc": "Definitive implementation of the stochastic interpolant framework for generative modeling in jax."}
{"type": "node", "id": "repo:martinschiodt/Turbulence_Stochastic_Interpolants", "kind": "repo", "label": "martinschiodt/Turbulence_Stochastic_Interpolants", "url": "https://github.com/martinschiodt/Turbulence_Stochastic_Interpolants", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 4, "lang": "Python", "desc": "Stochastic interpolants are applied to super-resolve a case study of two-dimensional turbulence"}
{"type": "node", "id": "repo:KAIST-Visual-AI-Group/BezierFlow", "kind": "repo", "label": "KAIST-Visual-AI-Group/BezierFlow", "url": "https://github.com/KAIST-Visual-AI-Group/BezierFlow", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 21, "lang": "Python", "desc": "[ICLR 2026] Official code for B\u00e9zierFlow: Learning B\u00e9zier Stochastic Interpolant Schedulers for Few-Step Generation"}
{"type": "node", "id": "repo:nmucke/StochasticInterpolants.jl", "kind": "repo", "label": "nmucke/StochasticInterpolants.jl", "url": "https://github.com/nmucke/StochasticInterpolants.jl", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 3, "lang": "Julia", "desc": ""}
{"type": "node", "id": "repo:pnkraemer/mini-stochastic-interpolants", "kind": "repo", "label": "pnkraemer/mini-stochastic-interpolants", "url": "https://github.com/pnkraemer/mini-stochastic-interpolants", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 3, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:multitaskstochasticinterpolant/Code-Multitask-Stochastic-Interpolants", "kind": "repo", "label": "multitaskstochasticinterpolant/Code-Multitask-Stochastic-Interpolants", "url": "https://github.com/multitaskstochasticinterpolant/Code-Multitask-Stochastic-Interpolants", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 3, "lang": "Jupyter Notebook", "desc": "Official Code for \"Multitask Learning With Stochastic Interpolants\", Spotlight NeurIPS2025"}
{"type": "node", "id": "repo:Erik-Wikingsson/DAISI", "kind": "repo", "label": "Erik-Wikingsson/DAISI", "url": "https://github.com/Erik-Wikingsson/DAISI", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 10, "lang": "Python", "desc": "The official implementation of DAISI: Data Assimilation with Inverse Sampling using Stochastic Interpolants"}
{"type": "node", "id": "repo:CompVis/Art-fm", "kind": "repo", "label": "CompVis/Art-fm", "url": "https://github.com/CompVis/Art-fm", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 8, "lang": "", "desc": "[ICCV 2025] Stochastic Interpolants for Revealing Stylistic Flows across the History of Art"}
{"type": "node", "id": "repo:WladGrm/si-adistill", "kind": "repo", "label": "WladGrm/si-adistill", "url": "https://github.com/WladGrm/si-adistill", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 5, "lang": "Jupyter Notebook", "desc": "Adversarial Distillation of Generative Models: A Unified View via Stochastic Interpolants"}
{"type": "node", "id": "repo:plurigrid/StochFlow", "kind": "repo", "label": "plurigrid/StochFlow", "url": "https://github.com/plurigrid/StochFlow", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 4, "lang": "Python", "desc": "a Python library that implements the stochastic interpolant models and algorithms described in the paper \"Stochastic Interpolants via Diffusive and Flow-based Processes\" by Chen et al."}
{"type": "node", "id": "repo:janisaiad/probgraph", "kind": "repo", "label": "janisaiad/probgraph", "url": "https://github.com/janisaiad/probgraph", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 0, "lang": "Jupyter Notebook", "desc": "stochastic interpolants investigations"}
{"type": "node", "id": "repo:joaovaleriano/stochastic-interpolants", "kind": "repo", "label": "joaovaleriano/stochastic-interpolants", "url": "https://github.com/joaovaleriano/stochastic-interpolants", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 0, "lang": "Jupyter Notebook", "desc": ""}
{"type": "node", "id": "repo:atreya-s/ReturnDistribution_StochasticInterpolants", "kind": "repo", "label": "atreya-s/ReturnDistribution_StochasticInterpolants", "url": "https://github.com/atreya-s/ReturnDistribution_StochasticInterpolants", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 0, "lang": "Python", "desc": "Using stochastic interpolants as a framework for modeling return distributions"}
{"type": "node", "id": "repo:clarkmiyamoto/stochastic-interpolants", "kind": "repo", "label": "clarkmiyamoto/stochastic-interpolants", "url": "https://github.com/clarkmiyamoto/stochastic-interpolants", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 0, "lang": "", "desc": "Notes on all things Stochastic Interpolants & some implementation here and there."}
{"type": "node", "id": "repo:clarkmiyamoto/interpolants", "kind": "repo", "label": "clarkmiyamoto/interpolants", "url": "https://github.com/clarkmiyamoto/interpolants", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 0, "lang": "Python", "desc": "Implementation of stochastic interpolants"}
{"type": "node", "id": "repo:Blaise143/stochastic-interpolant-diffusion", "kind": "repo", "label": "Blaise143/stochastic-interpolant-diffusion", "url": "https://github.com/Blaise143/stochastic-interpolant-diffusion", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 0, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:workerjl/glass_stochastic_interpolant", "kind": "repo", "label": "workerjl/glass_stochastic_interpolant", "url": "https://github.com/workerjl/glass_stochastic_interpolant", "source": "github", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "stars": 0, "lang": "Jupyter Notebook", "desc": ""}
{"type": "node", "id": "repo:zhujun98/sensor-fusion", "kind": "repo", "label": "zhujun98/sensor-fusion", "url": "https://github.com/zhujun98/sensor-fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 271, "lang": "C++", "desc": "Kalman filter, sensor fusion"}
{"type": "node", "id": "repo:ethz-asl/ethzasl_msf", "kind": "repo", "label": "ethz-asl/ethzasl_msf", "url": "https://github.com/ethz-asl/ethzasl_msf", "source": "github", "axis": "fusion", "layer": 0, "stars": 1096, "lang": "C++", "desc": "MSF - Modular framework for multi sensor fusion based on an Extended Kalman Filter (EKF)"}
{"type": "node", "id": "repo:mithi/fusion-ukf", "kind": "repo", "label": "mithi/fusion-ukf", "url": "https://github.com/mithi/fusion-ukf", "source": "github", "axis": "fusion", "layer": 0, "stars": 302, "lang": "C++", "desc": "An unscented Kalman Filter implementation for fusing lidar and radar sensor measurements."}
{"type": "node", "id": "repo:simondlevy/SensorFusion", "kind": "repo", "label": "simondlevy/SensorFusion", "url": "https://github.com/simondlevy/SensorFusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 177, "lang": "MATLAB", "desc": "A simple Matlab example of sensor fusion using a Kalman filter"}
{"type": "node", "id": "repo:sharathsrini/Kalman-Filter-for-Sensor-Fusion", "kind": "repo", "label": "sharathsrini/Kalman-Filter-for-Sensor-Fusion", "url": "https://github.com/sharathsrini/Kalman-Filter-for-Sensor-Fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 154, "lang": "Jupyter Notebook", "desc": "A Sensor Fusion Algorithm that can predict a State Estimate and Update if it is uncertain"}
{"type": "node", "id": "repo:maddevsio/mad-location-manager", "kind": "repo", "label": "maddevsio/mad-location-manager", "url": "https://github.com/maddevsio/mad-location-manager", "source": "github", "axis": "fusion", "layer": 0, "stars": 572, "lang": "Java", "desc": "Mad Location Manager is a library for GPS and Accelerometer data \"fusion\" with Kalman filter "}
{"type": "node", "id": "repo:paulyehtw/Lidar-and-Radar-sensor-fusion-with-Extended-Kalman-Filter", "kind": "repo", "label": "paulyehtw/Lidar-and-Radar-sensor-fusion-with-Extended-Kalman-Filter", "url": "https://github.com/paulyehtw/Lidar-and-Radar-sensor-fusion-with-Extended-Kalman-Filter", "source": "github", "axis": "fusion", "layer": 0, "stars": 150, "lang": "MATLAB", "desc": "Fusing Lidar and Radar data with Extended Kalman Filter (EKF)"}
{"type": "node", "id": "repo:technitute/AKFSF-Simulation-CPP", "kind": "repo", "label": "technitute/AKFSF-Simulation-CPP", "url": "https://github.com/technitute/AKFSF-Simulation-CPP", "source": "github", "axis": "fusion", "layer": 0, "stars": 111, "lang": "C++", "desc": "Simulation Environment for Advanced Kalman Filtering for Sensor Fusion Course"}
{"type": "node", "id": "repo:mbrossar/FUSION2018", "kind": "repo", "label": "mbrossar/FUSION2018", "url": "https://github.com/mbrossar/FUSION2018", "source": "github", "axis": "fusion", "layer": 0, "stars": 147, "lang": "MATLAB", "desc": "Matlab code used for the paper \" Invariant Kalman Filtering for Visual Inertial SLAM\" "}
{"type": "node", "id": "repo:mithi/fusion-ekf", "kind": "repo", "label": "mithi/fusion-ekf", "url": "https://github.com/mithi/fusion-ekf", "source": "github", "axis": "fusion", "layer": 0, "stars": 142, "lang": "C++", "desc": "An extended Kalman Filter implementation in C++ for fusing lidar and radar sensor measurements."}
{"type": "node", "id": "repo:flappyimi/Radar-Basic-Algorithm", "kind": "repo", "label": "flappyimi/Radar-Basic-Algorithm", "url": "https://github.com/flappyimi/Radar-Basic-Algorithm", "source": "github", "axis": "fusion", "layer": 0, "stars": 203, "lang": "MATLAB", "desc": "Some basic algorithm used in Radar data process, including pulse compression/CFAR/monopulse\u3001Kalman filter and fusion\u3001arrary antenna design."}
{"type": "node", "id": "repo:Jeff-Zhouxiaolong/demo_for_kalmanFilter", "kind": "repo", "label": "Jeff-Zhouxiaolong/demo_for_kalmanFilter", "url": "https://github.com/Jeff-Zhouxiaolong/demo_for_kalmanFilter", "source": "github", "axis": "fusion", "layer": 0, "stars": 4, "lang": "Matlab", "desc": "fusion location with only ranging and 6-axis imu sensor in similink data"}
{"type": "node", "id": "repo:awerries/kalman-localization", "kind": "repo", "label": "awerries/kalman-localization", "url": "https://github.com/awerries/kalman-localization", "source": "github", "axis": "fusion", "layer": 0, "stars": 98, "lang": "Matlab", "desc": "MATLAB implementation of localization using sensor fusion of GPS/INS through an error-state Kalman filter."}
{"type": "node", "id": "repo:diegoavillegasg/IMU-GNSS-Lidar-sensor-fusion-using-Extended-Kalman-Filter-for-State-Estimation", "kind": "repo", "label": "diegoavillegasg/IMU-GNSS-Lidar-sensor-fusion-using-Extended-Kalman-Filter-for-State-Estimation", "url": "https://github.com/diegoavillegasg/IMU-GNSS-Lidar-sensor-fusion-using-Extended-Kalman-Filter-for-State-Estimation", "source": "github", "axis": "fusion", "layer": 0, "stars": 279, "lang": "Python", "desc": "State Estimation and Localization of an autonomous vehicle based on IMU (high rate), GNSS (GPS) and Lidar data with sensor fusion techniques using the Extended Kalman Filter (EKF)."}
{"type": "node", "id": "repo:williamhyin/SFND_Unscented_Kalman_Filter", "kind": "repo", "label": "williamhyin/SFND_Unscented_Kalman_Filter", "url": "https://github.com/williamhyin/SFND_Unscented_Kalman_Filter", "source": "github", "axis": "fusion", "layer": 0, "stars": 63, "lang": "C++", "desc": "Unscented_Kalman_Filter, CTRV model, Sensor fusion of lidar and radar, multiobject detection"}
{"type": "node", "id": "repo:mithi/fusion-ekf-python", "kind": "repo", "label": "mithi/fusion-ekf-python", "url": "https://github.com/mithi/fusion-ekf-python", "source": "github", "axis": "fusion", "layer": 0, "stars": 70, "lang": "Jupyter Notebook", "desc": "An extended Kalman Filter implementation in Python for fusing lidar and radar sensor measurements"}
{"type": "node", "id": "repo:soarbear/imu_ekf", "kind": "repo", "label": "soarbear/imu_ekf", "url": "https://github.com/soarbear/imu_ekf", "source": "github", "axis": "fusion", "layer": 0, "stars": 172, "lang": "Python", "desc": "6-axis(3-axis acceleration sensor+3-axis gyro sensor) IMU fusion with Extended Kalman Filter."}
{"type": "node", "id": "repo:EliaTarasov/ESKF", "kind": "repo", "label": "EliaTarasov/ESKF", "url": "https://github.com/EliaTarasov/ESKF", "source": "github", "axis": "fusion", "layer": 0, "stars": 182, "lang": "C++", "desc": "ROS Error-State Kalman Filter based on PX4/ecl. Performs GPS/Magnetometer/Vision Pose/Optical Flow/RangeFinder fusion with IMU"}
{"type": "node", "id": "repo:bkarwoski/EKF_fusion", "kind": "repo", "label": "bkarwoski/EKF_fusion", "url": "https://github.com/bkarwoski/EKF_fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 57, "lang": "MATLAB", "desc": "Using an Extended Kalman Filter to calculate a UAV's pose from IMU and GPS data."}
{"type": "node", "id": "repo:EPVelasco/lidar-camera-fusion", "kind": "repo", "label": "EPVelasco/lidar-camera-fusion", "url": "https://github.com/EPVelasco/lidar-camera-fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 325, "lang": "C++", "desc": "The code implemented in ROS projects a point cloud obtained by a Velodyne VLP16 3D-Lidar sensor on an image from an RGB camera."}
{"type": "node", "id": "repo:mit-han-lab/bevfusion", "kind": "repo", "label": "mit-han-lab/bevfusion", "url": "https://github.com/mit-han-lab/bevfusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 3201, "lang": "Python", "desc": "[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation"}
{"type": "node", "id": "repo:CDonosoK/ros2_camera_lidar_fusion", "kind": "repo", "label": "CDonosoK/ros2_camera_lidar_fusion", "url": "https://github.com/CDonosoK/ros2_camera_lidar_fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 218, "lang": "Python", "desc": "ROS2 Package to calculate the intrinsic and extrinsic camera calibration. Adding an easy way to fuse camera and lidars"}
{"type": "node", "id": "repo:LiuFG/Camera-Lidar-Fusion-ROS", "kind": "repo", "label": "LiuFG/Camera-Lidar-Fusion-ROS", "url": "https://github.com/LiuFG/Camera-Lidar-Fusion-ROS", "source": "github", "axis": "fusion", "layer": 0, "stars": 215, "lang": "C", "desc": "fully applied in ROS. simply fuse the category and location information"}
{"type": "node", "id": "repo:joshmcculloch/lidar-camera-fusion", "kind": "repo", "label": "joshmcculloch/lidar-camera-fusion", "url": "https://github.com/joshmcculloch/lidar-camera-fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 59, "lang": "C++", "desc": ""}
{"type": "node", "id": "repo:ADLab-AutoDrive/BEVFusion", "kind": "repo", "label": "ADLab-AutoDrive/BEVFusion", "url": "https://github.com/ADLab-AutoDrive/BEVFusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 970, "lang": "Python", "desc": "Offical PyTorch implementation of \"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework\""}
{"type": "node", "id": "repo:pangsu0613/CLOCs", "kind": "repo", "label": "pangsu0613/CLOCs", "url": "https://github.com/pangsu0613/CLOCs", "source": "github", "axis": "fusion", "layer": 0, "stars": 404, "lang": "Python", "desc": "CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection"}
{"type": "node", "id": "repo:godloveliang/SFND_3D_Object_Tracking", "kind": "repo", "label": "godloveliang/SFND_3D_Object_Tracking", "url": "https://github.com/godloveliang/SFND_3D_Object_Tracking", "source": "github", "axis": "fusion", "layer": 0, "stars": 79, "lang": "C++", "desc": "camera object tracking\uff0clidar object tracking, camera and lidar fusion object tracking"}
{"type": "node", "id": "repo:ICEORY/DeepStream", "kind": "repo", "label": "ICEORY/DeepStream", "url": "https://github.com/ICEORY/DeepStream", "source": "github", "axis": "fusion", "layer": 0, "stars": 101, "lang": "Python", "desc": "A Platform for LiDAR-Camera Fusion"}
{"type": "node", "id": "repo:haomo-ai/SuperFusion", "kind": "repo", "label": "haomo-ai/SuperFusion", "url": "https://github.com/haomo-ai/SuperFusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 393, "lang": "Python", "desc": "[ICRA 2024] SuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map Generation"}
{"type": "node", "id": "repo:jie0110/image-pointcloud-fusion", "kind": "repo", "label": "jie0110/image-pointcloud-fusion", "url": "https://github.com/jie0110/image-pointcloud-fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 55, "lang": "Python", "desc": "LiDAR and camera fusion"}
{"type": "node", "id": "repo:ISEE-Technology/lidar-with-velocity", "kind": "repo", "label": "ISEE-Technology/lidar-with-velocity", "url": "https://github.com/ISEE-Technology/lidar-with-velocity", "source": "github", "axis": "fusion", "layer": 0, "stars": 274, "lang": "C++", "desc": "[RAL & IROS 2022] Lidar With Velocity: Correcting Moving Objects Point Cloud Distortion From Oscillating Scanning Lidars by Fusion With Camera"}
{"type": "node", "id": "repo:AutoLidarPerception/kitti_lidar_camera", "kind": "repo", "label": "AutoLidarPerception/kitti_lidar_camera", "url": "https://github.com/AutoLidarPerception/kitti_lidar_camera", "source": "github", "axis": "fusion", "layer": 0, "stars": 45, "lang": "Python", "desc": "KiTTI LiDAR-Camera Fusion, implemented using kitti_ros."}
{"type": "node", "id": "repo:OrangeSodahub/CRLFnet", "kind": "repo", "label": "OrangeSodahub/CRLFnet", "url": "https://github.com/OrangeSodahub/CRLFnet", "source": "github", "axis": "fusion", "layer": 0, "stars": 142, "lang": "Python", "desc": "Realtime Camera-Radar-Lidar Fusion detection in ROS simulation."}
{"type": "node", "id": "repo:HuangCongQing/multi-sensor-fusion", "kind": "repo", "label": "HuangCongQing/multi-sensor-fusion", "url": "https://github.com/HuangCongQing/multi-sensor-fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 71, "lang": "HTML", "desc": "\u591a\u4f20\u611f\u5668\u878d\u5408\uff08lidar radar camera\uff09"}
{"type": "node", "id": "repo:GCaptainNemo/Fusion-Lidar-Camera-ROS", "kind": "repo", "label": "GCaptainNemo/Fusion-Lidar-Camera-ROS", "url": "https://github.com/GCaptainNemo/Fusion-Lidar-Camera-ROS", "source": "github", "axis": "fusion", "layer": 0, "stars": 58, "lang": "C++", "desc": "This repository uses a ROS node to subscribe to camera (hikvision) and lidar (livox) data. After the node merges the data, it publishes the colored point cloud and displays it in rviz. "}
{"type": "node", "id": "repo:zcbmlijygrdwa/camera_lidar_fusion", "kind": "repo", "label": "zcbmlijygrdwa/camera_lidar_fusion", "url": "https://github.com/zcbmlijygrdwa/camera_lidar_fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 44, "lang": "Python", "desc": "Calibrate camera to lidar"}
{"type": "node", "id": "repo:TimKie/YOLO-LiDAR-Fusion", "kind": "repo", "label": "TimKie/YOLO-LiDAR-Fusion", "url": "https://github.com/TimKie/YOLO-LiDAR-Fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 78, "lang": "Python", "desc": "LiDAR-Camera Fusion for 3D Object Detection in Autonomous Driving Systems"}
{"type": "node", "id": "repo:APRIL-ZJU/Gaussian-LIC", "kind": "repo", "label": "APRIL-ZJU/Gaussian-LIC", "url": "https://github.com/APRIL-ZJU/Gaussian-LIC", "source": "github", "axis": "fusion", "layer": 0, "stars": 562, "lang": "C++", "desc": "[ICRA 2025] Gaussian-LIC: Real-Time Photo-Realistic SLAM with Gaussian Splatting and LiDAR-Inertial-Camera Fusion"}
{"type": "node", "id": "repo:wangxiyang2022/DeepFusionMOT", "kind": "repo", "label": "wangxiyang2022/DeepFusionMOT", "url": "https://github.com/wangxiyang2022/DeepFusionMOT", "source": "github", "axis": "fusion", "layer": 0, "stars": 245, "lang": "Python", "desc": "Code for RA-L journal and IROS 2022 paper \"DeepFusionMOT: A 3D Multi-Object Tracking Framework Based on  Camera-LiDAR Fusion with Deep Association\"."}
{"type": "node", "id": "repo:HKUST-Aerial-Robotics/VINS-Fusion", "kind": "repo", "label": "HKUST-Aerial-Robotics/VINS-Fusion", "url": "https://github.com/HKUST-Aerial-Robotics/VINS-Fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 4616, "lang": "C++", "desc": "An optimization-based multi-sensor state estimator"}
{"type": "node", "id": "repo:2013fangwentao/Multi_Sensor_Fusion", "kind": "repo", "label": "2013fangwentao/Multi_Sensor_Fusion", "url": "https://github.com/2013fangwentao/Multi_Sensor_Fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 930, "lang": "C++", "desc": "Multi-Sensor Fusion (GNSS, IMU, Camera) \u591a\u6e90\u591a\u4f20\u611f\u5668\u878d\u5408\u5b9a\u4f4d GPS/INS\u7ec4\u5408\u5bfc\u822a  PPP/INS\u7d27\u7ec4\u5408"}
{"type": "node", "id": "repo:ethz-asl/ethzasl_sensor_fusion", "kind": "repo", "label": "ethz-asl/ethzasl_sensor_fusion", "url": "https://github.com/ethz-asl/ethzasl_sensor_fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 334, "lang": "C++", "desc": "time delay single and multi sensor fusion framework based on an EKF"}
{"type": "node", "id": "repo:zhh2005757/FAST-LIO-Multi-Sensor-Fusion", "kind": "repo", "label": "zhh2005757/FAST-LIO-Multi-Sensor-Fusion", "url": "https://github.com/zhh2005757/FAST-LIO-Multi-Sensor-Fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 313, "lang": "C++", "desc": "Fusing GNSS and wheel measurements based on FAST-LIO and IKFOM"}
{"type": "node", "id": "repo:sjtuyinjie/Ultra-Fusion", "kind": "repo", "label": "sjtuyinjie/Ultra-Fusion", "url": "https://github.com/sjtuyinjie/Ultra-Fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 584, "lang": "Shell", "desc": "Ultra-Fusion: A Resilient Tightly-Coupled Multi-Sensor Fusion SLAM Framework under Sensor Degradation and Spatiotemporal Perturbation"}
{"type": "node", "id": "repo:AlexGeControl/Sensor-Fusion-for-Localization-Courseware", "kind": "repo", "label": "AlexGeControl/Sensor-Fusion-for-Localization-Courseware", "url": "https://github.com/AlexGeControl/Sensor-Fusion-for-Localization-Courseware", "source": "github", "axis": "fusion", "layer": 0, "stars": 139, "lang": "C++", "desc": "Multi-sensor fusion for localization courseware, \u6df1\u84dd\u5b66\u9662, China"}
{"type": "node", "id": "repo:yichen928/SparseFusion", "kind": "repo", "label": "yichen928/SparseFusion", "url": "https://github.com/yichen928/SparseFusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 270, "lang": "Python", "desc": "[ICCV 2023] SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection"}
{"type": "node", "id": "repo:autonomousvision/transfuser", "kind": "repo", "label": "autonomousvision/transfuser", "url": "https://github.com/autonomousvision/transfuser", "source": "github", "axis": "fusion", "layer": 0, "stars": 1575, "lang": "Python", "desc": "[PAMI'23] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving; [CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving"}
{"type": "node", "id": "repo:jypjypjypjyp/lvio_fusion", "kind": "repo", "label": "jypjypjypjyp/lvio_fusion", "url": "https://github.com/jypjypjypjyp/lvio_fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 274, "lang": "C++", "desc": "Lvio-Fusion: A Self-adaptive Multi-sensor Fusion SLAM Framework Using Actor-critic Method (IROS 2021)"}
{"type": "node", "id": "repo:TurtleZhong/LVIO-SAM", "kind": "repo", "label": "TurtleZhong/LVIO-SAM", "url": "https://github.com/TurtleZhong/LVIO-SAM", "source": "github", "axis": "fusion", "layer": 0, "stars": 238, "lang": "C++", "desc": "A Multi-sensor Fusion Odometry via Smoothing and Mapping."}
{"type": "node", "id": "repo:ICEORY/PMF", "kind": "repo", "label": "ICEORY/PMF", "url": "https://github.com/ICEORY/PMF", "source": "github", "axis": "fusion", "layer": 0, "stars": 231, "lang": "Python", "desc": "Perception-aware multi-sensor fusion for 3D LiDAR semantic segmentation (ICCV 2021)"}
{"type": "node", "id": "repo:GREAT-WHU/DBA-Fusion", "kind": "repo", "label": "GREAT-WHU/DBA-Fusion", "url": "https://github.com/GREAT-WHU/DBA-Fusion", "source": "github", "axis": "fusion", "layer": 0, "stars": 217, "lang": "Python", "desc": "[RA-L 2024] Fusing deep dense bundle adjustment (DBA) with multi-sensor factor graph optimization."}
{"type": "node", "id": "repo:kekeliu-whu/MSF_LOAM", "kind": "repo", "label": "kekeliu-whu/MSF_LOAM", "url": "https://github.com/kekeliu-whu/MSF_LOAM", "source": "github", "axis": "fusion", "layer": 0, "stars": 63, "lang": "C++", "desc": "Multi-Sensor Fusion SLAM Based on A-LOAM."}
{"type": "node", "id": "repo:zouyajing/multi_sensor_loclization_and_mapping", "kind": "repo", "label": "zouyajing/multi_sensor_loclization_and_mapping", "url": "https://github.com/zouyajing/multi_sensor_loclization_and_mapping", "source": "github", "axis": "fusion", "layer": 0, "stars": 50, "lang": "C++", "desc": "localization and mapping based on multiple sensor fusion"}
{"type": "node", "id": "repo:chakravarthi589/Event-based-Vision_Resources", "kind": "repo", "label": "chakravarthi589/Event-based-Vision_Resources", "url": "https://github.com/chakravarthi589/Event-based-Vision_Resources", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 313, "lang": "", "desc": "Resources Related to Event-based Vision | Event Cameras | DVS"}
{"type": "node", "id": "repo:cedric-scheerlinck/dvs_image_reconstruction", "kind": "repo", "label": "cedric-scheerlinck/dvs_image_reconstruction", "url": "https://github.com/cedric-scheerlinck/dvs_image_reconstruction", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 91, "lang": "C++", "desc": "Code for \"Continuous-time Intensity Estimation Using Event Cameras\" (ACCV, 2018)"}
{"type": "node", "id": "repo:idsc-frazzoli/retina", "kind": "repo", "label": "idsc-frazzoli/retina", "url": "https://github.com/idsc-frazzoli/retina", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 59, "lang": "MATLAB", "desc": "interfaces and algorithms for event based cameras, lidars, and actuators"}
{"type": "node", "id": "repo:VLOGroup/dvs-panotracking", "kind": "repo", "label": "VLOGroup/dvs-panotracking", "url": "https://github.com/VLOGroup/dvs-panotracking", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 38, "lang": "C++", "desc": "This repository accompanies our ICCP 2017 publication \"Real-Time Panoramic Tracking for Event Cameras\""}
{"type": "node", "id": "repo:Event-AHU/Event_Camera_in_Top_Conference", "kind": "repo", "label": "Event-AHU/Event_Camera_in_Top_Conference", "url": "https://github.com/Event-AHU/Event_Camera_in_Top_Conference", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 121, "lang": "", "desc": "Event camera (DVS, Spike) based Papers Published on Top International Conference"}
{"type": "node", "id": "repo:VLOGroup/dvs-reconstruction", "kind": "repo", "label": "VLOGroup/dvs-reconstruction", "url": "https://github.com/VLOGroup/dvs-reconstruction", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 57, "lang": "C++", "desc": "This repository provides software to our publication \"Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation\", BMVC 2016"}
{"type": "node", "id": "repo:better-flow/pydvs", "kind": "repo", "label": "better-flow/pydvs", "url": "https://github.com/better-flow/pydvs", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 45, "lang": "Python", "desc": "A set of algorithms to work with DAVIS/DVS event-based cameras"}
{"type": "node", "id": "repo:prgumd/EVDodgeNet", "kind": "repo", "label": "prgumd/EVDodgeNet", "url": "https://github.com/prgumd/EVDodgeNet", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 121, "lang": "Python", "desc": "EVDodgeNet: Deep Dynamic Obstacle Dodging with event cameras"}
{"type": "node", "id": "repo:wangxiao5791509/VisEvent_SOT_Benchmark", "kind": "repo", "label": "wangxiao5791509/VisEvent_SOT_Benchmark", "url": "https://github.com/wangxiao5791509/VisEvent_SOT_Benchmark", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 168, "lang": "Python", "desc": "[IEEE TCYB 2023] The first large-scale tracking dataset by fusing RGB and Event cameras. "}
{"type": "node", "id": "repo:tub-rip/dvs_mcemvs", "kind": "repo", "label": "tub-rip/dvs_mcemvs", "url": "https://github.com/tub-rip/dvs_mcemvs", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 64, "lang": "C++", "desc": "Official implementation of AISY 2022 paper MC-EMVS (Multi-Camera Event-based Multi-View Stereo)"}
{"type": "node", "id": "repo:vision-agh/gcnn-dvs-fpga", "kind": "repo", "label": "vision-agh/gcnn-dvs-fpga", "url": "https://github.com/vision-agh/gcnn-dvs-fpga", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 22, "lang": "SystemVerilog", "desc": "Hardware Acceleration of Neural Networks for Event Camera-Based Object Detection on SoC FPGAs"}
{"type": "node", "id": "repo:tub-rip/dvs_global_flow_skeleton", "kind": "repo", "label": "tub-rip/dvs_global_flow_skeleton", "url": "https://github.com/tub-rip/dvs_global_flow_skeleton", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 38, "lang": "C++", "desc": "Global optical flow estimation with an event camera using contrast maximization (EVIS course at TU Berlin)"}
{"type": "node", "id": "repo:iliis/dvs_reconstruction", "kind": "repo", "label": "iliis/dvs_reconstruction", "url": "https://github.com/iliis/dvs_reconstruction", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 14, "lang": "Matlab", "desc": "Calculate full image from event based camera (dynamic vision sensor)"}
{"type": "node", "id": "repo:TristanWH/DVS4PD", "kind": "repo", "label": "TristanWH/DVS4PD", "url": "https://github.com/TristanWH/DVS4PD", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 6, "lang": "", "desc": "Here we collect papers for DVS4PD(DVS/Event-based Camera for Pedestrian Detection) from past 10 years."}
{"type": "node", "id": "repo:xueleichen/snn-dvs-carla", "kind": "repo", "label": "xueleichen/snn-dvs-carla", "url": "https://github.com/xueleichen/snn-dvs-carla", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 11, "lang": "Python", "desc": "SNNs for CARLA Event Camera Data"}
{"type": "node", "id": "repo:mapleee/dvs-sonification", "kind": "repo", "label": "mapleee/dvs-sonification", "url": "https://github.com/mapleee/dvs-sonification", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 7, "lang": "Python", "desc": "use event-based camera to get sonification!"}
{"type": "node", "id": "repo:Neuromorphicism/neuromorphic-bird-classifier-desktop-app-dvs-stream-cli-and-gui", "kind": "repo", "label": "Neuromorphicism/neuromorphic-bird-classifier-desktop-app-dvs-stream-cli-and-gui", "url": "https://github.com/Neuromorphicism/neuromorphic-bird-classifier-desktop-app-dvs-stream-cli-and-gui", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 12, "lang": "Python", "desc": "Neuromorphic Bird Classifier Desktop App (NeuroBCDA) bundled with Live Event Camera Simulator"}
{"type": "node", "id": "repo:cargonriv/dvs", "kind": "repo", "label": "cargonriv/dvs", "url": "https://github.com/cargonriv/dvs", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 3, "lang": "C++", "desc": "Dynamic Vision Sensor Application (Event Based Camera detection)"}
{"type": "node", "id": "repo:tub-rip/dvs_mosaic_skeleton", "kind": "repo", "label": "tub-rip/dvs_mosaic_skeleton", "url": "https://github.com/tub-rip/dvs_mosaic_skeleton", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 6, "lang": "C++", "desc": "Partial re-implementation of Simultaneous Mosaicing and Tracking with an Event Camera, BMVC 2014 (EVIS course at TU Berlin)"}
{"type": "node", "id": "repo:NAIL-HNU/CalibrMultiDvs", "kind": "repo", "label": "NAIL-HNU/CalibrMultiDvs", "url": "https://github.com/NAIL-HNU/CalibrMultiDvs", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 4, "lang": "C++", "desc": "This repository provides tools for calibrating single or multiple Inivation event cameras."}
{"type": "node", "id": "repo:Kanaderu/lava-docker", "kind": "repo", "label": "Kanaderu/lava-docker", "url": "https://github.com/Kanaderu/lava-docker", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 1, "lang": "Dockerfile", "desc": "Docker Image of the Intel Lava Neuromorphic Computing Framework"}
{"type": "node", "id": "repo:open-neuromorphic/awesome-neuromorphic-hw", "kind": "repo", "label": "open-neuromorphic/awesome-neuromorphic-hw", "url": "https://github.com/open-neuromorphic/awesome-neuromorphic-hw", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 213, "lang": "", "desc": "Repository collecting papers about neuromorphic hardware, such as ASIC and FPGA implementations of SNNs and stuff."}
{"type": "node", "id": "repo:prophesee-ai/openeb", "kind": "repo", "label": "prophesee-ai/openeb", "url": "https://github.com/prophesee-ai/openeb", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 293, "lang": "C++", "desc": "Open source SDK to create applications leveraging event-based vision hardware equipment"}
{"type": "node", "id": "repo:open-neuromorphic/fpga-snntorch", "kind": "repo", "label": "open-neuromorphic/fpga-snntorch", "url": "https://github.com/open-neuromorphic/fpga-snntorch", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 75, "lang": "Jupyter Notebook", "desc": "Notebooks and code for Neuromorphic Hardware Workshop at ISFPGA 2024."}
{"type": "node", "id": "repo:qiaokaki/AedatTools", "kind": "repo", "label": "qiaokaki/AedatTools", "url": "https://github.com/qiaokaki/AedatTools", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 26, "lang": "Matlab", "desc": "Tools for manipulating .aedat files (timestamped address-event data from neuromorphic hardware), in Matlab and Python"}
{"type": "node", "id": "repo:alandiamond/spinnaker-neuromorphic-classifier", "kind": "repo", "label": "alandiamond/spinnaker-neuromorphic-classifier", "url": "https://github.com/alandiamond/spinnaker-neuromorphic-classifier", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 14, "lang": "C++", "desc": "Python PyNN code demonstrating classification using SpiNNaker neuromorphic hardware. This work was developed at the University of Sussex under funding from the Human Brain Project (HBP)."}
{"type": "node", "id": "repo:synsense/rockpool", "kind": "repo", "label": "synsense/rockpool", "url": "https://github.com/synsense/rockpool", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 87, "lang": "Python", "desc": "A machine learning library for spiking neural networks. Supports training with both torch and jax pipelines, and deployment to neuromorphic hardware."}
{"type": "node", "id": "repo:jeshraghian/ESSCIRC23-os-neuromorphic-tutorial", "kind": "repo", "label": "jeshraghian/ESSCIRC23-os-neuromorphic-tutorial", "url": "https://github.com/jeshraghian/ESSCIRC23-os-neuromorphic-tutorial", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 26, "lang": "Jupyter Notebook", "desc": "Notebooks for Hardware-Aware Training of Spiking Neural Networks. Open-Source Neuromorphic Circuit Design Tutorial at ESSCIRC 2023."}
{"type": "node", "id": "repo:synsense/sinabs", "kind": "repo", "label": "synsense/sinabs", "url": "https://github.com/synsense/sinabs", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 118, "lang": "Python", "desc": "A deep learning library for spiking neural networks which is based on PyTorch, focuses on fast training and supports inference on neuromorphic hardware."}
{"type": "node", "id": "repo:colinshane/LIF_Neuromorphic", "kind": "repo", "label": "colinshane/LIF_Neuromorphic", "url": "https://github.com/colinshane/LIF_Neuromorphic", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 9, "lang": "Verilog", "desc": "some of our simulation codes for : A Low-Cost High-Speed Neuromorphic Hardware Based on Spiking Neural Network"}
{"type": "node", "id": "repo:combra-lab/snn-eeg", "kind": "repo", "label": "combra-lab/snn-eeg", "url": "https://github.com/combra-lab/snn-eeg", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 51, "lang": "Python", "desc": "PyTorch and Loihi implementation of the Spiking Neural Network for decoding EEG on Neuromorphic Hardware"}
{"type": "node", "id": "repo:markplagge/NeMo", "kind": "repo", "label": "markplagge/NeMo", "url": "https://github.com/markplagge/NeMo", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 14, "lang": "C", "desc": "NeMo -  A hardware agnostic neuromorphic processor simulation model built on ROSS"}
{"type": "node", "id": "repo:Thonner/NeuromorphicProcessor", "kind": "repo", "label": "Thonner/NeuromorphicProcessor", "url": "https://github.com/Thonner/NeuromorphicProcessor", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 6, "lang": "Scala", "desc": "Neuromorphic hardware implementaion for Master thesis"}
{"type": "node", "id": "repo:lachlanchen/OpenHI", "kind": "repo", "label": "lachlanchen/OpenHI", "url": "https://github.com/lachlanchen/OpenHI", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 103, "lang": "Python", "desc": "Self\u2011calibrated neuromorphic hyperspectral imaging pipeline for event cameras with diffractive  illumination. Includes end\u2011to\u2011end tools for RAW segmentation, multi\u2011window time\u2011warping compensation, spectral visualization, and hardware contr"}
{"type": "node", "id": "repo:hisrg/Neural-Network-Compression-and-Accelerator-on-Hardware", "kind": "repo", "label": "hisrg/Neural-Network-Compression-and-Accelerator-on-Hardware", "url": "https://github.com/hisrg/Neural-Network-Compression-and-Accelerator-on-Hardware", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 52, "lang": "", "desc": "My name is Fang Biao. I'm currently pursuing my Master degree with the college of Computer Science and Engineering, Si Chuan University, Cheng Du, China. For more informantion about me and my research, you can go to [my homepage](https://gi"}
{"type": "node", "id": "repo:AdamDHines/LENS", "kind": "repo", "label": "AdamDHines/LENS", "url": "https://github.com/AdamDHines/LENS", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 25, "lang": "Python", "desc": "Code for LENS, fully neuromorphic place recognition integrating sensors, hardware, and algorithms for robotic localization."}
{"type": "node", "id": "repo:KI-ASIC-TUM/time-coded-SFT", "kind": "repo", "label": "KI-ASIC-TUM/time-coded-SFT", "url": "https://github.com/KI-ASIC-TUM/time-coded-SFT", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 10, "lang": "Jupyter Notebook", "desc": "SNN implementation of the Fourier transform in neuromorphic hardware "}
{"type": "node", "id": "repo:sandialabs/NeuroFEM", "kind": "repo", "label": "sandialabs/NeuroFEM", "url": "https://github.com/sandialabs/NeuroFEM", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 9, "lang": "Jupyter Notebook", "desc": "Code to accompany the paper \"Solving Sparse Finite Element Problems on Neuromorphic Hardware\""}
{"type": "node", "id": "repo:cepdnaclk/e16-4yp-neuromorphic-architecture", "kind": "repo", "label": "cepdnaclk/e16-4yp-neuromorphic-architecture", "url": "https://github.com/cepdnaclk/e16-4yp-neuromorphic-architecture", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 10, "lang": "VHDL", "desc": "Neuromorphic architectures are hardware architectures that use the biologically inspired neural functions as the basis of operation. Information processing based on spiking neuron architectures have caught considerable attention in recent y"}
{"type": "node", "id": "repo:ferdinandolivier/Dynex-Wallet-App", "kind": "repo", "label": "ferdinandolivier/Dynex-Wallet-App", "url": "https://github.com/ferdinandolivier/Dynex-Wallet-App", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "C++", "desc": "Dynex is a next-generation platform for neuromorphic computing based on a new flexible blockchain protocol. It is designed for the development of software applications and algorithms that utilize neuromorphic hardware and are capable of acc"}
{"type": "node", "id": "repo:solversa/Master-Thesis-Brain-Machine-Interface", "kind": "repo", "label": "solversa/Master-Thesis-Brain-Machine-Interface", "url": "https://github.com/solversa/Master-Thesis-Brain-Machine-Interface", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 2, "lang": "Jupyter Notebook", "desc": "Decoding of 3D Reach and Grasp Movements from Non-invasive EEG Signals using SpiNNaker Neuromorphic Hardware"}
{"type": "node", "id": "repo:nengo/nengo-ocl", "kind": "repo", "label": "nengo/nengo-ocl", "url": "https://github.com/nengo/nengo-ocl", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 26, "lang": "Python", "desc": "OpenCL-based simulator for Nengo neural models"}
{"type": "node", "id": "repo:nengo/nengo-mpi", "kind": "repo", "label": "nengo/nengo-mpi", "url": "https://github.com/nengo/nengo-mpi", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 5, "lang": "Python", "desc": "MPI backend for the nengo neural simulator."}
{"type": "node", "id": "repo:atakehiro/Neural_Simulator-Colab", "kind": "repo", "label": "atakehiro/Neural_Simulator-Colab", "url": "https://github.com/atakehiro/Neural_Simulator-Colab", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 4, "lang": "Jupyter Notebook", "desc": "Demo code of neural simulators for Google Colab"}
{"type": "node", "id": "repo:simondlevy/NengoCPP", "kind": "repo", "label": "simondlevy/NengoCPP", "url": "https://github.com/simondlevy/NengoCPP", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 2, "lang": "C++", "desc": "Example of how to call the Nengo neural simulator from C++"}
{"type": "node", "id": "repo:ctn-archive/gosmann-frontiers2017", "kind": "repo", "label": "ctn-archive/gosmann-frontiers2017", "url": "https://github.com/ctn-archive/gosmann-frontiers2017", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 3, "lang": "Jupyter Notebook", "desc": "Automatic Optimization of the Computation Graph in the Nengo Neural Network Simulator"}
{"type": "node", "id": "repo:NickleDave/aver", "kind": "repo", "label": "NickleDave/aver", "url": "https://github.com/NickleDave/aver", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 2, "lang": "Python", "desc": "aver: active vision models, built with the Nengo neural simulator"}
{"type": "node", "id": "repo:jvitku/nengo_java", "kind": "repo", "label": "jvitku/nengo_java", "url": "https://github.com/jvitku/nengo_java", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "Java", "desc": "The Nengo neural simulator, implemented in Java."}
{"type": "node", "id": "repo:mtrberzi/nengo-gpu-surrogate-backend", "kind": "repo", "label": "mtrberzi/nengo-gpu-surrogate-backend", "url": "https://github.com/mtrberzi/nengo-gpu-surrogate-backend", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "Python", "desc": "An OpenCL-accelerated backend for population surrogate simulation with the Nengo 2.0 neural simulator"}
{"type": "node", "id": "repo:kpc-simone/modelling_tutorial", "kind": "repo", "label": "kpc-simone/modelling_tutorial", "url": "https://github.com/kpc-simone/modelling_tutorial", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "Python", "desc": "Workshop on simulating and collaborating on neural architectures built with the Nengo simulator."}
{"type": "node", "id": "repo:OmarGAlcantara/MIL-Simulation-Nengo-ROS-XPlane", "kind": "repo", "label": "OmarGAlcantara/MIL-Simulation-Nengo-ROS-XPlane", "url": "https://github.com/OmarGAlcantara/MIL-Simulation-Nengo-ROS-XPlane", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "Python", "desc": "This is the repo which describes the Master Thesis work published at [] in which a communication scheme between the Neural Network Development Software, Nengo and the Flight Simulator, X-Plane are coonected for MIL simulations through ROS."}
{"type": "node", "id": "repo:jeshraghian/snntorch", "kind": "repo", "label": "jeshraghian/snntorch", "url": "https://github.com/jeshraghian/snntorch", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 2007, "lang": "Python", "desc": "Deep and online learning with spiking neural networks in Python"}
{"type": "node", "id": "repo:jjd1123/snntorch-implement4spike-deeplab", "kind": "repo", "label": "jjd1123/snntorch-implement4spike-deeplab", "url": "https://github.com/jjd1123/snntorch-implement4spike-deeplab", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 12, "lang": "Python", "desc": "snn implementation for spike-deeplab and spike-fcn"}
{"type": "node", "id": "repo:Laz4rz/spikingNeuralNetworks", "kind": "repo", "label": "Laz4rz/spikingNeuralNetworks", "url": "https://github.com/Laz4rz/spikingNeuralNetworks", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 6, "lang": "Jupyter Notebook", "desc": "Spiking Neural Networks dependance on initial conditions using snnTorch. The results are presented in my Bachelors Thesis: \"The impact of initial parameters on the learning of spiking neural networks\"."}
{"type": "node", "id": "repo:AndreaLolli2912/Spiking-ResNet", "kind": "repo", "label": "AndreaLolli2912/Spiking-ResNet", "url": "https://github.com/AndreaLolli2912/Spiking-ResNet", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 3, "lang": "Jupyter Notebook", "desc": "Spiking ResNet\u201118 (snnTorch) for blood\u2011pressure prediction from PPG. Implements PA\u2011B residual connections and Densely Additive Connections (Li et\u202fal., Rethinking residual connection in training large-scale spiking neural networks). Includes"}
{"type": "node", "id": "repo:Sergeevks/SpikingNetTutorial", "kind": "repo", "label": "Sergeevks/SpikingNetTutorial", "url": "https://github.com/Sergeevks/SpikingNetTutorial", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "Jupyter Notebook", "desc": "\u041f\u0435\u0440\u0435\u0432\u043e\u0434 \u0441 \u043a\u043e\u043c\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u044f\u043c\u0438 \u0442\u0443\u0442\u043e\u0440\u0438\u0430\u043b\u0430 \u043f\u043e  snntorch"}
{"type": "node", "id": "repo:shilpakancharla/snn-networking", "kind": "repo", "label": "shilpakancharla/snn-networking", "url": "https://github.com/shilpakancharla/snn-networking", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 12, "lang": "Python", "desc": "Neuromorphic computing is a new technology which uses very-large-scale integration (VLSI) systems containing electrical analogs that mimic neurobiological structures. Such technology can be simulated using the Python framework snnTorch, a d"}
{"type": "node", "id": "repo:chardiwall/DPSNN", "kind": "repo", "label": "chardiwall/DPSNN", "url": "https://github.com/chardiwall/DPSNN", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 4, "lang": "Jupyter Notebook", "desc": "A differentially private spiking neural network with temporal enhanced pooling"}
{"type": "node", "id": "repo:Brain-inspired-Neural-Networks-Lab/LGN_snnTorch_classification", "kind": "repo", "label": "Brain-inspired-Neural-Networks-Lab/LGN_snnTorch_classification", "url": "https://github.com/Brain-inspired-Neural-Networks-Lab/LGN_snnTorch_classification", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 2, "lang": "Jupyter Notebook", "desc": "A spiking neural network of the lateral geniculate nucleus developed on snnTorch running on GPU and demonstrating image classification task"}
{"type": "node", "id": "repo:reyhane-1997/snntorch_leaky", "kind": "repo", "label": "reyhane-1997/snntorch_leaky", "url": "https://github.com/reyhane-1997/snntorch_leaky", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "", "desc": "spiking neural network"}
{"type": "node", "id": "repo:jmadden173/tt05-delta-modulation", "kind": "repo", "label": "jmadden173/tt05-delta-modulation", "url": "https://github.com/jmadden173/tt05-delta-modulation", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 2, "lang": "Verilog", "desc": "Delta Modulation for Spiking Neural Networks (SNN) based on snnTorch's implementation"}
{"type": "node", "id": "repo:Saad-data/ANN-to-SNN-Conversion-with-snnTorch", "kind": "repo", "label": "Saad-data/ANN-to-SNN-Conversion-with-snnTorch", "url": "https://github.com/Saad-data/ANN-to-SNN-Conversion-with-snnTorch", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 2, "lang": "Jupyter Notebook", "desc": "Demonstrates the conversion of a simple Artificial Neural Network (ANN) into a Spiking Neural Network (SNN) using the snnTorch library."}
{"type": "node", "id": "repo:Twenkid/SNN", "kind": "repo", "label": "Twenkid/SNN", "url": "https://github.com/Twenkid/SNN", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "", "desc": "Spiking neural networks - examples, tests ... snntorch, Lava, ..."}
{"type": "node", "id": "repo:franzhd/snntorch_network", "kind": "repo", "label": "franzhd/snntorch_network", "url": "https://github.com/franzhd/snntorch_network", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "Jupyter Notebook", "desc": "Folder for training HAR spiking neural networks with snntorch "}
{"type": "node", "id": "repo:Triponymous/brAIn", "kind": "repo", "label": "Triponymous/brAIn", "url": "https://github.com/Triponymous/brAIn", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 7, "lang": "Python", "desc": "A persistent spiking neural network that lives on your desktop \u2014 1,260 neurons, STDP learning, neuromodulators, and an LLM speech layer."}
{"type": "node", "id": "repo:muddycode-tech/SPIKING_MNIST_SNN", "kind": "repo", "label": "muddycode-tech/SPIKING_MNIST_SNN", "url": "https://github.com/muddycode-tech/SPIKING_MNIST_SNN", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "Python", "desc": "Simple Spiking Neural Network (SNN) using snnTorch for MNIST digit classification"}
{"type": "node", "id": "repo:spikora/SpikingTSF", "kind": "repo", "label": "spikora/SpikingTSF", "url": "https://github.com/spikora/SpikingTSF", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 2, "lang": "Python", "desc": "Open-source Benchmark Library for Spiking Neural Network based Time-Series Forecasting."}
{"type": "node", "id": "repo:Biswajitnahak2003/snn-glacier-segmentation", "kind": "repo", "label": "Biswajitnahak2003/snn-glacier-segmentation", "url": "https://github.com/Biswajitnahak2003/snn-glacier-segmentation", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "Jupyter Notebook", "desc": "image segmentation using spiking neural network "}
{"type": "node", "id": "repo:KrishnaSagar-108/SNNtorch.js-SpikeNet.js", "kind": "repo", "label": "KrishnaSagar-108/SNNtorch.js-SpikeNet.js", "url": "https://github.com/KrishnaSagar-108/SNNtorch.js-SpikeNet.js", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "", "desc": "Lightweight, Event-Driven Spiking Neural Networks for Edge Devices in JavaScript"}
{"type": "node", "id": "repo:KP-AROB/AROB-SNNTorch", "kind": "repo", "label": "KP-AROB/AROB-SNNTorch", "url": "https://github.com/KP-AROB/AROB-SNNTorch", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 1, "lang": "Jupyter Notebook", "desc": "Code to reproduce the work in \"Optimizing Neural Coding in Spiking Neural Networks for Mammography Image Processing\""}
{"type": "node", "id": "repo:SpikingIntelligenceSystem/snn-mnist-classifier-project", "kind": "repo", "label": "SpikingIntelligenceSystem/snn-mnist-classifier-project", "url": "https://github.com/SpikingIntelligenceSystem/snn-mnist-classifier-project", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "Python", "desc": "Spiking neural network classifier for MNIST using PyTorch and snnTorch."}
{"type": "node", "id": "repo:fangwei123456/spikingjelly", "kind": "repo", "label": "fangwei123456/spikingjelly", "url": "https://github.com/fangwei123456/spikingjelly", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 2059, "lang": "Python", "desc": "SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch."}
{"type": "node", "id": "repo:conda-forge/spikingjelly-feedstock", "kind": "repo", "label": "conda-forge/spikingjelly-feedstock", "url": "https://github.com/conda-forge/spikingjelly-feedstock", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "", "desc": "A conda-smithy repository for spikingjelly."}
{"type": "node", "id": "repo:Barchid/spikingjelly-lightning", "kind": "repo", "label": "Barchid/spikingjelly-lightning", "url": "https://github.com/Barchid/spikingjelly-lightning", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 5, "lang": "Python", "desc": "Spiking Neural Network for Computer Vision using SpikingJelly framework and Pytorch-Lightning "}
{"type": "node", "id": "repo:IamSandipanBhowmick/SNN_DSpike", "kind": "repo", "label": "IamSandipanBhowmick/SNN_DSpike", "url": "https://github.com/IamSandipanBhowmick/SNN_DSpike", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 1, "lang": "", "desc": "base code DSPIKE with SPikingjelly"}
{"type": "node", "id": "repo:TheBrainLab/Awesome-Spiking-Neural-Networks", "kind": "repo", "label": "TheBrainLab/Awesome-Spiking-Neural-Networks", "url": "https://github.com/TheBrainLab/Awesome-Spiking-Neural-Networks", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 797, "lang": "", "desc": "A paper list of spiking neural networks, including papers, codes, and related websites.  \u672c\u4ed3\u5e93\u6536\u96c6\u8109\u51b2\u795e\u7ecf\u7f51\u7edc\u76f8\u5173\u7684\u9876\u4f1a\u9876\u520a\u4ee5\u53caCNS\u8bba\u6587\u548c\u4ee3\u7801\uff0c\u6b63\u5728\u6301\u7eed\u66f4\u65b0\u4e2d\u3002"}
{"type": "node", "id": "repo:TheBrainLab/Spikingformer", "kind": "repo", "label": "TheBrainLab/Spikingformer", "url": "https://github.com/TheBrainLab/Spikingformer", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 143, "lang": "Python", "desc": "Spikingformer: A Key Foundation Model for Spiking Neural Networks (AAAI 2026)"}
{"type": "node", "id": "repo:Yanqi-Chen/spikingjellyCppExt", "kind": "repo", "label": "Yanqi-Chen/spikingjellyCppExt", "url": "https://github.com/Yanqi-Chen/spikingjellyCppExt", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 3, "lang": "Cuda", "desc": "SpikingJelly\u6846\u67b6\u7684C++\u6269\u5c55 \u00b7 The C++ extensions of SpikingJelly"}
{"type": "node", "id": "repo:IamSandipanBhowmick/SNN-Segmentation-Via-SpikingJelly", "kind": "repo", "label": "IamSandipanBhowmick/SNN-Segmentation-Via-SpikingJelly", "url": "https://github.com/IamSandipanBhowmick/SNN-Segmentation-Via-SpikingJelly", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 2, "lang": "Jupyter Notebook", "desc": "Semantic Segmentation Using Spikingjelly"}
{"type": "node", "id": "repo:CodeAlanqian/SNN-MNIST", "kind": "repo", "label": "CodeAlanqian/SNN-MNIST", "url": "https://github.com/CodeAlanqian/SNN-MNIST", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 6, "lang": "Jupyter Notebook", "desc": "\u57fa\u4e8epytorch\uff0cspikingjelly\u5b9e\u73b0SNN\u8bad\u7ec3MNIST\u624b\u5199\u6570\u636e\u96c6"}
{"type": "node", "id": "repo:lcedapro/SpikingJelly", "kind": "repo", "label": "lcedapro/SpikingJelly", "url": "https://github.com/lcedapro/SpikingJelly", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 2, "lang": "Python", "desc": "SpikingJelly and PAIBox Learning"}
{"type": "node", "id": "repo:coderonion/awesome-snn", "kind": "repo", "label": "coderonion/awesome-snn", "url": "https://github.com/coderonion/awesome-snn", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 235, "lang": "", "desc": "\ud83d\udd25\ud83d\udd25\ud83d\udd25A collection of some awesome public SNN(Spiking Neural Network) projects."}
{"type": "node", "id": "repo:DPR00/SpikingNeuralNetworks", "kind": "repo", "label": "DPR00/SpikingNeuralNetworks", "url": "https://github.com/DPR00/SpikingNeuralNetworks", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 4, "lang": "Jupyter Notebook", "desc": "This repository contains files related to the training of SNNs for object recognition using SpikingJelly library and PyTorch."}
{"type": "node", "id": "repo:TheBrainLab/SGLFormer", "kind": "repo", "label": "TheBrainLab/SGLFormer", "url": "https://github.com/TheBrainLab/SGLFormer", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 22, "lang": "Python", "desc": "Spiking Global-Local Fusion Transformer"}
{"type": "node", "id": "repo:gv1x2/ANN2SNN-SpikingJelly-", "kind": "repo", "label": "gv1x2/ANN2SNN-SpikingJelly-", "url": "https://github.com/gv1x2/ANN2SNN-SpikingJelly-", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 3, "lang": "Jupyter Notebook", "desc": ""}
{"type": "node", "id": "repo:AllenYolk/dendritic-spiking-neuron", "kind": "repo", "label": "AllenYolk/dendritic-spiking-neuron", "url": "https://github.com/AllenYolk/dendritic-spiking-neuron", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 4, "lang": "Python", "desc": "A new dendritic computing package based on pytorch and spikingjelly. Draw inspiration from the nonlinear nature of biological dendritic neurons!"}
{"type": "node", "id": "repo:daydreamal/SpikingJelly_study", "kind": "repo", "label": "daydreamal/SpikingJelly_study", "url": "https://github.com/daydreamal/SpikingJelly_study", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "", "desc": "SpikingJelly study"}
{"type": "node", "id": "repo:ali-rasteh/spikingjelly-develop", "kind": "repo", "label": "ali-rasteh/spikingjelly-develop", "url": "https://github.com/ali-rasteh/spikingjelly-develop", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 2, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:DingJianhao/spikingjelly_lite", "kind": "repo", "label": "DingJianhao/spikingjelly_lite", "url": "https://github.com/DingJianhao/spikingjelly_lite", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 1, "lang": "Python", "desc": "A lite and essential version of spikingjelly (https://github.com/fangwei123456/spikingjelly)"}
{"type": "node", "id": "repo:Barchid/liaf-lightning", "kind": "repo", "label": "Barchid/liaf-lightning", "url": "https://github.com/Barchid/liaf-lightning", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "Python", "desc": "SpikingJelly + LIAF Neurons with Lightning"}
{"type": "node", "id": "repo:twetto/sje_extensions", "kind": "repo", "label": "twetto/sje_extensions", "url": "https://github.com/twetto/sje_extensions", "source": "github", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "stars": 0, "lang": "Python", "desc": "Extensions for the SpikingJelly library."}
{"type": "node", "id": "repo:lululxvi/deepxde", "kind": "repo", "label": "lululxvi/deepxde", "url": "https://github.com/lululxvi/deepxde", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 4286, "lang": "Python", "desc": "A library for scientific machine learning and physics-informed learning"}
{"type": "node", "id": "repo:Wulx2050/DeepXDE-and-PINN", "kind": "repo", "label": "Wulx2050/DeepXDE-and-PINN", "url": "https://github.com/Wulx2050/DeepXDE-and-PINN", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 156, "lang": "Jupyter Notebook", "desc": "DeepXDE and PINN"}
{"type": "node", "id": "repo:imcs-compsim/pinns_for_comp_mech", "kind": "repo", "label": "imcs-compsim/pinns_for_comp_mech", "url": "https://github.com/imcs-compsim/pinns_for_comp_mech", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 69, "lang": "Python", "desc": "Implementation of Physics-Informed Neural Networks for Computational Mechanics based on the DeepXDE package."}
{"type": "node", "id": "repo:aid4nscud/PINNResearch", "kind": "repo", "label": "aid4nscud/PINNResearch", "url": "https://github.com/aid4nscud/PINNResearch", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 21, "lang": "Python", "desc": "Physics-Informed Neural Networks: Forward/Inverse Modeling of Partial Differential Equations"}
{"type": "node", "id": "repo:stfc-sciml/DeepXDE-ZCS", "kind": "repo", "label": "stfc-sciml/DeepXDE-ZCS", "url": "https://github.com/stfc-sciml/DeepXDE-ZCS", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 8, "lang": "Python", "desc": "Contains ZCS integrated version of the DeepXDE"}
{"type": "node", "id": "repo:yiwang89/lululxvi-deepxde", "kind": "repo", "label": "yiwang89/lululxvi-deepxde", "url": "https://github.com/yiwang89/lululxvi-deepxde", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 10, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:circularsquare/dxde-covid", "kind": "repo", "label": "circularsquare/dxde-covid", "url": "https://github.com/circularsquare/dxde-covid", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 4, "lang": "Python", "desc": "using deepxde to predict covid-19s SIR coefficients and covid spread"}
{"type": "node", "id": "repo:PhysicsTeacher13/Deepxde", "kind": "repo", "label": "PhysicsTeacher13/Deepxde", "url": "https://github.com/PhysicsTeacher13/Deepxde", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 0, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:conda-forge/deepxde-feedstock", "kind": "repo", "label": "conda-forge/deepxde-feedstock", "url": "https://github.com/conda-forge/deepxde-feedstock", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 0, "lang": "Python", "desc": "A conda-smithy repository for deepxde."}
{"type": "node", "id": "repo:pescap/FastDeepXDE", "kind": "repo", "label": "pescap/FastDeepXDE", "url": "https://github.com/pescap/FastDeepXDE", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 0, "lang": "", "desc": "Horovod acceleration of the DeepXDE library"}
{"type": "node", "id": "repo:KozakHou/Python-Tensorflow-DeepXDE", "kind": "repo", "label": "KozakHou/Python-Tensorflow-DeepXDE", "url": "https://github.com/KozakHou/Python-Tensorflow-DeepXDE", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 6, "lang": "Jupyter Notebook", "desc": ""}
{"type": "node", "id": "repo:javierfa98/PINNs-Examples", "kind": "repo", "label": "javierfa98/PINNs-Examples", "url": "https://github.com/javierfa98/PINNs-Examples", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 9, "lang": "Python", "desc": "Examples of Physics-Informed Neural Networks (PINNs), implemented with PyTorch and DeepXDE."}
{"type": "node", "id": "repo:shadzzz90/Heat-Equation-using-Deep-Galerkin-Method-and-DeepXDE", "kind": "repo", "label": "shadzzz90/Heat-Equation-using-Deep-Galerkin-Method-and-DeepXDE", "url": "https://github.com/shadzzz90/Heat-Equation-using-Deep-Galerkin-Method-and-DeepXDE", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 2, "lang": "Jupyter Notebook", "desc": ""}
{"type": "node", "id": "repo:athtareq/PFE_LicenceMIASI", "kind": "repo", "label": "athtareq/PFE_LicenceMIASI", "url": "https://github.com/athtareq/PFE_LicenceMIASI", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 2, "lang": "", "desc": "My undergraduate end of studies project / Mon projet de fin d'etudes de Licence SOLVING DIFFERENTIAL EQUATIONS USING THE DEEP LEARNING LIBRARY DEEPXDE / RESOLUTION DES EQUATIONS DIFFERENTIELLES EN UTLISANT LA LIBRAIRIE D'APPRENTISSAGE PROFO"}
{"type": "node", "id": "repo:praksharma/DeepXDE-frontend", "kind": "repo", "label": "praksharma/DeepXDE-frontend", "url": "https://github.com/praksharma/DeepXDE-frontend", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 2, "lang": "Python", "desc": "A GUI frontend for DeepXDE."}
{"type": "node", "id": "repo:zongzi13545329/PINNS", "kind": "repo", "label": "zongzi13545329/PINNS", "url": "https://github.com/zongzi13545329/PINNS", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 2, "lang": "Python", "desc": "A lite implement of DeepXDE"}
{"type": "node", "id": "repo:xuelanghanbao/AI4XDE", "kind": "repo", "label": "xuelanghanbao/AI4XDE", "url": "https://github.com/xuelanghanbao/AI4XDE", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 6, "lang": "Python", "desc": "A library of XDE cases and algorithm"}
{"type": "node", "id": "repo:tonymlebaron/DeepXDE_Training", "kind": "repo", "label": "tonymlebaron/DeepXDE_Training", "url": "https://github.com/tonymlebaron/DeepXDE_Training", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 0, "lang": "Jupyter Notebook", "desc": "Learning to use DeepXDE"}
{"type": "node", "id": "repo:zjuliu/AIgibson", "kind": "repo", "label": "zjuliu/AIgibson", "url": "https://github.com/zjuliu/AIgibson", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 0, "lang": "Python", "desc": "Gibson inversion by deepxde"}
{"type": "node", "id": "repo:StoneDaweiKing/Example_on_deepXde", "kind": "repo", "label": "StoneDaweiKing/Example_on_deepXde", "url": "https://github.com/StoneDaweiKing/Example_on_deepXde", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 2, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:neo-fetch/nvidia-modulus-airfoil-optimisation", "kind": "repo", "label": "neo-fetch/nvidia-modulus-airfoil-optimisation", "url": "https://github.com/neo-fetch/nvidia-modulus-airfoil-optimisation", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 26, "lang": "Python", "desc": "Using NVIDIA modulus for airfoil optimizations at different angles. "}
{"type": "node", "id": "repo:adytiaa/physAI_CFDsim", "kind": "repo", "label": "adytiaa/physAI_CFDsim", "url": "https://github.com/adytiaa/physAI_CFDsim", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 6, "lang": "Jupyter Notebook", "desc": "CFD simulation performed using Physics based AI models (Nvidia modulus)"}
{"type": "node", "id": "repo:TejasARathod/PhyCV-PhysicsNemo-Triton-Yolov9", "kind": "repo", "label": "TejasARathod/PhyCV-PhysicsNemo-Triton-Yolov9", "url": "https://github.com/TejasARathod/PhyCV-PhysicsNemo-Triton-Yolov9", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 2, "lang": "Python", "desc": "During 2024, I was heavily invested in NVIDIA's Modulus now known as PhysicsNemo. This repository is dedicated to my vision I had in 2024 of combining computer vision with physics. To capture the seen and unseen."}
{"type": "node", "id": "repo:Mattjesc/PTQ-MeshGraphNet-NVIDIA-Modulus", "kind": "repo", "label": "Mattjesc/PTQ-MeshGraphNet-NVIDIA-Modulus", "url": "https://github.com/Mattjesc/PTQ-MeshGraphNet-NVIDIA-Modulus", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 1, "lang": "Python", "desc": "Post-Training Quantization for MeshGraphNet Physics-Based ML Model: Cardiovascular Flow Simulation Implementation"}
{"type": "node", "id": "repo:Shrestha-Bipin/PINN_Projects", "kind": "repo", "label": "Shrestha-Bipin/PINN_Projects", "url": "https://github.com/Shrestha-Bipin/PINN_Projects", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 0, "lang": "Jupyter Notebook", "desc": "Physics-Informed Neural Network (PINN) examples for classical ODE systems, including Newton\u2019s Law of Cooling and a three-mass spring system, implemented with PyTorch and NVIDIA Modulus."}
{"type": "node", "id": "repo:saitejasrivilli/maxwell-pinn", "kind": "repo", "label": "saitejasrivilli/maxwell-pinn", "url": "https://github.com/saitejasrivilli/maxwell-pinn", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 1, "lang": "Python", "desc": "Physics-informed neural network solving Maxwell's equations in ICP reactors. Hard BC ansatz, transfer learning across geometries, autograd sensitivity maps. 1700\u00d7 faster than FEM. Built with NVIDIA Modulus + PyTorch."}
{"type": "node", "id": "repo:li-Pingan/fourier-neural-operator", "kind": "repo", "label": "li-Pingan/fourier-neural-operator", "url": "https://github.com/li-Pingan/fourier-neural-operator", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 103, "lang": "", "desc": ""}
{"type": "node", "id": "repo:neuraloperator/Geo-FNO", "kind": "repo", "label": "neuraloperator/Geo-FNO", "url": "https://github.com/neuraloperator/Geo-FNO", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 342, "lang": "Jupyter Notebook", "desc": "Geometry-Aware Fourier Neural Operator (Geo-FNO)"}
{"type": "node", "id": "repo:SciML/FluxNeuralOperators.jl", "kind": "repo", "label": "SciML/FluxNeuralOperators.jl", "url": "https://github.com/SciML/FluxNeuralOperators.jl", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 293, "lang": "Julia", "desc": "DeepONets, (Fourier) Neural Operators, Physics-Informed Neural Operators, and more in Julia"}
{"type": "node", "id": "repo:alasdairtran/fourierflow", "kind": "repo", "label": "alasdairtran/fourierflow", "url": "https://github.com/alasdairtran/fourierflow", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 195, "lang": "Python", "desc": "[ICLR 2023] Factorized Fourier Neural Operators"}
{"type": "node", "id": "repo:erik-norlin/Fourier-Neural-Operator", "kind": "repo", "label": "erik-norlin/Fourier-Neural-Operator", "url": "https://github.com/erik-norlin/Fourier-Neural-Operator", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 55, "lang": "Jupyter Notebook", "desc": "A small research project about advanced machine learning with neural networks. The Fourier neural operator was implemented here to see if it could predict zero-shot super resolution of fluid flows."}
{"type": "node", "id": "repo:SciML/NeuralOperators.jl", "kind": "repo", "label": "SciML/NeuralOperators.jl", "url": "https://github.com/SciML/NeuralOperators.jl", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 38, "lang": "Julia", "desc": "DeepONets, (Fourier) Neural Operators, Physics-Informed Neural Operators, and more in Julia"}
{"type": "node", "id": "repo:lonestar686/AdaptiveFourierNeuralOperator", "kind": "repo", "label": "lonestar686/AdaptiveFourierNeuralOperator", "url": "https://github.com/lonestar686/AdaptiveFourierNeuralOperator", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 30, "lang": "", "desc": ""}
{"type": "node", "id": "repo:gegewen/ufno", "kind": "repo", "label": "gegewen/ufno", "url": "https://github.com/gegewen/ufno", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 178, "lang": "Jupyter Notebook", "desc": "U-FNO - an enhanced Fourier neural operator-based deep-learning model for multiphase flow"}
{"type": "node", "id": "repo:slimgroup/dfno", "kind": "repo", "label": "slimgroup/dfno", "url": "https://github.com/slimgroup/dfno", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 33, "lang": "Python", "desc": "Distributed Fourier Neural Operators"}
{"type": "node", "id": "repo:abelsr/Fourier-Neural-Operator", "kind": "repo", "label": "abelsr/Fourier-Neural-Operator", "url": "https://github.com/abelsr/Fourier-Neural-Operator", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 36, "lang": "Jupyter Notebook", "desc": "Implementation of Fourier Neural Operator using PyTorch"}
{"type": "node", "id": "repo:Hrrsmjd/fourier_neural_operator", "kind": "repo", "label": "Hrrsmjd/fourier_neural_operator", "url": "https://github.com/Hrrsmjd/fourier_neural_operator", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 13, "lang": "Jupyter Notebook", "desc": "Fourier Neural Operator"}
{"type": "node", "id": "repo:bilzinet/pifno", "kind": "repo", "label": "bilzinet/pifno", "url": "https://github.com/bilzinet/pifno", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 31, "lang": "Python", "desc": "Physics Informed Fourier Neural Operator"}
{"type": "node", "id": "repo:ADharaUTEXAS123007/FNO", "kind": "repo", "label": "ADharaUTEXAS123007/FNO", "url": "https://github.com/ADharaUTEXAS123007/FNO", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 17, "lang": "Python", "desc": "Fourier_neural_operator"}
{"type": "node", "id": "repo:camlab-ethz/DSE-for-NeuralOperators", "kind": "repo", "label": "camlab-ethz/DSE-for-NeuralOperators", "url": "https://github.com/camlab-ethz/DSE-for-NeuralOperators", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 24, "lang": "Python", "desc": "Code for \"Beyond Regular Grids: Fourier-Based Neural Operators on Arbitrary Domains\""}
{"type": "node", "id": "repo:matlab-deep-learning/fourier-neural-operator", "kind": "repo", "label": "matlab-deep-learning/fourier-neural-operator", "url": "https://github.com/matlab-deep-learning/fourier-neural-operator", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 21, "lang": "MATLAB", "desc": ""}
{"type": "node", "id": "repo:Duke-MG-Lab/Allen-Cahn-FNO", "kind": "repo", "label": "Duke-MG-Lab/Allen-Cahn-FNO", "url": "https://github.com/Duke-MG-Lab/Allen-Cahn-FNO", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 20, "lang": "Python", "desc": "Fourier Neural Operators to solve for Allen Cahn PDE equations"}
{"type": "node", "id": "repo:slimgroup/FNO4CO2", "kind": "repo", "label": "slimgroup/FNO4CO2", "url": "https://github.com/slimgroup/FNO4CO2", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 24, "lang": "Julia", "desc": "Learned coupled inversion for carbon sequestration monitoring and forecasting with Fourier neural operators"}
{"type": "node", "id": "repo:astanziola/fourier-neural-operator-flax", "kind": "repo", "label": "astanziola/fourier-neural-operator-flax", "url": "https://github.com/astanziola/fourier-neural-operator-flax", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 19, "lang": "Python", "desc": "An unofficial implementation of the Fourier Neural Operator in Flax"}
{"type": "node", "id": "repo:lu-group/fourier-mionet-gcs", "kind": "repo", "label": "lu-group/fourier-mionet-gcs", "url": "https://github.com/lu-group/fourier-mionet-gcs", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 19, "lang": "Python", "desc": "Fourier-MIONet: Fourier-enhanced multiple-input neural operators for multiphase modeling of geological carbon sequestration"}
{"type": "node", "id": "repo:CUBELeonwang/FNO-3DUM", "kind": "repo", "label": "CUBELeonwang/FNO-3DUM", "url": "https://github.com/CUBELeonwang/FNO-3DUM", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 24, "lang": "Python", "desc": "Fourier neural operator for real-time simulation of 3D dynamic urban microclimate"}
{"type": "node", "id": "repo:prateekbhustali/Physics-Informed-Neural-Networks", "kind": "repo", "label": "prateekbhustali/Physics-Informed-Neural-Networks", "url": "https://github.com/prateekbhustali/Physics-Informed-Neural-Networks", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 774, "lang": "Jupyter Notebook", "desc": "Investigating PINNs"}
{"type": "node", "id": "repo:idrl-lab/PINNpapers", "kind": "repo", "label": "idrl-lab/PINNpapers", "url": "https://github.com/idrl-lab/PINNpapers", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 1515, "lang": "Python", "desc": "Must-read Papers on Physics-Informed Neural Networks."}
{"type": "node", "id": "repo:jayroxis/PINNs", "kind": "repo", "label": "jayroxis/PINNs", "url": "https://github.com/jayroxis/PINNs", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 722, "lang": "Jupyter Notebook", "desc": "PyTorch Implementation of Physics-informed Neural Networks "}
{"type": "node", "id": "repo:mathLab/PINA", "kind": "repo", "label": "mathLab/PINA", "url": "https://github.com/mathLab/PINA", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 772, "lang": "Python", "desc": "Physics-Informed Neural networks for Advanced modeling"}
{"type": "node", "id": "repo:SciML/NeuralPDE.jl", "kind": "repo", "label": "SciML/NeuralPDE.jl", "url": "https://github.com/SciML/NeuralPDE.jl", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 1205, "lang": "Julia", "desc": "Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation"}
{"type": "node", "id": "repo:PML-UCF/pinn", "kind": "repo", "label": "PML-UCF/pinn", "url": "https://github.com/PML-UCF/pinn", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 346, "lang": "Python", "desc": "Physics-informed neural networks package"}
{"type": "node", "id": "repo:rezaakb/pinns-torch", "kind": "repo", "label": "rezaakb/pinns-torch", "url": "https://github.com/rezaakb/pinns-torch", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 922, "lang": "Python", "desc": "PINNs-Torch, Physics-informed Neural Networks (PINNs) implemented in PyTorch."}
{"type": "node", "id": "repo:EhsanGh94/PINN", "kind": "repo", "label": "EhsanGh94/PINN", "url": "https://github.com/EhsanGh94/PINN", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 95, "lang": "Python", "desc": "Physics-Informed Neural Network"}
{"type": "node", "id": "repo:wang-fujin/PINN4SOH", "kind": "repo", "label": "wang-fujin/PINN4SOH", "url": "https://github.com/wang-fujin/PINN4SOH", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 460, "lang": "Python", "desc": "A physics-informed neural network for battery SOH estimation"}
{"type": "node", "id": "repo:gmisy/Physics-Informed-Neural-Networks-for-Power-Systems", "kind": "repo", "label": "gmisy/Physics-Informed-Neural-Networks-for-Power-Systems", "url": "https://github.com/gmisy/Physics-Informed-Neural-Networks-for-Power-Systems", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 104, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:benmoseley/harmonic-oscillator-pinn", "kind": "repo", "label": "benmoseley/harmonic-oscillator-pinn", "url": "https://github.com/benmoseley/harmonic-oscillator-pinn", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 675, "lang": "Jupyter Notebook", "desc": "Code accompanying my blog post: So, what is a physics-informed neural network?"}
{"type": "node", "id": "repo:nanditadoloi/PINN", "kind": "repo", "label": "nanditadoloi/PINN", "url": "https://github.com/nanditadoloi/PINN", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 380, "lang": "Jupyter Notebook", "desc": "Simple PyTorch Implementation of Physics Informed Neural Network (PINN)"}
{"type": "node", "id": "repo:Raocp/PINN-elastodynamics", "kind": "repo", "label": "Raocp/PINN-elastodynamics", "url": "https://github.com/Raocp/PINN-elastodynamics", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 164, "lang": "Python", "desc": "physics-informed neural network for elastodynamics problem"}
{"type": "node", "id": "repo:Raocp/PINN-laminar-flow", "kind": "repo", "label": "Raocp/PINN-laminar-flow", "url": "https://github.com/Raocp/PINN-laminar-flow", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 282, "lang": "Python", "desc": "Physics-informed neural network for solving fluid dynamics problems"}
{"type": "node", "id": "repo:nguyenkhoa0209/pinns_tutorial", "kind": "repo", "label": "nguyenkhoa0209/pinns_tutorial", "url": "https://github.com/nguyenkhoa0209/pinns_tutorial", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 142, "lang": "Jupyter Notebook", "desc": "Tutorials for Physics-Informed Neural Networks"}
{"type": "node", "id": "repo:FilippoMB/Physics-Informed-Neural-Networks-tutorial", "kind": "repo", "label": "FilippoMB/Physics-Informed-Neural-Networks-tutorial", "url": "https://github.com/FilippoMB/Physics-Informed-Neural-Networks-tutorial", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 69, "lang": "Jupyter Notebook", "desc": "Hands-on tutorial for implementing Physics Informed Neural Networks in Pytorch"}
{"type": "node", "id": "repo:Photon-AI-Research/NeuralSolvers", "kind": "repo", "label": "Photon-AI-Research/NeuralSolvers", "url": "https://github.com/Photon-AI-Research/NeuralSolvers", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 172, "lang": "Python", "desc": "Neural network based solvers for partial differential equations and inverse problems :milky_way:. Implementation of physics-informed neural networks in pytorch. "}
{"type": "node", "id": "repo:a1k12/characterizing-pinns-failure-modes", "kind": "repo", "label": "a1k12/characterizing-pinns-failure-modes", "url": "https://github.com/a1k12/characterizing-pinns-failure-modes", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 153, "lang": "Python", "desc": "Characterizing possible failure modes in physics-informed neural networks."}
{"type": "node", "id": "repo:pierremtb/PINNs-TF2.0", "kind": "repo", "label": "pierremtb/PINNs-TF2.0", "url": "https://github.com/pierremtb/PINNs-TF2.0", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 267, "lang": "Mathematica", "desc": "TensorFlow 2.0 implementation of Maziar Raissi's Physics Informed Neural Networks (PINNs)."}
{"type": "node", "id": "repo:okada39/pinn_wave", "kind": "repo", "label": "okada39/pinn_wave", "url": "https://github.com/okada39/pinn_wave", "source": "github", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "stars": 214, "lang": "Python", "desc": "Physics Informed Neural Network (PINN) for the wave equation."}
{"type": "node", "id": "repo:oliverweissl/NeuralDecoderToric3D", "kind": "repo", "label": "oliverweissl/NeuralDecoderToric3D", "url": "https://github.com/oliverweissl/NeuralDecoderToric3D", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 4, "lang": "Python", "desc": "Neural decoders for quantum error correction on the 3D Toric code. Includes implementation of TheEND decoder for 2D toric code corrections."}
{"type": "node", "id": "repo:Olfj/QEC_GNN-RNN", "kind": "repo", "label": "Olfj/QEC_GNN-RNN", "url": "https://github.com/Olfj/QEC_GNN-RNN", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 4, "lang": "Python", "desc": "Simplified code base for thesis \"Sequential Graph-Based Decoding of the Surface Code using a Hybrid Graph and Recurrent Neural Network Model\".  See branch \"Thesis\" for the code of the thesis."}
{"type": "node", "id": "repo:thatemocoder/qec-neural-decoder", "kind": "repo", "label": "thatemocoder/qec-neural-decoder", "url": "https://github.com/thatemocoder/qec-neural-decoder", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 1, "lang": "Jupyter Notebook", "desc": "Neural network decoders for quantum error correction: MLP, LSTM, CNN, GNN, and Transformer vs MWPM on simulated and real IBM hardware surface code circuits."}
{"type": "node", "id": "repo:GrahamYan/QEC-neural-decoder-benchmark", "kind": "repo", "label": "GrahamYan/QEC-neural-decoder-benchmark", "url": "https://github.com/GrahamYan/QEC-neural-decoder-benchmark", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "Source code for ICML26 paper: Rethinking the role of neural decoders in quantum error correction"}
{"type": "node", "id": "repo:sghowell/nano-qec", "kind": "repo", "label": "sghowell/nano-qec", "url": "https://github.com/sghowell/nano-qec", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "Autoresearch inspired neural decoder training using Hermes Agent and Stim"}
{"type": "node", "id": "repo:thisac/qecco", "kind": "repo", "label": "thisac/qecco", "url": "https://github.com/thisac/qecco", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 1, "lang": "Python", "desc": "Encoder/decoder for quantum error correction schemes on Quantum Optical Neural Networks"}
{"type": "node", "id": "repo:roguetrainer/bnn-for-qec-decoder", "kind": "repo", "label": "roguetrainer/bnn-for-qec-decoder", "url": "https://github.com/roguetrainer/bnn-for-qec-decoder", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Jupyter Notebook", "desc": "Bayesian Neural Network for Quantum Error Correction Decoding"}
{"type": "node", "id": "repo:afogelis/ml-qec-decoder", "kind": "repo", "label": "afogelis/ml-qec-decoder", "url": "https://github.com/afogelis/ml-qec-decoder", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "Machine-learning surface-code decoders (random forest, XGBoost, neural network) compared against classical decoders."}
{"type": "node", "id": "repo:Sumitchongder/adaptive-qec-decoder", "kind": "repo", "label": "Sumitchongder/adaptive-qec-decoder", "url": "https://github.com/Sumitchongder/adaptive-qec-decoder", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "Adaptive neural and MWPM decoding framework for latency-constrained surface-code quantum error correction."}
{"type": "node", "id": "repo:adityakhannaadk/Spiking-Neural-Decoders", "kind": "repo", "label": "adityakhannaadk/Spiking-Neural-Decoders", "url": "https://github.com/adityakhannaadk/Spiking-Neural-Decoders", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Jupyter Notebook", "desc": "Spiking Neural Network based QEC decoders. Working a) with Neuroaikit and b) with Snntorch for NIR exportability. "}
{"type": "node", "id": "repo:PrismaticFlame/qec_decoder_transformer", "kind": "repo", "label": "PrismaticFlame/qec_decoder_transformer", "url": "https://github.com/PrismaticFlame/qec_decoder_transformer", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "A quantum error correction decoder with a recurrent, transformer based neural network that works on the surface code."}
{"type": "node", "id": "repo:EnriqueHA/qec_toric", "kind": "repo", "label": "EnriqueHA/qec_toric", "url": "https://github.com/EnriqueHA/qec_toric", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "Experiments with the Toric code: Circuit-level noise simulations and Equivariant Neural Decoder implementation."}
{"type": "node", "id": "repo:ibengtsson/qec_nn_w_mwpm", "kind": "repo", "label": "ibengtsson/qec_nn_w_mwpm", "url": "https://github.com/ibengtsson/qec_nn_w_mwpm", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 1, "lang": "Jupyter Notebook", "desc": "A repository aimed at developing a hybrid decoder using a graph neural network together with MWPM.  "}
{"type": "node", "id": "repo:m2papierz/gnns-qec-decoding", "kind": "repo", "label": "m2papierz/gnns-qec-decoding", "url": "https://github.com/m2papierz/gnns-qec-decoding", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "An end-to-end project on decoding topological quantum error-correcting codes with Graph Neural Networks (GNNs)."}
{"type": "node", "id": "repo:bledden/pathfinder", "kind": "repo", "label": "bledden/pathfinder", "url": "https://github.com/bledden/pathfinder", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "Open-source QEC decoders: Pathfinder \u2014 a direction-aware neural surface-code decoder (real-time-budget Triton kernel) whose multi-seed ensemble lowers logical error below the prior open-source GNN at operational noise rates \u2014 plus a kernel-"}
{"type": "node", "id": "repo:watermarkhu/qsurface", "kind": "repo", "label": "watermarkhu/qsurface", "url": "https://github.com/watermarkhu/qsurface", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 80, "lang": "Python", "desc": "\u2705 Python package for simulation and visualization of quantum error-correction on surface codes. The package provides the ability to inspect the error-correcting code during the decoding process, and tools to benchmark the decoder."}
{"type": "node", "id": "repo:nanleij/The-toric-code", "kind": "repo", "label": "nanleij/The-toric-code", "url": "https://github.com/nanleij/The-toric-code", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 22, "lang": "Python", "desc": "The Toric Code (surface code for quantum error correction) together with the MWPM decoder (need a package) and the union-find decoder programmed in python"}
{"type": "node", "id": "repo:cduck/VLQ", "kind": "repo", "label": "cduck/VLQ", "url": "https://github.com/cduck/VLQ", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 13, "lang": "Julia", "desc": "Simple and fast quantum error correction architecture simulator for the rotated surface code"}
{"type": "node", "id": "repo:multimodalas/fusion-qec-sim", "kind": "repo", "label": "multimodalas/fusion-qec-sim", "url": "https://github.com/multimodalas/fusion-qec-sim", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "Quantum error correction simulation and diagnostics bundle for global education and LMIC labs. Features surface/Steane code integration, syndrome fusion analytics, and automated reproducibility tools."}
{"type": "node", "id": "repo:rasidi3112/Quantum-error-correction-threshold-simulator", "kind": "repo", "label": "rasidi3112/Quantum-error-correction-threshold-simulator", "url": "https://github.com/rasidi3112/Quantum-error-correction-threshold-simulator", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 7, "lang": "Python", "desc": "Fault-tolerant QEC simulator simulating Rotated Surface Code (d=3-11). Implements MWPM decoding, depolarizing/biased noise, and verified threshold analysis with visualizations."}
{"type": "node", "id": "repo:emreyalcin26/SurfaceCodes", "kind": "repo", "label": "emreyalcin26/SurfaceCodes", "url": "https://github.com/emreyalcin26/SurfaceCodes", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 3, "lang": "", "desc": "Surface Codes for Error Correction for Quantum Computing"}
{"type": "node", "id": "repo:seandiscovery/quantum_topology", "kind": "repo", "label": "seandiscovery/quantum_topology", "url": "https://github.com/seandiscovery/quantum_topology", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 5, "lang": "Jupyter Notebook", "desc": "Implementing toric and surface codes for topological quantum error correction"}
{"type": "node", "id": "repo:cobycloud/quantum-error-correction", "kind": "repo", "label": "cobycloud/quantum-error-correction", "url": "https://github.com/cobycloud/quantum-error-correction", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 3, "lang": "Python", "desc": "Surface Code Simulation. Explore and simulate quantum error correction using the surface code. This library provides a simple yet powerful framework to experiment with error detection, correction, and logical qubit operations in the quantum"}
{"type": "node", "id": "repo:qfizik/Surface-Code", "kind": "repo", "label": "qfizik/Surface-Code", "url": "https://github.com/qfizik/Surface-Code", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 2, "lang": "", "desc": "The simulation of Google's quantum error correction code, the surface code. "}
{"type": "node", "id": "repo:hpoqh/Surface_Code", "kind": "repo", "label": "hpoqh/Surface_Code", "url": "https://github.com/hpoqh/Surface_Code", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 1, "lang": "", "desc": "Quantum Error Correction"}
{"type": "node", "id": "repo:aknapen/Pinball", "kind": "repo", "label": "aknapen/Pinball", "url": "https://github.com/aknapen/Pinball", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 7, "lang": "Python", "desc": "Source code for the Pinball predecoder, a cryogenic hardware predecoder for surface code quantum error correction decoding under circuit-level noise."}
{"type": "node", "id": "repo:Alexisdevpro/surfaces_codes_stim", "kind": "repo", "label": "Alexisdevpro/surfaces_codes_stim", "url": "https://github.com/Alexisdevpro/surfaces_codes_stim", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Jupyter Notebook", "desc": "Surfaces Codes - Quantum Error Correction"}
{"type": "node", "id": "repo:btq-ag/QLDPC", "kind": "repo", "label": "btq-ag/QLDPC", "url": "https://github.com/btq-ag/QLDPC", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 2, "lang": "Python", "desc": "Interactive Python toolkit for quantum LDPC error correction: circuit builder, real-time belief propagation simulation, surface code and Tanner graph visualization, with Qiskit integration."}
{"type": "node", "id": "repo:PriyaRana19/quantum-error-correction-surface-code", "kind": "repo", "label": "PriyaRana19/quantum-error-correction-surface-code", "url": "https://github.com/PriyaRana19/quantum-error-correction-surface-code", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "", "desc": "Distance-3 rotated surface code simulator using real IBM QPU noise measurements. Connects to FlexiSCD research on dynamic defects."}
{"type": "node", "id": "repo:shipradsingh/surface-codes-quantum-error-correction", "kind": "repo", "label": "shipradsingh/surface-codes-quantum-error-correction", "url": "https://github.com/shipradsingh/surface-codes-quantum-error-correction", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "", "desc": "A research repository for implementing and benchmarking real-time decoders for Surface Codes in Quantum Error Correction. Includes Stim-based simulations, existing decoder implementations, and development of an enhanced real-time decoder."}
{"type": "node", "id": "repo:Linghua-Zhu/surface-code", "kind": "repo", "label": "Linghua-Zhu/surface-code", "url": "https://github.com/Linghua-Zhu/surface-code", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "A surface code quantum error correction simulator"}
{"type": "node", "id": "repo:glanzz/qec-surface-code", "kind": "repo", "label": "glanzz/qec-surface-code", "url": "https://github.com/glanzz/qec-surface-code", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Jupyter Notebook", "desc": "Quantum Error Correction: Surface Code in Q#"}
{"type": "node", "id": "repo:conition/surface_code", "kind": "repo", "label": "conition/surface_code", "url": "https://github.com/conition/surface_code", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Jupyter Notebook", "desc": "Simulation of Surface Codes for Quantum Error Correction"}
{"type": "node", "id": "repo:natashamp/Quantum-Error-Correction-Decoder", "kind": "repo", "label": "natashamp/Quantum-Error-Correction-Decoder", "url": "https://github.com/natashamp/Quantum-Error-Correction-Decoder", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "Python Surface Code Quantum Error Correction Decoder"}
{"type": "node", "id": "repo:ftahas/Quantum-Computing", "kind": "repo", "label": "ftahas/Quantum-Computing", "url": "https://github.com/ftahas/Quantum-Computing", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 4, "lang": "Jupyter Notebook", "desc": "Jupyter notebooks on quantum algorithms: QFT, Shor's factoring, phase estimation, VQE (H\u2082 & LiH ground states), stabiliser codes, and surface code error correction. Research-level detail, fully runnable with Qiskit 2.x."}
{"type": "node", "id": "repo:overshiki/stim-hs", "kind": "repo", "label": "overshiki/stim-hs", "url": "https://github.com/overshiki/stim-hs", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 2, "lang": "Haskell", "desc": "Haskell bindings for Stim - Google's high-performance stabilizer circuit simulator."}
{"type": "node", "id": "repo:NTrevisani/Quantum_Stimulator", "kind": "repo", "label": "NTrevisani/Quantum_Stimulator", "url": "https://github.com/NTrevisani/Quantum_Stimulator", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "A quantum computer simulator"}
{"type": "node", "id": "repo:DeDuckProject/stim-mcp", "kind": "repo", "label": "DeDuckProject/stim-mcp", "url": "https://github.com/DeDuckProject/stim-mcp", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "An MCP server for Stim - quantum stabilizer circuit simulator."}
{"type": "node", "id": "repo:HABER7789/QuantumFaultSim", "kind": "repo", "label": "HABER7789/QuantumFaultSim", "url": "https://github.com/HABER7789/QuantumFaultSim", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "HPC assisted Surface Code threshold simulator powered by Stim, PyMatching, and Sinter for distributed quantum error correction research."}
{"type": "node", "id": "repo:Pyhroff/qec-lab", "kind": "repo", "label": "Pyhroff/qec-lab", "url": "https://github.com/Pyhroff/qec-lab", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "HTML", "desc": "Rotated surface code quantum error correction simulator: Stim + PyMatching threshold curve, D3 lattice animation, RSA-2048 qubit estimator"}
{"type": "node", "id": "repo:AriaWu34/qec-surface-code-simulation", "kind": "repo", "label": "AriaWu34/qec-surface-code-simulation", "url": "https://github.com/AriaWu34/qec-surface-code-simulation", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "Modular quantum error correction simulator built in Python and Qiskit, featuring repetition codes, planar surface codes, configurable noise models, MWPM decoding, Monte Carlo benchmarking, and ongoing integration of Stim/PyMatching-based de"}
{"type": "node", "id": "repo:yaleqc/qtcodes", "kind": "repo", "label": "yaleqc/qtcodes", "url": "https://github.com/yaleqc/qtcodes", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 99, "lang": "Jupyter Notebook", "desc": "Qiskit Topological Codes"}
{"type": "node", "id": "repo:cbmi-group/FFM-Multi-Decoder-Network", "kind": "repo", "label": "cbmi-group/FFM-Multi-Decoder-Network", "url": "https://github.com/cbmi-group/FFM-Multi-Decoder-Network", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 30, "lang": "Python", "desc": "The official code repository for the ECCV 2024 accepted paper \"Representing Topological Self-Similarity Using Fractal Feature Maps for Accurate Segmentation of Tubular Structures\"."}
{"type": "node", "id": "repo:bcriger/py-qcode", "kind": "repo", "label": "bcriger/py-qcode", "url": "https://github.com/bcriger/py-qcode", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 6, "lang": "C++", "desc": "Decoding topological quantum error-correcting codes in Python"}
{"type": "node", "id": "repo:MikeVasmer/Sweep-Decoder-Boundaries", "kind": "repo", "label": "MikeVasmer/Sweep-Decoder-Boundaries", "url": "https://github.com/MikeVasmer/Sweep-Decoder-Boundaries", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 5, "lang": "C++", "desc": "C++ implementation of the sweep rule decoder for topological quantum codes with boundaries."}
{"type": "node", "id": "repo:ethanlake/message-passing-decoders", "kind": "repo", "label": "ethanlake/message-passing-decoders", "url": "https://github.com/ethanlake/message-passing-decoders", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 2, "lang": "Julia", "desc": "message-passing cellular automaton decoders for topological codes"}
{"type": "node", "id": "repo:relicx99991231/MatrixCode", "kind": "repo", "label": "relicx99991231/MatrixCode", "url": "https://github.com/relicx99991231/MatrixCode", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "JavaScript", "desc": "A pure frontend Base-121 color matrix encoder/decoder, featuring built-in Reed-Solomon ECC and a native JS topological vision parser"}
{"type": "node", "id": "repo:adam-the-hacker/TIPE-Quantum-Resilience", "kind": "repo", "label": "adam-the-hacker/TIPE-Quantum-Resilience", "url": "https://github.com/adam-the-hacker/TIPE-Quantum-Resilience", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Python", "desc": "Resilience of quantum information : Topological study and simulation of decoding of the Toric Code"}
{"type": "node", "id": "repo:OgatiesInstitute/Iron-Skeleton", "kind": "repo", "label": "OgatiesInstitute/Iron-Skeleton", "url": "https://github.com/OgatiesInstitute/Iron-Skeleton", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "Jupyter Notebook", "desc": "Official code & data for THE IRON SKELETON. Decoding the 53,000-point Nikkei via Topological Data Analysis."}
{"type": "node", "id": "repo:lostree99/hyperbolic_decoding", "kind": "repo", "label": "lostree99/hyperbolic_decoding", "url": "https://github.com/lostree99/hyperbolic_decoding", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "", "desc": "This project systematically compares classical (analytic) and machine\u2011learned decoders for finite\u2011rate topological codes under both simplified Pauli noise and realistic circuit\u2011level noise. Results will include thresholds, scaling laws, run"}
{"type": "node", "id": "repo:ericrenone/KITAEV", "kind": "repo", "label": "ericrenone/KITAEV", "url": "https://github.com/ericrenone/KITAEV", "source": "github", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "stars": 0, "lang": "", "desc": "The Surface Code Stabilizer Group as the Topological col(F)/ker(F) of a Logical Qubit, the Below-Threshold \u039b Suppression as the Sherman\u2013Morrison Exponential Decay of the Logical Error Rate, the Real-Time Decoder as the Fisher-Information-Op"}
{"type": "node", "id": "repo:mit-han-lab/llm-awq", "kind": "repo", "label": "mit-han-lab/llm-awq", "url": "https://github.com/mit-han-lab/llm-awq", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 3582, "lang": "Python", "desc": "[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration"}
{"type": "node", "id": "repo:Kubenew/TurboQuant-v3", "kind": "repo", "label": "Kubenew/TurboQuant-v3", "url": "https://github.com/Kubenew/TurboQuant-v3", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 18, "lang": "Python", "desc": "# TurboQuant v3 (INT4 + AWQ + Protected Channels + Low-Rank) This notebook demonstrates a **TurboQuant-like** quantization algorithm: - Group-wise INT4 quantization - Activation-aware scaling (AWQ-style) - Protected FP16 channels - Optional"}
{"type": "node", "id": "repo:liyuan24/nanoquantization", "kind": "repo", "label": "liyuan24/nanoquantization", "url": "https://github.com/liyuan24/nanoquantization", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 5, "lang": "Python", "desc": "A self-contained end-to-end quantization framework that currently supports AWQ (Activation-aware Weight Quantization) and Qwen3 models."}
{"type": "node", "id": "repo:ziyoudeshizi-hub/temporal-code", "kind": "repo", "label": "ziyoudeshizi-hub/temporal-code", "url": "https://github.com/ziyoudeshizi-hub/temporal-code", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "Activation-Aware Ternary Quantization for LLMs"}
{"type": "node", "id": "repo:archanareddy3640/AWQ-LLM-Quantization", "kind": "repo", "label": "archanareddy3640/AWQ-LLM-Quantization", "url": "https://github.com/archanareddy3640/AWQ-LLM-Quantization", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Jupyter Notebook", "desc": "Activation-Aware Weight Quantization for LLMs"}
{"type": "node", "id": "repo:ziyoudeshizi-hub/aemp", "kind": "repo", "label": "ziyoudeshizi-hub/aemp", "url": "https://github.com/ziyoudeshizi-hub/aemp", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "Activation-Aware Ternary Quantization for LLMs"}
{"type": "node", "id": "repo:QuangHPV/mlsys-awq", "kind": "repo", "label": "QuangHPV/mlsys-awq", "url": "https://github.com/QuangHPV/mlsys-awq", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Jupyter Notebook", "desc": "MLSys Project: Activation-aware Weight Quantization"}
{"type": "node", "id": "repo:ziyoudeshizi-hub/aatq", "kind": "repo", "label": "ziyoudeshizi-hub/aatq", "url": "https://github.com/ziyoudeshizi-hub/aatq", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "Activation-Aware Ternary Quantization for LLMs"}
{"type": "node", "id": "repo:Epsom700/RotorQuant", "kind": "repo", "label": "Epsom700/RotorQuant", "url": "https://github.com/Epsom700/RotorQuant", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 2, "lang": "C++", "desc": "Rotation-aware quantization for LLM activations on Apple Silicon, featuring Hadamard transforms, Lloyd-Max quantization, and native PyTorch integration"}
{"type": "node", "id": "repo:isgaoyan/BoundaryQAT", "kind": "repo", "label": "isgaoyan/BoundaryQAT", "url": "https://github.com/isgaoyan/BoundaryQAT", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 1, "lang": "", "desc": " Boundary-Aware Activation Scaling for Quantization-Aware Training of Small-Object Segmentation"}
{"type": "node", "id": "repo:leeroopedia/workflow-mit-han-lab-llm-awq-awq-model-quantization", "kind": "repo", "label": "leeroopedia/workflow-mit-han-lab-llm-awq-awq-model-quantization", "url": "https://github.com/leeroopedia/workflow-mit-han-lab-llm-awq-awq-model-quantization", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "AWQ Model Quantization: Compress LLM weights from FP16 to INT4 using Activation-aware Weight Quantization"}
{"type": "node", "id": "repo:vk032503/test-time-quantization-llm-inference", "kind": "repo", "label": "vk032503/test-time-quantization-llm-inference", "url": "https://github.com/vk032503/test-time-quantization-llm-inference", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 1, "lang": "Python", "desc": "Activation-aware test-time quantization framework to compress and accelerate LLM inference without retraining."}
{"type": "node", "id": "repo:AlessandroVaraldi/approx-activations-lstm", "kind": "repo", "label": "AlessandroVaraldi/approx-activations-lstm", "url": "https://github.com/AlessandroVaraldi/approx-activations-lstm", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "valuate LUT-based sigmoid/tanh approximations in a minimal LSTM classifier, with optional quantization-aware training."}
{"type": "node", "id": "repo:Ange10jk/AWQ-reproduction", "kind": "repo", "label": "Ange10jk/AWQ-reproduction", "url": "https://github.com/Ange10jk/AWQ-reproduction", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "Course project on LLMs quantization for intro2ML ran by NJU-SIST. Reproduction of AWQ activation-aware weight quantization for LLM."}
{"type": "node", "id": "repo:vimarsh244/llm-awq", "kind": "repo", "label": "vimarsh244/llm-awq", "url": "https://github.com/vimarsh244/llm-awq", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "", "desc": "[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration"}
{"type": "node", "id": "repo:jun-hyun-kim/ExtraAWQ", "kind": "repo", "label": "jun-hyun-kim/ExtraAWQ", "url": "https://github.com/jun-hyun-kim/ExtraAWQ", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "LLM Compression : Improved AWQ(Activation-aware Weight Quantization) with extra scaling (2024 Fall graduation project)"}
{"type": "node", "id": "repo:panjd123/llm-awq-reproduction", "kind": "repo", "label": "panjd123/llm-awq-reproduction", "url": "https://github.com/panjd123/llm-awq-reproduction", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 1, "lang": "Python", "desc": "This repository contains the reproduction of the paper \"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration\"."}
{"type": "node", "id": "repo:ananya-mh/MoE-Quantization-Study", "kind": "repo", "label": "ananya-mh/MoE-Quantization-Study", "url": "https://github.com/ananya-mh/MoE-Quantization-Study", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "Activation-aware weight quantization for Mixture-of-Experts models. Profiles per-expert routing frequency in OLMoE-1B-7B and allocates bit precision accordingly \u2014 keeping high-traffic experts at INT8 while pushing rarely-activated experts t"}
{"type": "node", "id": "repo:RiyaJ6/Solar10.7BInferenceOptimizer", "kind": "repo", "label": "RiyaJ6/Solar10.7BInferenceOptimizer", "url": "https://github.com/RiyaJ6/Solar10.7BInferenceOptimizer", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "4 bit Activation aware Weight Quantization (AWQ) pipeline and CI benchmarking tool optimized for Solar 10.7B high throughput serving."}
{"type": "node", "id": "repo:Hayder-H8/AWQ-3bits-on-small-LLMs", "kind": "repo", "label": "Hayder-H8/AWQ-3bits-on-small-LLMs", "url": "https://github.com/Hayder-H8/AWQ-3bits-on-small-LLMs", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Jupyter Notebook", "desc": "This repo tries to implement Activation-aware Weight Quantization for LLM Compression and Acceleration from scratch and apply it on small LLMs and assess performance degradation"}
{"type": "node", "id": "repo:bitsandbytes-foundation/bitsandbytes", "kind": "repo", "label": "bitsandbytes-foundation/bitsandbytes", "url": "https://github.com/bitsandbytes-foundation/bitsandbytes", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 8308, "lang": "Python", "desc": "Accessible large language models via k-bit quantization for PyTorch."}
{"type": "node", "id": "repo:facebookresearch/bitsandbytes", "kind": "repo", "label": "facebookresearch/bitsandbytes", "url": "https://github.com/facebookresearch/bitsandbytes", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 779, "lang": "", "desc": "Library for 8-bit optimizers and quantization routines."}
{"type": "node", "id": "repo:jllllll/bitsandbytes-windows-webui", "kind": "repo", "label": "jllllll/bitsandbytes-windows-webui", "url": "https://github.com/jllllll/bitsandbytes-windows-webui", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 359, "lang": "HTML", "desc": "Windows compile of bitsandbytes for use in text-generation-webui."}
{"type": "node", "id": "repo:comfyanonymous/ComfyUI_bitsandbytes_NF4", "kind": "repo", "label": "comfyanonymous/ComfyUI_bitsandbytes_NF4", "url": "https://github.com/comfyanonymous/ComfyUI_bitsandbytes_NF4", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 424, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:taprosoft/llm_finetuning", "kind": "repo", "label": "taprosoft/llm_finetuning", "url": "https://github.com/taprosoft/llm_finetuning", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 144, "lang": "Python", "desc": "Convenient wrapper for fine-tuning and inference of Large Language Models (LLMs) with several quantization techniques (GTPQ, bitsandbytes)"}
{"type": "node", "id": "repo:broncotc/bitsandbytes-rocm", "kind": "repo", "label": "broncotc/bitsandbytes-rocm", "url": "https://github.com/broncotc/bitsandbytes-rocm", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 36, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:cyan2k/molmo-7b-bnb-4bit", "kind": "repo", "label": "cyan2k/molmo-7b-bnb-4bit", "url": "https://github.com/cyan2k/molmo-7b-bnb-4bit", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 33, "lang": "Python", "desc": "4bit bitsandbytes quants of the best 7B vlms"}
{"type": "node", "id": "repo:DeXtmL/bitsandbytes-win-prebuilt", "kind": "repo", "label": "DeXtmL/bitsandbytes-win-prebuilt", "url": "https://github.com/DeXtmL/bitsandbytes-win-prebuilt", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 75, "lang": "", "desc": ""}
{"type": "node", "id": "repo:mohitmishra786/BitsAndBytes", "kind": "repo", "label": "mohitmishra786/BitsAndBytes", "url": "https://github.com/mohitmishra786/BitsAndBytes", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 78, "lang": "C", "desc": "A comprehensive systems programming toolkit implementing low-level concepts in C, from memory management to OS internals. Features practical implementations of computer architecture concepts with a focus on performance and hardware interact"}
{"type": "node", "id": "repo:james-things/bitsandbytes-prebuilt-all_arch", "kind": "repo", "label": "james-things/bitsandbytes-prebuilt-all_arch", "url": "https://github.com/james-things/bitsandbytes-prebuilt-all_arch", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 40, "lang": "", "desc": "A repository containing prebuilt versions of the bitsandbytes library for Windows"}
{"type": "node", "id": "repo:conda-forge/bitsandbytes-feedstock", "kind": "repo", "label": "conda-forge/bitsandbytes-feedstock", "url": "https://github.com/conda-forge/bitsandbytes-feedstock", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 1, "lang": "Shell", "desc": "A conda-smithy repository for bitsandbytes."}
{"type": "node", "id": "repo:bits-and-bytes-association/bitsandbytesassociation.ca", "kind": "repo", "label": "bits-and-bytes-association/bitsandbytesassociation.ca", "url": "https://github.com/bits-and-bytes-association/bitsandbytesassociation.ca", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 6, "lang": "JavaScript", "desc": "Offical website for the club built with the Next.js framework"}
{"type": "node", "id": "repo:heiko-hotz/sm-bnb-transformers", "kind": "repo", "label": "heiko-hotz/sm-bnb-transformers", "url": "https://github.com/heiko-hotz/sm-bnb-transformers", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 5, "lang": "Jupyter Notebook", "desc": "Transformers with bitsandbytes on SageMaker"}
{"type": "node", "id": "repo:aredden/torch-bnb-fp4", "kind": "repo", "label": "aredden/torch-bnb-fp4", "url": "https://github.com/aredden/torch-bnb-fp4", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 30, "lang": "Python", "desc": "Faster Pytorch bitsandbytes 4bit fp4 nn.Linear ops"}
{"type": "node", "id": "repo:DaoyuanLi2816/can-i-finetune-this", "kind": "repo", "label": "DaoyuanLi2816/can-i-finetune-this", "url": "https://github.com/DaoyuanLi2816/can-i-finetune-this", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 789, "lang": "Python", "desc": "Estimate whether a Hugging Face model fits and fine-tunes on your local GPU."}
{"type": "node", "id": "repo:ZoffixUser4092/bitsandbytes", "kind": "repo", "label": "ZoffixUser4092/bitsandbytes", "url": "https://github.com/ZoffixUser4092/bitsandbytes", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 4, "lang": "Python", "desc": "Fork of BnB for updating Metal and ROCm implementations from."}
{"type": "node", "id": "repo:squeakus/bitsandbytes", "kind": "repo", "label": "squeakus/bitsandbytes", "url": "https://github.com/squeakus/bitsandbytes", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 2, "lang": "C", "desc": "random snippets of code"}
{"type": "node", "id": "repo:dvgodoy/FineTuningLLMs", "kind": "repo", "label": "dvgodoy/FineTuningLLMs", "url": "https://github.com/dvgodoy/FineTuningLLMs", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 846, "lang": "Jupyter Notebook", "desc": "Official repository of my book \"A Hands-On Guide to Fine-Tuning LLMs with PyTorch and Hugging Face\""}
{"type": "node", "id": "repo:subhash307/SpringBoot-BitsAndBytes", "kind": "repo", "label": "subhash307/SpringBoot-BitsAndBytes", "url": "https://github.com/subhash307/SpringBoot-BitsAndBytes", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 8, "lang": "Java", "desc": ""}
{"type": "node", "id": "repo:bitsandbytes-foundation/bitsandbytes-intel", "kind": "repo", "label": "bitsandbytes-foundation/bitsandbytes-intel", "url": "https://github.com/bitsandbytes-foundation/bitsandbytes-intel", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 3, "lang": "Python", "desc": "An extension to enable performance acceleration for bitsandbytes on Intel platforms."}
{"type": "node", "id": "repo:vllm-project/vllm", "kind": "repo", "label": "vllm-project/vllm", "url": "https://github.com/vllm-project/vllm", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 85586, "lang": "Python", "desc": "A high-throughput and memory-efficient inference and serving engine for LLMs"}
{"type": "node", "id": "repo:NVIDIA/TensorRT-LLM", "kind": "repo", "label": "NVIDIA/TensorRT-LLM", "url": "https://github.com/NVIDIA/TensorRT-LLM", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 14061, "lang": "Python", "desc": "TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports high-performing optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create P"}
{"type": "node", "id": "repo:openlake-project/openlake", "kind": "repo", "label": "openlake-project/openlake", "url": "https://github.com/openlake-project/openlake", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 1767, "lang": "Rust", "desc": "OpenLake is a high performance storage engine for efficient LLM inference and GPU Training"}
{"type": "node", "id": "repo:NVIDIA/Star-Attention", "kind": "repo", "label": "NVIDIA/Star-Attention", "url": "https://github.com/NVIDIA/Star-Attention", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 393, "lang": "Python", "desc": "Efficient LLM Inference over Long Sequences"}
{"type": "node", "id": "repo:quic/efficient-transformers", "kind": "repo", "label": "quic/efficient-transformers", "url": "https://github.com/quic/efficient-transformers", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 90, "lang": "Python", "desc": "This library empowers users to smoothly port pretrained models and checkpoints on the HuggingFace (HF) hub (developed using HF transformers library) into inference-ready formats that run efficiently on Qualcomm Cloud AI 100 accelerators."}
{"type": "node", "id": "repo:VectorInstitute/vector-inference", "kind": "repo", "label": "VectorInstitute/vector-inference", "url": "https://github.com/VectorInstitute/vector-inference", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 105, "lang": "Python", "desc": "Efficient LLM inference on Slurm clusters. "}
{"type": "node", "id": "repo:mit-han-lab/Quest", "kind": "repo", "label": "mit-han-lab/Quest", "url": "https://github.com/mit-han-lab/Quest", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 396, "lang": "Cuda", "desc": "[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference"}
{"type": "node", "id": "repo:intel/neural-speed", "kind": "repo", "label": "intel/neural-speed", "url": "https://github.com/intel/neural-speed", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 353, "lang": "C++", "desc": "An innovative library for efficient LLM inference via low-bit quantization"}
{"type": "node", "id": "repo:AlibabaResearch/flash-llm", "kind": "repo", "label": "AlibabaResearch/flash-llm", "url": "https://github.com/AlibabaResearch/flash-llm", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 246, "lang": "Cuda", "desc": "Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity"}
{"type": "node", "id": "repo:usyd-fsalab/fp6_llm", "kind": "repo", "label": "usyd-fsalab/fp6_llm", "url": "https://github.com/usyd-fsalab/fp6_llm", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 282, "lang": "Cuda", "desc": "An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5)."}
{"type": "node", "id": "repo:nobodywho-ooo/nobodywho", "kind": "repo", "label": "nobodywho-ooo/nobodywho", "url": "https://github.com/nobodywho-ooo/nobodywho", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 1019, "lang": "Rust", "desc": "NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.  "}
{"type": "node", "id": "repo:mit-han-lab/duo-attention", "kind": "repo", "label": "mit-han-lab/duo-attention", "url": "https://github.com/mit-han-lab/duo-attention", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 539, "lang": "Python", "desc": "[ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads"}
{"type": "node", "id": "repo:z-lab/paroquant", "kind": "repo", "label": "z-lab/paroquant", "url": "https://github.com/z-lab/paroquant", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 318, "lang": "Python", "desc": "[ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference"}
{"type": "node", "id": "repo:LeanModels/DFloat11", "kind": "repo", "label": "LeanModels/DFloat11", "url": "https://github.com/LeanModels/DFloat11", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 639, "lang": "Python", "desc": "DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference"}
{"type": "node", "id": "repo:wangcx18/llm-vscode-inference-server", "kind": "repo", "label": "wangcx18/llm-vscode-inference-server", "url": "https://github.com/wangcx18/llm-vscode-inference-server", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 59, "lang": "Python", "desc": "An endpoint server for efficiently serving quantized open-source LLMs for code."}
{"type": "node", "id": "repo:NLPOptimize/flash-tokenizer", "kind": "repo", "label": "NLPOptimize/flash-tokenizer", "url": "https://github.com/NLPOptimize/flash-tokenizer", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 461, "lang": "C++", "desc": "EFFICIENT AND OPTIMIZED TOKENIZER ENGINE FOR LLM INFERENCE SERVING"}
{"type": "node", "id": "repo:inferflow/inferflow", "kind": "repo", "label": "inferflow/inferflow", "url": "https://github.com/inferflow/inferflow", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 250, "lang": "C++", "desc": "Inferflow is an efficient and highly configurable inference engine for large language models (LLMs)."}
{"type": "node", "id": "repo:skylight-org/sparse-attention-hub", "kind": "repo", "label": "skylight-org/sparse-attention-hub", "url": "https://github.com/skylight-org/sparse-attention-hub", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 66, "lang": "Python", "desc": "Advancing the frontier of efficient AI"}
{"type": "node", "id": "repo:opengear-project/GEAR", "kind": "repo", "label": "opengear-project/GEAR", "url": "https://github.com/opengear-project/GEAR", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 183, "lang": "Python", "desc": "GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM"}
{"type": "node", "id": "repo:xLLM-AI/xllm-service", "kind": "repo", "label": "xLLM-AI/xllm-service", "url": "https://github.com/xLLM-AI/xllm-service", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 94, "lang": "C++", "desc": "A flexible serving framework that delivers efficient and fault-tolerant LLM inference for clustered deployments."}
{"type": "node", "id": "repo:qwopqwop200/GPTQ-for-LLaMa", "kind": "repo", "label": "qwopqwop200/GPTQ-for-LLaMa", "url": "https://github.com/qwopqwop200/GPTQ-for-LLaMa", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 3071, "lang": "Python", "desc": "4 bits quantization of LLaMA using GPTQ"}
{"type": "node", "id": "repo:AutoGPTQ/AutoGPTQ", "kind": "repo", "label": "AutoGPTQ/AutoGPTQ", "url": "https://github.com/AutoGPTQ/AutoGPTQ", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 5073, "lang": "Python", "desc": "An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm."}
{"type": "node", "id": "repo:IST-DASLab/gptq", "kind": "repo", "label": "IST-DASLab/gptq", "url": "https://github.com/IST-DASLab/gptq", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 2331, "lang": "Python", "desc": "Code for the ICLR 2023 paper \"GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers\"."}
{"type": "node", "id": "repo:ModelCloud/GPTQModel", "kind": "repo", "label": "ModelCloud/GPTQModel", "url": "https://github.com/ModelCloud/GPTQModel", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 1201, "lang": "Python", "desc": "LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang."}
{"type": "node", "id": "repo:Lightning-AI/lit-llama", "kind": "repo", "label": "Lightning-AI/lit-llama", "url": "https://github.com/Lightning-AI/lit-llama", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 6082, "lang": "Python", "desc": "Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed."}
{"type": "node", "id": "repo:intel/neural-compressor", "kind": "repo", "label": "intel/neural-compressor", "url": "https://github.com/intel/neural-compressor", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 2676, "lang": "Python", "desc": "SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; widely-used model compression techniques on PyTorch, TensorFlow, and ONNX Runtime"}
{"type": "node", "id": "repo:IST-DASLab/gptq-gguf-toolkit", "kind": "repo", "label": "IST-DASLab/gptq-gguf-toolkit", "url": "https://github.com/IST-DASLab/gptq-gguf-toolkit", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 64, "lang": "Python", "desc": "Efficient non-uniform quantization with GPTQ for GGUF"}
{"type": "node", "id": "repo:wejoncy/QLLM", "kind": "repo", "label": "wejoncy/QLLM", "url": "https://github.com/wejoncy/QLLM", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 190, "lang": "Python", "desc": "A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily."}
{"type": "node", "id": "repo:taishan1994/LLM-Quantization", "kind": "repo", "label": "taishan1994/LLM-Quantization", "url": "https://github.com/taishan1994/LLM-Quantization", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 77, "lang": "Python", "desc": "\u8bb0\u5f55\u91cf\u5316LLM\u4e2d\u7684\u603b\u7ed3\u3002"}
{"type": "node", "id": "repo:K024/chatglm-q", "kind": "repo", "label": "K024/chatglm-q", "url": "https://github.com/K024/chatglm-q", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 55, "lang": "Python", "desc": "Another ChatGLM2 implementation for GPTQ quantization"}
{"type": "node", "id": "repo:abhinand5/gptq_for_langchain", "kind": "repo", "label": "abhinand5/gptq_for_langchain", "url": "https://github.com/abhinand5/gptq_for_langchain", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 40, "lang": "Jupyter Notebook", "desc": "A guide about how to use GPTQ models with langchain"}
{"type": "node", "id": "repo:davisyoshida/jax-gptq", "kind": "repo", "label": "davisyoshida/jax-gptq", "url": "https://github.com/davisyoshida/jax-gptq", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 10, "lang": "Python", "desc": "JAX implementation of GPTQ quantization algorithm"}
{"type": "node", "id": "repo:xhedit/quantkit", "kind": "repo", "label": "xhedit/quantkit", "url": "https://github.com/xhedit/quantkit", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 78, "lang": "Python", "desc": "cli tool to quantize gguf, gptq, awq, hqq and exl2 models"}
{"type": "node", "id": "repo:inferless/dolphin-2.5-mixtral-8x7b-gptq", "kind": "repo", "label": "inferless/dolphin-2.5-mixtral-8x7b-gptq", "url": "https://github.com/inferless/dolphin-2.5-mixtral-8x7b-gptq", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 7, "lang": "Python", "desc": "A GPTQ\u2011quantized version of Eric Hartford\u2019s Dolphin 2.5 Mixtral 8x7B model, fine\u2011tuned for coding and conversational tasks. <metadata> gpu: A100 | collections: [\"vLLM\",\"GPTQ\"] </metadata>"}
{"type": "node", "id": "repo:IST-DASLab/MatGPTQ", "kind": "repo", "label": "IST-DASLab/MatGPTQ", "url": "https://github.com/IST-DASLab/MatGPTQ", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 22, "lang": "Python", "desc": "Code for MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization"}
{"type": "node", "id": "repo:seonglae/llama2gptq", "kind": "repo", "label": "seonglae/llama2gptq", "url": "https://github.com/seonglae/llama2gptq", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 31, "lang": "Python", "desc": "Chat to LLaMa 2 that also provides responses with reference documents over vector database. Locally available model using GPTQ 4bit quantization."}
{"type": "node", "id": "repo:inferless/mixtral-8x7b-v0.1", "kind": "repo", "label": "inferless/mixtral-8x7b-v0.1", "url": "https://github.com/inferless/mixtral-8x7b-v0.1", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 4, "lang": "Python", "desc": "A GPTQ-quantized variant of the Mixtral 8x7B model, fine-tuned for efficient text generation and conversational applications. <metadata> gpu: A100 | collections: [\"vLLM\",\"GPTQ\"] </metadata>"}
{"type": "node", "id": "repo:EasonGZY/AutoAPTQ", "kind": "repo", "label": "EasonGZY/AutoAPTQ", "url": "https://github.com/EasonGZY/AutoAPTQ", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 14, "lang": "Jupyter Notebook", "desc": "AutoAPTQ: Integrated Quantization Framework (APTQ, GPTQ, AWQ)"}
{"type": "node", "id": "repo:bayjarvis/llm", "kind": "repo", "label": "bayjarvis/llm", "url": "https://github.com/bayjarvis/llm", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 15, "lang": "Python", "desc": "Fine-tuning, DPO, RLHF, RLAIF on LLMs - Qwen3, Zephyr 7B GPTQ with 4-Bit Quantization, Mistral-7B-GPTQ "}
{"type": "node", "id": "repo:IST-DASLab/GPTQ-Babai", "kind": "repo", "label": "IST-DASLab/GPTQ-Babai", "url": "https://github.com/IST-DASLab/GPTQ-Babai", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 9, "lang": "Python", "desc": "Official Repository for \"The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm\" (ICLR 2026)"}
{"type": "node", "id": "repo:horseee/LLM-Pruner", "kind": "repo", "label": "horseee/LLM-Pruner", "url": "https://github.com/horseee/LLM-Pruner", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 1129, "lang": "Python", "desc": "[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA,  BLOOM, Vicuna, Baichuan, TinyLlama, etc."}
{"type": "node", "id": "repo:tianyic/only_train_once_personal_footprint", "kind": "repo", "label": "tianyic/only_train_once_personal_footprint", "url": "https://github.com/tianyic/only_train_once_personal_footprint", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 311, "lang": "Python", "desc": "OTOv1-v3, NeurIPS, ICLR, TMLR, DNN Training, Compression, Structured Pruning, Erasing Operators, CNN, Diffusion, LLM"}
{"type": "node", "id": "repo:openvinotoolkit/nncf", "kind": "repo", "label": "openvinotoolkit/nncf", "url": "https://github.com/openvinotoolkit/nncf", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 1179, "lang": "Python", "desc": "Neural Network Compression Framework for enhanced OpenVINO\u2122 inference"}
{"type": "node", "id": "repo:MAC-AutoML/MindPipe", "kind": "repo", "label": "MAC-AutoML/MindPipe", "url": "https://github.com/MAC-AutoML/MindPipe", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 1012, "lang": "Python", "desc": "A powerful model compression framework for LLMs and LVLMs, adapted for NVIDIA GPUs and Huawei Ascend NPUs."}
{"type": "node", "id": "repo:CASIA-LMC-Lab/FLAP", "kind": "repo", "label": "CASIA-LMC-Lab/FLAP", "url": "https://github.com/CASIA-LMC-Lab/FLAP", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 76, "lang": "Python", "desc": "[AAAI 2024] Fluctuation-based Adaptive Structured Pruning for Large Language Models"}
{"type": "node", "id": "repo:microsoft/only_train_once", "kind": "repo", "label": "microsoft/only_train_once", "url": "https://github.com/microsoft/only_train_once", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 51, "lang": "Python", "desc": "OTOv1-v3, NeurIPS, ICLR, TMLR, DNN Training, Compression, Structured Pruning, Erasing Operators, CNN, Diffusion, LLM"}
{"type": "node", "id": "repo:SamsungSAILMontreal/ream", "kind": "repo", "label": "SamsungSAILMontreal/ream", "url": "https://github.com/SamsungSAILMontreal/ream", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 20, "lang": "Python", "desc": "REAM: Merging Improves Pruning of Experts in LLMs"}
{"type": "node", "id": "repo:MAC-AutoML/Awesome-Efficient-Large-Models", "kind": "repo", "label": "MAC-AutoML/Awesome-Efficient-Large-Models", "url": "https://github.com/MAC-AutoML/Awesome-Efficient-Large-Models", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 16, "lang": "", "desc": "A list of awesome papers on compression and acceleration of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs)."}
{"type": "node", "id": "repo:bupt-ai-club/llm-compression-papers", "kind": "repo", "label": "bupt-ai-club/llm-compression-papers", "url": "https://github.com/bupt-ai-club/llm-compression-papers", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 13, "lang": "", "desc": "papers of llm compression "}
{"type": "node", "id": "repo:daniel-eai/LoRP-Locality-Aware-Redundancy-Pruning", "kind": "repo", "label": "daniel-eai/LoRP-Locality-Aware-Redundancy-Pruning", "url": "https://github.com/daniel-eai/LoRP-Locality-Aware-Redundancy-Pruning", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 3, "lang": "Python", "desc": "LoRP-Locality-Aware Redundancy Pruning for LLM Depth Compression"}
{"type": "node", "id": "repo:yaya-sy/lillama", "kind": "repo", "label": "yaya-sy/lillama", "url": "https://github.com/yaya-sy/lillama", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 11, "lang": "Python", "desc": "[NAACL' 25 main] Lillama: Large Language Model Compression via Low-Rank Feature Distillation"}
{"type": "node", "id": "repo:MyPrototypeWhat/context-chef", "kind": "repo", "label": "MyPrototypeWhat/context-chef", "url": "https://github.com/MyPrototypeWhat/context-chef", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 23, "lang": "TypeScript", "desc": "Context compiler for TypeScript/JavaScript AI agents. Automatically compiles agent state into optimized LLM payloads with history compression, tool pruning, multi-provider support, and more."}
{"type": "node", "id": "repo:gaosh/ToMoE", "kind": "repo", "label": "gaosh/ToMoE", "url": "https://github.com/gaosh/ToMoE", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 11, "lang": "Python", "desc": "[TMLR] Offical Implementation of ToMoE: ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning"}
{"type": "node", "id": "repo:upunaprosk/Awesome-LLM-Compression-Safety", "kind": "repo", "label": "upunaprosk/Awesome-LLM-Compression-Safety", "url": "https://github.com/upunaprosk/Awesome-LLM-Compression-Safety", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 3, "lang": "", "desc": "A curated collection of papers and resources on the safety impacts of model compression in Large Language Models (LLMs), highlighting key challenges, risks, and recent advances."}
{"type": "node", "id": "repo:cbacary/MoDeGPT", "kind": "repo", "label": "cbacary/MoDeGPT", "url": "https://github.com/cbacary/MoDeGPT", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 7, "lang": "Python", "desc": "An implementation of the MoDeGPT LLM compression from the ICLR 2025 Conference paper: Modular Decomposition For Large Language Model Compression."}
{"type": "node", "id": "repo:transcendencelabs/gateframe-context-manager", "kind": "repo", "label": "transcendencelabs/gateframe-context-manager", "url": "https://github.com/transcendencelabs/gateframe-context-manager", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 4, "lang": "TypeScript", "desc": "Gateframe Context Manager \u2014 OpenCode plugin for layered context management: model-driven compression, supersede pruning, lossless SQLite recall archive, and an emergency compaction governor with auto-resume. Fork of opencode-dcp (AGPL-3.0)."}
{"type": "node", "id": "repo:moxin-org/CC-MoE", "kind": "repo", "label": "moxin-org/CC-MoE", "url": "https://github.com/moxin-org/CC-MoE", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 5, "lang": "Python", "desc": "Collaborative Compression for Large-Scale MoE Deployment on Edge"}
{"type": "node", "id": "repo:railus2/Semantic-Pruning-Pipeline-for-LLM-Compression", "kind": "repo", "label": "railus2/Semantic-Pruning-Pipeline-for-LLM-Compression", "url": "https://github.com/railus2/Semantic-Pruning-Pipeline-for-LLM-Compression", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Jupyter Notebook", "desc": ""}
{"type": "node", "id": "repo:psunlpgroup/Compression-Effects", "kind": "repo", "label": "psunlpgroup/Compression-Effects", "url": "https://github.com/psunlpgroup/Compression-Effects", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 2, "lang": "Python", "desc": "[ICLR2026] When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models. Support interpretation of Qwen, Llama, etc."}
{"type": "node", "id": "repo:RWKV/rwkv.cpp", "kind": "repo", "label": "RWKV/rwkv.cpp", "url": "https://github.com/RWKV/rwkv.cpp", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 1574, "lang": "C++", "desc": "INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model"}
{"type": "node", "id": "repo:intel/ipex-llm-tutorial", "kind": "repo", "label": "intel/ipex-llm-tutorial", "url": "https://github.com/intel/ipex-llm-tutorial", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 171, "lang": "Jupyter Notebook", "desc": "Accelerate LLM with low-bit (FP4 / INT4 / FP8 / INT8) optimizations using ipex-llm"}
{"type": "node", "id": "repo:Mininglamp-AI/cider", "kind": "repo", "label": "Mininglamp-AI/cider", "url": "https://github.com/Mininglamp-AI/cider", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 333, "lang": "Python", "desc": "W8A8/W4A8 inference + optimized SDPA on Apple Silicon \u2014 unlocking unused INT8 TensorOps in M5 for 1.2\u20131.9\u00d7 faster LLM prefill, plus FlashInfer-inspired GQA decode attention for up to 1.6\u00d7 SDPA speedup, built as MLX custom primitives."}
{"type": "node", "id": "repo:bassrehab/triton-kernels", "kind": "repo", "label": "bassrehab/triton-kernels", "url": "https://github.com/bassrehab/triton-kernels", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 30, "lang": "Python", "desc": "High-performance GPU kernels for LLM inference in OpenAI Triton. Fused RMSNorm, SwiGLU, INT8 GEMM with benchmarks and roofline analysis."}
{"type": "node", "id": "repo:xigh/herbert-rs", "kind": "repo", "label": "xigh/herbert-rs", "url": "https://github.com/xigh/herbert-rs", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 31, "lang": "Rust", "desc": "Local LLM inference engine written from scratch in Rust \u2014 hand-written AVX-512 assembly kernels, Metal & Vulkan compute shaders. Supports Qwen3, Mistral3, ... Q4/INT8/BF16 quantization."}
{"type": "node", "id": "repo:dasdristanta13/LLM-Lora-PEFT_accumulate", "kind": "repo", "label": "dasdristanta13/LLM-Lora-PEFT_accumulate", "url": "https://github.com/dasdristanta13/LLM-Lora-PEFT_accumulate", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 6, "lang": "Jupyter Notebook", "desc": "LLM-Lora-PEFT_accumulate explores optimizations for Large Language Models (LLMs) using PEFT, LORA, and QLORA. Contribute experiments and implementations to enhance LLM efficiency. Join discussions and push the boundaries of LLM optimization"}
{"type": "node", "id": "repo:jiaoch/Triton-INT8", "kind": "repo", "label": "jiaoch/Triton-INT8", "url": "https://github.com/jiaoch/Triton-INT8", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "LLM   INT8-Quant"}
{"type": "node", "id": "repo:NguyenThaiVu/llm_int8_quant", "kind": "repo", "label": "NguyenThaiVu/llm_int8_quant", "url": "https://github.com/NguyenThaiVu/llm_int8_quant", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "HTML", "desc": ""}
{"type": "node", "id": "repo:jinho-choi123/LLM.int8-quantization-experiment", "kind": "repo", "label": "jinho-choi123/LLM.int8-quantization-experiment", "url": "https://github.com/jinho-choi123/LLM.int8-quantization-experiment", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": "Reproducing https://arxiv.org/pdf/2208.07339"}
{"type": "node", "id": "repo:Ne-minus/nlp-llm_int8-proj", "kind": "repo", "label": "Ne-minus/nlp-llm_int8-proj", "url": "https://github.com/Ne-minus/nlp-llm_int8-proj", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:ankitgmishra/int8", "kind": "repo", "label": "ankitgmishra/int8", "url": "https://github.com/ankitgmishra/int8", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Jupyter Notebook", "desc": "LLM.int8() from First Principles. Most people understand that large language models have billions of parameters, but don't know exactly how we compress them to run on normal GPUs without destroying their intelligence."}
{"type": "node", "id": "repo:Aswathy-K/llm-quantization-benchmark", "kind": "repo", "label": "Aswathy-K/llm-quantization-benchmark", "url": "https://github.com/Aswathy-K/llm-quantization-benchmark", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Jupyter Notebook", "desc": "Benchmarking INT8 and INT4 quantization methods"}
{"type": "node", "id": "repo:CuongNgyn2005/LLM_GEMMA3-1B-INT8", "kind": "repo", "label": "CuongNgyn2005/LLM_GEMMA3-1B-INT8", "url": "https://github.com/CuongNgyn2005/LLM_GEMMA3-1B-INT8", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Verilog", "desc": ""}
{"type": "node", "id": "repo:2404589803/LowMemoryLLM", "kind": "repo", "label": "2404589803/LowMemoryLLM", "url": "https://github.com/2404589803/LowMemoryLLM", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 4, "lang": "C", "desc": "\ud83d\ude80 LowMemoryLLM is A lightweight C-based LLM inference engine optimized for memory-constrained environments.  \u2728 Features: - \ud83d\udcca Multiple quantization (INT8/4/2) - \ud83d\udcbe Smart memory management - \ud83d\udd04 Efficient KV-cache  Built for edge devices and sys"}
{"type": "node", "id": "repo:shyamsridhar123/Quantization", "kind": "repo", "label": "shyamsridhar123/Quantization", "url": "https://github.com/shyamsridhar123/Quantization", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 3, "lang": "Python", "desc": "Model quantization techniques for efficient LLM inference. Experiments with INT8, INT4, and mixed-precision quantization."}
{"type": "node", "id": "repo:moneyally/yua-t16", "kind": "repo", "label": "moneyally/yua-t16", "url": "https://github.com/moneyally/yua-t16", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 2, "lang": "Python", "desc": "INT8 16x16 GEMM tile accelerator for LLM FFN inference (FPGA \u2192 MPW ready)."}
{"type": "node", "id": "repo:fei121/qwen3-8b-quant", "kind": "repo", "label": "fei121/qwen3-8b-quant", "url": "https://github.com/fei121/qwen3-8b-quant", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 2, "lang": "Python", "desc": "Qwen3-8B quantization study across vLLM, TensorRT-LLM, AutoRound, INT8, and MXFP4"}
{"type": "node", "id": "repo:saadtariq001s/custom-INT8-quantizer", "kind": "repo", "label": "saadtariq001s/custom-INT8-quantizer", "url": "https://github.com/saadtariq001s/custom-INT8-quantizer", "source": "github", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "stars": 0, "lang": "Jupyter Notebook", "desc": "Make your own 8-bit linear quantizer that can quantize any LLM, Vision, Audio model to INT8 precision."}
{"type": "node", "id": "repo:danijar/dreamerv3", "kind": "repo", "label": "danijar/dreamerv3", "url": "https://github.com/danijar/dreamerv3", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 3501, "lang": "Python", "desc": "Mastering Diverse Domains through World Models"}
{"type": "node", "id": "repo:danijar/dreamerv2", "kind": "repo", "label": "danijar/dreamerv2", "url": "https://github.com/danijar/dreamerv2", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 1050, "lang": "Python", "desc": "Mastering Atari with Discrete World Models"}
{"type": "node", "id": "repo:nicklashansen/dreamer4", "kind": "repo", "label": "nicklashansen/dreamer4", "url": "https://github.com/nicklashansen/dreamer4", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 348, "lang": "Python", "desc": "Unofficial implementation of the Dreamer 4 world model in PyTorch."}
{"type": "node", "id": "repo:ucd-dare/CarDreamer", "kind": "repo", "label": "ucd-dare/CarDreamer", "url": "https://github.com/ucd-dare/CarDreamer", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 358, "lang": "Python", "desc": "World Model based Autonomous Driving Platform in CARLA :car:"}
{"type": "node", "id": "repo:JeffWang987/DriveDreamer", "kind": "repo", "label": "JeffWang987/DriveDreamer", "url": "https://github.com/JeffWang987/DriveDreamer", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 581, "lang": "Python", "desc": "[ECCV 2024] DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving"}
{"type": "node", "id": "repo:f1yfisher/DriveDreamer2", "kind": "repo", "label": "f1yfisher/DriveDreamer2", "url": "https://github.com/f1yfisher/DriveDreamer2", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 263, "lang": "Python", "desc": "[AAAI 2025] DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation"}
{"type": "node", "id": "repo:vincent-thevenin/DreamerV2-Pytorch", "kind": "repo", "label": "vincent-thevenin/DreamerV2-Pytorch", "url": "https://github.com/vincent-thevenin/DreamerV2-Pytorch", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 53, "lang": "Python", "desc": "Pytorch implementation of DreamerV2: MASTERING ATARI WITH DISCRETE WORLD MODELS"}
{"type": "node", "id": "repo:JeffWang987/WorldDreamer", "kind": "repo", "label": "JeffWang987/WorldDreamer", "url": "https://github.com/JeffWang987/WorldDreamer", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 206, "lang": "", "desc": "WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens"}
{"type": "node", "id": "repo:PKU-Alignment/SafeDreamer", "kind": "repo", "label": "PKU-Alignment/SafeDreamer", "url": "https://github.com/PKU-Alignment/SafeDreamer", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 105, "lang": "Python", "desc": "ICLR 2024: SafeDreamer: Safe Reinforcement Learning with World Models"}
{"type": "node", "id": "repo:OSU-NLP-Group/WebDreamer", "kind": "repo", "label": "OSU-NLP-Group/WebDreamer", "url": "https://github.com/OSU-NLP-Group/WebDreamer", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 104, "lang": "Python", "desc": "[TMLR'25] \"Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents\""}
{"type": "node", "id": "repo:changchencc/TransDreamer", "kind": "repo", "label": "changchencc/TransDreamer", "url": "https://github.com/changchencc/TransDreamer", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 31, "lang": "Python", "desc": "Code for TRANSDREAMER: REINFORCEMENT LEARNING WITH TRANSFORMER WORLD MODELS"}
{"type": "node", "id": "repo:GigaAI-research/DriveDreamer", "kind": "repo", "label": "GigaAI-research/DriveDreamer", "url": "https://github.com/GigaAI-research/DriveDreamer", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 41, "lang": "Python", "desc": "[ECCV 2024] DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving"}
{"type": "node", "id": "repo:esteveste/dreamerV2-pytorch", "kind": "repo", "label": "esteveste/dreamerV2-pytorch", "url": "https://github.com/esteveste/dreamerV2-pytorch", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 22, "lang": "Python", "desc": "Pytorch implementation of DreamerV2: Mastering Atari with Discrete World Models, based on the original implementation"}
{"type": "node", "id": "repo:youngzhou1999/DriveDreamer-Policy", "kind": "repo", "label": "youngzhou1999/DriveDreamer-Policy", "url": "https://github.com/youngzhou1999/DriveDreamer-Policy", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 52, "lang": "Python", "desc": "DriveDreamer-Policy: A Geometry-Grounded World\u2013Action Model for Unified Generation and Planning"}
{"type": "node", "id": "repo:burchim/DreamerV3-PyTorch", "kind": "repo", "label": "burchim/DreamerV3-PyTorch", "url": "https://github.com/burchim/DreamerV3-PyTorch", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 13, "lang": "Python", "desc": "PyTorch implementation of DreamerV3, Mastering Diverse Domains through World Models."}
{"type": "node", "id": "repo:machines-in-motion/dreamer-v4", "kind": "repo", "label": "machines-in-motion/dreamer-v4", "url": "https://github.com/machines-in-motion/dreamer-v4", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 6, "lang": "Jupyter Notebook", "desc": "Unofficial implementation of the dreamer v4 world model. "}
{"type": "node", "id": "repo:naivoder/dreamerv3", "kind": "repo", "label": "naivoder/dreamerv3", "url": "https://github.com/naivoder/dreamerv3", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 19, "lang": "Python", "desc": "PyTorch implementation of DreamerV3 from \"Mastering Diverse Domains with World Models\""}
{"type": "node", "id": "repo:Cimy-wang/FusDreamer", "kind": "repo", "label": "Cimy-wang/FusDreamer", "url": "https://github.com/Cimy-wang/FusDreamer", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 15, "lang": "Python", "desc": "A label-efficient Remote Sensing World Model for Multimodal Data Fusion. IEEE TGRS 2025."}
{"type": "node", "id": "repo:ParamThakkar123/torchwm", "kind": "repo", "label": "ParamThakkar123/torchwm", "url": "https://github.com/ParamThakkar123/torchwm", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 23, "lang": "Python", "desc": "A modular PyTorch library designed for learning, training, and deploying world models across various environments."}
{"type": "node", "id": "repo:chenghands-on/Dreamer_assemble", "kind": "repo", "label": "chenghands-on/Dreamer_assemble", "url": "https://github.com/chenghands-on/Dreamer_assemble", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 10, "lang": "Python", "desc": "An assemble of various world model including dreamer v2 and v3"}
{"type": "node", "id": "repo:AlmondGod/tinyworlds", "kind": "repo", "label": "AlmondGod/tinyworlds", "url": "https://github.com/AlmondGod/tinyworlds", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 1325, "lang": "Python", "desc": "A minimal implementation of DeepMind's Genie world model"}
{"type": "node", "id": "repo:SkyworkAI/Matrix-Game", "kind": "repo", "label": "SkyworkAI/Matrix-Game", "url": "https://github.com/SkyworkAI/Matrix-Game", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 2248, "lang": "Python", "desc": "Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory"}
{"type": "node", "id": "repo:insait-institute/GenieRedux", "kind": "repo", "label": "insait-institute/GenieRedux", "url": "https://github.com/insait-institute/GenieRedux", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 77, "lang": "Python", "desc": "A framework for training world models with virtual environments, complete with annotated environment dataset (RetroAct), exploration agent (AutoExplore Agent), and GenieRedux-G - an implementation of Genie with enhancements"}
{"type": "node", "id": "repo:Huster-YZY/GenieDrive", "kind": "repo", "label": "Huster-YZY/GenieDrive", "url": "https://github.com/Huster-YZY/GenieDrive", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 100, "lang": "Python", "desc": "[CVPR 2026] \"GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation\""}
{"type": "node", "id": "repo:showlab/Olaf-World", "kind": "repo", "label": "showlab/Olaf-World", "url": "https://github.com/showlab/Olaf-World", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 111, "lang": "Python", "desc": "[ICML 2026] Orienting Latent Actions for Video World Modeling"}
{"type": "node", "id": "repo:imsight-knowhow/genie3-survey", "kind": "repo", "label": "imsight-knowhow/genie3-survey", "url": "https://github.com/imsight-knowhow/genie3-survey", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 15, "lang": "TeX", "desc": "A comprehensive study of related works and research around Google's Genie 3 model - a new frontier for world models"}
{"type": "node", "id": "repo:Pseudo-Lab/hello-world-models", "kind": "repo", "label": "Pseudo-Lab/hello-world-models", "url": "https://github.com/Pseudo-Lab/hello-world-models", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 10, "lang": "HTML", "desc": "Hello, World! \u2014 A structured study repository for World Models papers (Dreamer, MuZero, JEPA, Genie, Cosmos and beyond)."}
{"type": "node", "id": "repo:nomitchell/pytorch-genie-world-model", "kind": "repo", "label": "nomitchell/pytorch-genie-world-model", "url": "https://github.com/nomitchell/pytorch-genie-world-model", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 4, "lang": "Python", "desc": "Pytorch implementation of Genie by deepmind: the coinrun case study at the end of the paper"}
{"type": "node", "id": "repo:danimelatru/Mini-Genie", "kind": "repo", "label": "danimelatru/Mini-Genie", "url": "https://github.com/danimelatru/Mini-Genie", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 7, "lang": "Python", "desc": "Replicating the Genie paper. Generative World Model pipeline for multi-agent SSDs (Sequential Social Dilemmas)"}
{"type": "node", "id": "repo:plugyawn/opengenie", "kind": "repo", "label": "plugyawn/opengenie", "url": "https://github.com/plugyawn/opengenie", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 25, "lang": "Python", "desc": "An open attempt at reproducing a simplified version of Google's Genie World Model API on a single H100."}
{"type": "node", "id": "repo:AmanSwar/genie", "kind": "repo", "label": "AmanSwar/genie", "url": "https://github.com/AmanSwar/genie", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 0, "lang": "Python", "desc": "implementation of Genie world model in Pytorch"}
{"type": "node", "id": "repo:jin-seop-shin/Genie_world_model", "kind": "repo", "label": "jin-seop-shin/Genie_world_model", "url": "https://github.com/jin-seop-shin/Genie_world_model", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 0, "lang": "Python", "desc": ""}
{"type": "node", "id": "repo:Nhatlinh9898/Genie-Forge-World-Model-AI", "kind": "repo", "label": "Nhatlinh9898/Genie-Forge-World-Model-AI", "url": "https://github.com/Nhatlinh9898/Genie-Forge-World-Model-AI", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 0, "lang": "TypeScript", "desc": "kh\u00f4ng ph\u00e2n lo\u1ea1i (t\u1ea1o app game )"}
{"type": "node", "id": "repo:rotem154154/efficient_genie", "kind": "repo", "label": "rotem154154/efficient_genie", "url": "https://github.com/rotem154154/efficient_genie", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 1, "lang": "", "desc": "Efficient world model based on google's Genie"}
{"type": "node", "id": "repo:Nonepf/birds-in-world-models", "kind": "repo", "label": "Nonepf/birds-in-world-models", "url": "https://github.com/Nonepf/birds-in-world-models", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 1, "lang": "Python", "desc": "Reproducing the evolution of World Models (from Ha et al. (2018) to Dreamer, Genie, etc.) from scratch in PyTorch using Flappy Bird."}
{"type": "node", "id": "repo:milasd/nanogenie", "kind": "repo", "label": "milasd/nanogenie", "url": "https://github.com/milasd/nanogenie", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 0, "lang": "Python", "desc": "Small-scale reproduction of the Genie 1 world model architecture reported in paper \"Genie: Generative Interactive Environments\"."}
{"type": "node", "id": "repo:BABI1023/Study-genie", "kind": "repo", "label": "BABI1023/Study-genie", "url": "https://github.com/BABI1023/Study-genie", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 1, "lang": "JavaScript", "desc": "Integrated AI models with real-world tools via API-driven workflows, strengthening skills in backend scalability and platform engineering."}
{"type": "node", "id": "repo:754liam/Genie-Opt", "kind": "repo", "label": "754liam/Genie-Opt", "url": "https://github.com/754liam/Genie-Opt", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 0, "lang": "Python", "desc": "A consumer-hardware-friendly open implementation inspired by Google DeepMind's Genie World Model, covering data collection and VQ-VAE quantization as the foundation for a latent action model."}
{"type": "node", "id": "repo:edisonzhu2006/lucid", "kind": "repo", "label": "edisonzhu2006/lucid", "url": "https://github.com/edisonzhu2006/lucid", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 0, "lang": "Python", "desc": "A playable, learned dream: Genie-style world model trained on raw CoinRun video (no action labels) + a DreamerV3 agent trained entirely inside the dream, evaluated in the real game"}
{"type": "node", "id": "repo:mattqlf/ephemeral-submission", "kind": "repo", "label": "mattqlf/ephemeral-submission", "url": "https://github.com/mattqlf/ephemeral-submission", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 0, "lang": "Python", "desc": "Open source Project Genie. Fine-tuned and served a 1.3b parameter diffusion model, reverse engineered the Suno client to generate background music, and implemented parallel world exploration with websockets + Modal."}
{"type": "node", "id": "repo:facebookresearch/jepa", "kind": "repo", "label": "facebookresearch/jepa", "url": "https://github.com/facebookresearch/jepa", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 4015, "lang": "Python", "desc": "PyTorch code and models for V-JEPA self-supervised learning from video."}
{"type": "node", "id": "repo:gaasher/I-JEPA", "kind": "repo", "label": "gaasher/I-JEPA", "url": "https://github.com/gaasher/I-JEPA", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 290, "lang": "Python", "desc": "Implementation of I-JEPA from \"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture\""}
{"type": "node", "id": "repo:facebookresearch/ijepa", "kind": "repo", "label": "facebookresearch/ijepa", "url": "https://github.com/facebookresearch/ijepa", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 3459, "lang": "Python", "desc": "Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, \"Self-supervised learning from images with a joint-embedding predictive architecture.\""}
{"type": "node", "id": "repo:AbdelStark/awesome-jepa", "kind": "repo", "label": "AbdelStark/awesome-jepa", "url": "https://github.com/AbdelStark/awesome-jepa", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 136, "lang": "CSS", "desc": "Curated resources for JEPA (Joint Embedding Predictive Architecture) world models and self-supervised learning"}
{"type": "node", "id": "repo:Ayumu-J-S/Point-JEPA", "kind": "repo", "label": "Ayumu-J-S/Point-JEPA", "url": "https://github.com/Ayumu-J-S/Point-JEPA", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 47, "lang": "Python", "desc": "[WACV 2025] Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud"}
{"type": "node", "id": "repo:kaland313/CNN-JEPA", "kind": "repo", "label": "kaland313/CNN-JEPA", "url": "https://github.com/kaland313/CNN-JEPA", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 38, "lang": "Jupyter Notebook", "desc": "Official implementation of our paper \"CNN-JEPA: Self-Supervised Pretraining Convolutional Neural Networks Using Joint Embedding Predictive Architecture\""}
{"type": "node", "id": "repo:waterdisappear/SAR-JEPA", "kind": "repo", "label": "waterdisappear/SAR-JEPA", "url": "https://github.com/waterdisappear/SAR-JEPA", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 100, "lang": "Python", "desc": "Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture"}
{"type": "node", "id": "repo:HaoranZhuExplorer/adljepa", "kind": "repo", "label": "HaoranZhuExplorer/adljepa", "url": "https://github.com/HaoranZhuExplorer/adljepa", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 48, "lang": "Python", "desc": "[AAAI 2026] AD-L-JEPA: Self-Supervised Representation Learning with Joint Embedding Predictive Architecture for Automotive LiDAR Object Detection"}
{"type": "node", "id": "repo:jonwiggins/H-JEPA", "kind": "repo", "label": "jonwiggins/H-JEPA", "url": "https://github.com/jonwiggins/H-JEPA", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 23, "lang": "Python", "desc": "PyTorch implementation of Hierarchical Joint-Embedding Predictive Architecture for multi-scale visual self-supervised learning."}
{"type": "node", "id": "repo:LudovicTuncay/Audio-JEPA", "kind": "repo", "label": "LudovicTuncay/Audio-JEPA", "url": "https://github.com/LudovicTuncay/Audio-JEPA", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 63, "lang": "Python", "desc": "Audio-JEPA is an adaptation of the Joint-Embedding Predictive Architecture (JEPA) for self-supervised audio representation learning. Built upon the I-JEPA paradigm, it uses a Vision Transformer (ViT) backbone to predict latent representatio"}
{"type": "node", "id": "repo:theAdamColton/ijepa-enhanced", "kind": "repo", "label": "theAdamColton/ijepa-enhanced", "url": "https://github.com/theAdamColton/ijepa-enhanced", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 14, "lang": "Python", "desc": "recipe for training fully-featured self supervised image jepa models"}
{"type": "node", "id": "repo:filipbasara0/simple-ijepa", "kind": "repo", "label": "filipbasara0/simple-ijepa", "url": "https://github.com/filipbasara0/simple-ijepa", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 5, "lang": "Python", "desc": "A simple and efficient implementation of Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture (I-JEPA)"}
{"type": "node", "id": "repo:jackswl/bim-jepa", "kind": "repo", "label": "jackswl/bim-jepa", "url": "https://github.com/jackswl/bim-jepa", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 4, "lang": "Jupyter Notebook", "desc": "Self-supervised learning for BIM element classification using a joint embedding predictive architecture"}
{"type": "node", "id": "repo:kweimann/ECG-JEPA", "kind": "repo", "label": "kweimann/ECG-JEPA", "url": "https://github.com/kweimann/ECG-JEPA", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 15, "lang": "Python", "desc": "Self-supervised Pre-training of ECG Classifiers with Joint-Embedding Predictive Architecture"}
{"type": "node", "id": "repo:aidelab-iitbombay/RadJEPA", "kind": "repo", "label": "aidelab-iitbombay/RadJEPA", "url": "https://github.com/aidelab-iitbombay/RadJEPA", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 9, "lang": "", "desc": "RadJEPA, a self-supervised frame- work built on a Joint Embedding Predictive Architecture that learns without language supervision. "}
{"type": "node", "id": "repo:helloelora/jepa-point-cloud", "kind": "repo", "label": "helloelora/jepa-point-cloud", "url": "https://github.com/helloelora/jepa-point-cloud", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 10, "lang": "Python", "desc": "Self-supervised 3D point-cloud representations (PointNet + JEPA). 86% linear probe on ModelNet40, no labels"}
{"type": "node", "id": "repo:marypilataki/amt-jepa", "kind": "repo", "label": "marypilataki/amt-jepa", "url": "https://github.com/marypilataki/amt-jepa", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 10, "lang": "Python", "desc": "Source code for \"Self-Supervised Representation Learning with a JEPA Framework for Multi-Instrument Music Transcription\""}
{"type": "node", "id": "repo:VU-AIML/SAT-JEPA-DIFF", "kind": "repo", "label": "VU-AIML/SAT-JEPA-DIFF", "url": "https://github.com/VU-AIML/SAT-JEPA-DIFF", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 11, "lang": "Python", "desc": "[ICLR ML4RS 2026] Official implementation for the paper \"Sat-JEPA-Diff: Bridging Self-Supervised Learning and Generative Diffusion for Remote Sensing\", [IEEE GRSL] Official implementation for the paper \"Sat-JEPA-Diff: Caption-Guided Zero-RG"}
{"type": "node", "id": "repo:driano1221/LeJEPA-TimeSeries", "kind": "repo", "label": "driano1221/LeJEPA-TimeSeries", "url": "https://github.com/driano1221/LeJEPA-TimeSeries", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 3, "lang": "Python", "desc": "Self-Supervised Learning for Time Series Benchmark"}
{"type": "node", "id": "repo:aimagelab/JARVIS", "kind": "repo", "label": "aimagelab/JARVIS", "url": "https://github.com/aimagelab/JARVIS", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 9, "lang": "Python", "desc": "Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models"}
{"type": "node", "id": "repo:tkipf/c-swm", "kind": "repo", "label": "tkipf/c-swm", "url": "https://github.com/tkipf/c-swm", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 398, "lang": "Python", "desc": "Contrastive Learning of Structured World Models"}
{"type": "node", "id": "repo:danijar/daydreamer", "kind": "repo", "label": "danijar/daydreamer", "url": "https://github.com/danijar/daydreamer", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 449, "lang": "Jupyter Notebook", "desc": "DayDreamer: World Models for Physical Robot Learning"}
{"type": "node", "id": "repo:learning-at-home/hivemind", "kind": "repo", "label": "learning-at-home/hivemind", "url": "https://github.com/learning-at-home/hivemind", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 2488, "lang": "Python", "desc": "Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world."}
{"type": "node", "id": "repo:Snowflake-Labs/agent-world-model", "kind": "repo", "label": "Snowflake-Labs/agent-world-model", "url": "https://github.com/Snowflake-Labs/agent-world-model", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 400, "lang": "Python", "desc": "Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning"}
{"type": "node", "id": "repo:UMass-Embodied-AGI/TesserAct", "kind": "repo", "label": "UMass-Embodied-AGI/TesserAct", "url": "https://github.com/UMass-Embodied-AGI/TesserAct", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 401, "lang": "Python", "desc": "ICCV 2025 | TesserAct: Learning 4D Embodied World Models"}
{"type": "node", "id": "repo:eloialonso/diamond", "kind": "repo", "label": "eloialonso/diamond", "url": "https://github.com/eloialonso/diamond", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 2073, "lang": "Python", "desc": "DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight."}
{"type": "node", "id": "repo:leggedrobotics/robotic_world_model", "kind": "repo", "label": "leggedrobotics/robotic_world_model", "url": "https://github.com/leggedrobotics/robotic_world_model", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 655, "lang": "Python", "desc": "Repository for our papers: Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics and Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots"}
{"type": "node", "id": "repo:TencentARC/AnimeSR", "kind": "repo", "label": "TencentARC/AnimeSR", "url": "https://github.com/TencentARC/AnimeSR", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 368, "lang": "Python", "desc": "Codes for \"AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos\""}
{"type": "node", "id": "repo:Little-Podi/AdaWorld", "kind": "repo", "label": "Little-Podi/AdaWorld", "url": "https://github.com/Little-Podi/AdaWorld", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 250, "lang": "Python", "desc": "[ICML'25] The PyTorch implementation of paper: \"AdaWorld: Learning Adaptable World Models with Latent Actions\"."}
{"type": "node", "id": "repo:codingforentrepreneurs/The-Hello-World-of-Machine-Learning", "kind": "repo", "label": "codingforentrepreneurs/The-Hello-World-of-Machine-Learning", "url": "https://github.com/codingforentrepreneurs/The-Hello-World-of-Machine-Learning", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 71, "lang": "Jupyter Notebook", "desc": "Learn to build a basic machine learning model from scratch with this repo and tutorial series."}
{"type": "node", "id": "repo:AIAnytime/Machine-Learning-Models-Implementation", "kind": "repo", "label": "AIAnytime/Machine-Learning-Models-Implementation", "url": "https://github.com/AIAnytime/Machine-Learning-Models-Implementation", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 17, "lang": "Jupyter Notebook", "desc": "Implementation of several ML models on real-world datasets with detailed explanation in notebooks."}
{"type": "node", "id": "repo:jlin816/dynalang", "kind": "repo", "label": "jlin816/dynalang", "url": "https://github.com/jlin816/dynalang", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 418, "lang": "Python", "desc": "Code for \"Learning to Model the World with Language.\" ICML 2024 Oral."}
{"type": "node", "id": "repo:itsmuriuki/FIFA-2018-World-cup-predictions", "kind": "repo", "label": "itsmuriuki/FIFA-2018-World-cup-predictions", "url": "https://github.com/itsmuriuki/FIFA-2018-World-cup-predictions", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 169, "lang": "Jupyter Notebook", "desc": "I used Machine Learning to make a Logistic Regression model using scikit-learn, pandas, numpy, seaborn and matplotlib to predict the results of FIFA 2018 World Cup."}
{"type": "node", "id": "repo:dariopavllo/textured-3d-gan", "kind": "repo", "label": "dariopavllo/textured-3d-gan", "url": "https://github.com/dariopavllo/textured-3d-gan", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 158, "lang": "Python", "desc": "Learning Generative Models of Textured 3D Meshes from Real-World Images, ICCV 2021"}
{"type": "node", "id": "repo:thuml/RLVR-World", "kind": "repo", "label": "thuml/RLVR-World", "url": "https://github.com/thuml/RLVR-World", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 266, "lang": "Python", "desc": "Official repository for \"RLVR-World: Training World Models with Reinforcement Learning\" (NeurIPS 2025), https://arxiv.org/abs/2505.13934"}
{"type": "node", "id": "repo:Tencent-Hunyuan/Hy-Embodied-0.5-VLA", "kind": "repo", "label": "Tencent-Hunyuan/Hy-Embodied-0.5-VLA", "url": "https://github.com/Tencent-Hunyuan/Hy-Embodied-0.5-VLA", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 184, "lang": "Python", "desc": "From Vision-Language-Action Models to a Real-World Robot Learning Stack"}
{"type": "node", "id": "repo:facebookresearch/denoised_mdp", "kind": "repo", "label": "facebookresearch/denoised_mdp", "url": "https://github.com/facebookresearch/denoised_mdp", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 140, "lang": "Python", "desc": "Open source code for paper \"Denoised MDPs: Learning World Models Better Than the World Itself\" "}
{"type": "node", "id": "repo:karthikncode/text-world-player", "kind": "repo", "label": "karthikncode/text-world-player", "url": "https://github.com/karthikncode/text-world-player", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 128, "lang": "Lua", "desc": "Framework and model code for the paper \"Language Understanding for Text-based Games using Deep Reinforcement Learning\", EMNLP 2015 "}
{"type": "node", "id": "repo:maris205/airsim_agent", "kind": "repo", "label": "maris205/airsim_agent", "url": "https://github.com/maris205/airsim_agent", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 100, "lang": "Jupyter Notebook", "desc": "AirSim-based UAV Foundation Model Learning: Covering Agents, VLN, World Models, etc."}
{"type": "node", "id": "repo:imgeorgiev/PWM", "kind": "repo", "label": "imgeorgiev/PWM", "url": "https://github.com/imgeorgiev/PWM", "source": "github", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "stars": 70, "lang": "Jupyter Notebook", "desc": "PWM: Policy Learning with Large World Models"}
{"type": "node", "id": "paper:2402.11651", "kind": "paper", "label": "Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents", "url": "https://arxiv.org/abs/2402.11651", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-02-18"}
{"type": "node", "id": "author:renxi_wang", "kind": "person", "label": "Renxi Wang", "url": "https://arxiv.org/a/renxi_wang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:haonan_li", "kind": "person", "label": "Haonan Li", "url": "https://arxiv.org/a/haonan_li", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:xudong_han", "kind": "person", "label": "Xudong Han", "url": "https://arxiv.org/a/xudong_han", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yixuan_zhang", "kind": "person", "label": "Yixuan Zhang", "url": "https://arxiv.org/a/yixuan_zhang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:timothy_baldwin", "kind": "person", "label": "Timothy Baldwin", "url": "https://arxiv.org/a/timothy_baldwin", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2304.10464", "kind": "paper", "label": "Learning to Plan with Natural Language", "url": "https://arxiv.org/abs/2304.10464", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2023-04-20"}
{"type": "node", "id": "author:yiduo_guo", "kind": "person", "label": "Yiduo Guo", "url": "https://arxiv.org/a/yiduo_guo", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yaobo_liang", "kind": "person", "label": "Yaobo Liang", "url": "https://arxiv.org/a/yaobo_liang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:chenfei_wu", "kind": "person", "label": "Chenfei Wu", "url": "https://arxiv.org/a/chenfei_wu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:wenshan_wu", "kind": "person", "label": "Wenshan Wu", "url": "https://arxiv.org/a/wenshan_wu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:dongyan_zhao", "kind": "person", "label": "Dongyan Zhao", "url": "https://arxiv.org/a/dongyan_zhao", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2605.27825", "kind": "paper", "label": "MRMMIA: Membership Inference Attacks on Memory in Chat Agents", "url": "https://arxiv.org/abs/2605.27825", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2026-05-27"}
{"type": "node", "id": "author:kai_chen", "kind": "person", "label": "Kai Chen", "url": "https://arxiv.org/a/kai_chen", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yan_pang", "kind": "person", "label": "Yan Pang", "url": "https://arxiv.org/a/yan_pang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:tianhao_wang", "kind": "person", "label": "Tianhao Wang", "url": "https://arxiv.org/a/tianhao_wang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2404.19065", "kind": "paper", "label": "HELPER-X: A Unified Instructable Embodied Agent to Tackle Four Interactive Vision-Language Domains with Memory-Augmented Language Models", "url": "https://arxiv.org/abs/2404.19065", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-04-29"}
{"type": "node", "id": "author:gabriel_sarch", "kind": "person", "label": "Gabriel Sarch", "url": "https://arxiv.org/a/gabriel_sarch", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:sahil_somani", "kind": "person", "label": "Sahil Somani", "url": "https://arxiv.org/a/sahil_somani", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:raghav_kapoor", "kind": "person", "label": "Raghav Kapoor", "url": "https://arxiv.org/a/raghav_kapoor", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:michael_j_tarr", "kind": "person", "label": "Michael J. Tarr", "url": "https://arxiv.org/a/michael_j_tarr", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:katerina_fragkiadaki", "kind": "person", "label": "Katerina Fragkiadaki", "url": "https://arxiv.org/a/katerina_fragkiadaki", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2606.24775", "kind": "paper", "label": "Are We Ready For An Agent-Native Memory System?", "url": "https://arxiv.org/abs/2606.24775", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2026-06-23"}
{"type": "node", "id": "author:wei_zhou", "kind": "person", "label": "Wei Zhou", "url": "https://arxiv.org/a/wei_zhou", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:xuanhe_zhou", "kind": "person", "label": "Xuanhe Zhou", "url": "https://arxiv.org/a/xuanhe_zhou", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:shaokun_han", "kind": "person", "label": "Shaokun Han", "url": "https://arxiv.org/a/shaokun_han", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:hongming_xu", "kind": "person", "label": "Hongming Xu", "url": "https://arxiv.org/a/hongming_xu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:guoliang_li", "kind": "person", "label": "Guoliang Li", "url": "https://arxiv.org/a/guoliang_li", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:1503.07220", "kind": "paper", "label": "Individual Planning in Agent Populations: Exploiting Anonymity and Frame-Action Hypergraphs", "url": "https://arxiv.org/abs/1503.07220", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2015-03-24"}
{"type": "node", "id": "author:ekhlas_sonu", "kind": "person", "label": "Ekhlas Sonu", "url": "https://arxiv.org/a/ekhlas_sonu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yingke_chen", "kind": "person", "label": "Yingke Chen", "url": "https://arxiv.org/a/yingke_chen", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:prashant_doshi", "kind": "person", "label": "Prashant Doshi", "url": "https://arxiv.org/a/prashant_doshi", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2408.00764", "kind": "paper", "label": "AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation", "url": "https://arxiv.org/abs/2408.00764", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-08-01"}
{"type": "node", "id": "author:mengkang_hu", "kind": "person", "label": "Mengkang Hu", "url": "https://arxiv.org/a/mengkang_hu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:pu_zhao", "kind": "person", "label": "Pu Zhao", "url": "https://arxiv.org/a/pu_zhao", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:can_xu", "kind": "person", "label": "Can Xu", "url": "https://arxiv.org/a/can_xu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:qingfeng_sun", "kind": "person", "label": "Qingfeng Sun", "url": "https://arxiv.org/a/qingfeng_sun", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:jianguang_lou", "kind": "person", "label": "Jianguang Lou", "url": "https://arxiv.org/a/jianguang_lou", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2310.15127", "kind": "paper", "label": "Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models", "url": "https://arxiv.org/abs/2310.15127", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2023-10-23"}
{"type": "node", "id": "author:yue_wu", "kind": "person", "label": "Yue Wu", "url": "https://arxiv.org/a/yue_wu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2409.02645", "kind": "paper", "label": "Emergent Language: A Survey and Taxonomy", "url": "https://arxiv.org/abs/2409.02645", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-09-04"}
{"type": "node", "id": "author:jannik_peters", "kind": "person", "label": "Jannik Peters", "url": "https://arxiv.org/a/jannik_peters", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:constantin_waubert_de_puiseau", "kind": "person", "label": "Constantin Waubert de Puiseau", "url": "https://arxiv.org/a/constantin_waubert_de_puiseau", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:hasan_tercan", "kind": "person", "label": "Hasan Tercan", "url": "https://arxiv.org/a/hasan_tercan", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:arya_gopikrishnan", "kind": "person", "label": "Arya Gopikrishnan", "url": "https://arxiv.org/a/arya_gopikrishnan", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:gustavo_adolpho_lucas_de_carvalho", "kind": "person", "label": "Gustavo Adolpho Lucas De Carvalho", "url": "https://arxiv.org/a/gustavo_adolpho_lucas_de_carvalho", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2306.07353", "kind": "paper", "label": "HDDL 2.1: Towards Defining a Formalism and a Semantics for Temporal HTN Planning", "url": "https://arxiv.org/abs/2306.07353", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2023-06-12"}
{"type": "node", "id": "author:damien_pellier", "kind": "person", "label": "Damien Pellier", "url": "https://arxiv.org/a/damien_pellier", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:alexandre_albore", "kind": "person", "label": "Alexandre Albore", "url": "https://arxiv.org/a/alexandre_albore", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:humbert_fiorino", "kind": "person", "label": "Humbert Fiorino", "url": "https://arxiv.org/a/humbert_fiorino", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:rafael_bailon_ruiz", "kind": "person", "label": "Rafael Bailon-Ruiz", "url": "https://arxiv.org/a/rafael_bailon_ruiz", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2512.24957", "kind": "paper", "label": "AMAP Agentic Planning Technical Report", "url": "https://arxiv.org/abs/2512.24957", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-12-31"}
{"type": "node", "id": "author:amap_ai_agent_team", "kind": "person", "label": "AMAP AI Agent Team", "url": "https://arxiv.org/a/amap_ai_agent_team", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yulan_hu", "kind": "person", "label": "Yulan Hu", "url": "https://arxiv.org/a/yulan_hu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:xiangwen_zhang", "kind": "person", "label": "Xiangwen Zhang", "url": "https://arxiv.org/a/xiangwen_zhang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:sheng_ouyang", "kind": "person", "label": "Sheng Ouyang", "url": "https://arxiv.org/a/sheng_ouyang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:hao_yi", "kind": "person", "label": "Hao Yi", "url": "https://arxiv.org/a/hao_yi", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2503.21676", "kind": "paper", "label": "How do language models learn facts? Dynamics, curricula and hallucinations", "url": "https://arxiv.org/abs/2503.21676", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-03-27"}
{"type": "node", "id": "author:nicolas_zucchet", "kind": "person", "label": "Nicolas Zucchet", "url": "https://arxiv.org/a/nicolas_zucchet", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:j_rg_bornschein", "kind": "person", "label": "J\u00f6rg Bornschein", "url": "https://arxiv.org/a/j_rg_bornschein", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:stephanie_chan", "kind": "person", "label": "Stephanie Chan", "url": "https://arxiv.org/a/stephanie_chan", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:andrew_lampinen", "kind": "person", "label": "Andrew Lampinen", "url": "https://arxiv.org/a/andrew_lampinen", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:razvan_pascanu", "kind": "person", "label": "Razvan Pascanu", "url": "https://arxiv.org/a/razvan_pascanu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2011.01774", "kind": "paper", "label": "Provenance-Based Assessment of Plans in Context", "url": "https://arxiv.org/abs/2011.01774", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2020-11-03"}
{"type": "node", "id": "author:scott_e_friedman", "kind": "person", "label": "Scott E. Friedman", "url": "https://arxiv.org/a/scott_e_friedman", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:robert_p_goldman", "kind": "person", "label": "Robert P. Goldman", "url": "https://arxiv.org/a/robert_p_goldman", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:richard_g_freedman", "kind": "person", "label": "Richard G. Freedman", "url": "https://arxiv.org/a/richard_g_freedman", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:ugur_kuter", "kind": "person", "label": "Ugur Kuter", "url": "https://arxiv.org/a/ugur_kuter", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:christopher_geib", "kind": "person", "label": "Christopher Geib", "url": "https://arxiv.org/a/christopher_geib", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2603.04428", "kind": "paper", "label": "Agent Memory Below the Prompt: Persistent Q4 KV Cache for Multi-Agent LLM Inference on Edge Devices", "url": "https://arxiv.org/abs/2603.04428", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2026-02-17"}
{"type": "node", "id": "author:yakov_pyotr_shkolnikov", "kind": "person", "label": "Yakov Pyotr Shkolnikov", "url": "https://arxiv.org/a/yakov_pyotr_shkolnikov", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2512.13930", "kind": "paper", "label": "Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Functional Materials Discovery", "url": "https://arxiv.org/abs/2512.13930", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-12-15"}
{"type": "node", "id": "author:samuel_rothfarb", "kind": "person", "label": "Samuel Rothfarb", "url": "https://arxiv.org/a/samuel_rothfarb", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:megan_c_davis", "kind": "person", "label": "Megan C. Davis", "url": "https://arxiv.org/a/megan_c_davis", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:ivana_matanovic", "kind": "person", "label": "Ivana Matanovic", "url": "https://arxiv.org/a/ivana_matanovic", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:baikun_li", "kind": "person", "label": "Baikun Li", "url": "https://arxiv.org/a/baikun_li", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:edward_f_holby", "kind": "person", "label": "Edward F. Holby", "url": "https://arxiv.org/a/edward_f_holby", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2404.01023", "kind": "paper", "label": "Large Language Model Evaluation Via Multi AI Agents: Preliminary results", "url": "https://arxiv.org/abs/2404.01023", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-04-01"}
{"type": "node", "id": "author:zeeshan_rasheed", "kind": "person", "label": "Zeeshan Rasheed", "url": "https://arxiv.org/a/zeeshan_rasheed", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:muhammad_waseem", "kind": "person", "label": "Muhammad Waseem", "url": "https://arxiv.org/a/muhammad_waseem", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:kari_syst", "kind": "person", "label": "Kari Syst\u00e4", "url": "https://arxiv.org/a/kari_syst", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:pekka_abrahamsson", "kind": "person", "label": "Pekka Abrahamsson", "url": "https://arxiv.org/a/pekka_abrahamsson", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2309.02427", "kind": "paper", "label": "Cognitive Architectures for Language Agents", "url": "https://arxiv.org/abs/2309.02427", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2023-09-05"}
{"type": "node", "id": "author:theodore_r_sumers", "kind": "person", "label": "Theodore R. Sumers", "url": "https://arxiv.org/a/theodore_r_sumers", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:shunyu_yao", "kind": "person", "label": "Shunyu Yao", "url": "https://arxiv.org/a/shunyu_yao", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:karthik_narasimhan", "kind": "person", "label": "Karthik Narasimhan", "url": "https://arxiv.org/a/karthik_narasimhan", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:thomas_l_griffiths", "kind": "person", "label": "Thomas L. Griffiths", "url": "https://arxiv.org/a/thomas_l_griffiths", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2312.10793", "kind": "paper", "label": "Demystifying Instruction Mixing for Fine-tuning Large Language Models", "url": "https://arxiv.org/abs/2312.10793", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2023-12-17"}
{"type": "node", "id": "author:minghao_wu", "kind": "person", "label": "Minghao Wu", "url": "https://arxiv.org/a/minghao_wu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yuxia_wang", "kind": "person", "label": "Yuxia Wang", "url": "https://arxiv.org/a/yuxia_wang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2304.12244", "kind": "paper", "label": "WizardLM: Empowering large pre-trained language models to follow complex instructions", "url": "https://arxiv.org/abs/2304.12244", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2023-04-24"}
{"type": "node", "id": "author:kai_zheng", "kind": "person", "label": "Kai Zheng", "url": "https://arxiv.org/a/kai_zheng", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:xiubo_geng", "kind": "person", "label": "Xiubo Geng", "url": "https://arxiv.org/a/xiubo_geng", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2401.16158", "kind": "paper", "label": "Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception", "url": "https://arxiv.org/abs/2401.16158", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-01-29"}
{"type": "node", "id": "author:junyang_wang", "kind": "person", "label": "Junyang Wang", "url": "https://arxiv.org/a/junyang_wang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:haiyang_xu", "kind": "person", "label": "Haiyang Xu", "url": "https://arxiv.org/a/haiyang_xu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:jiabo_ye", "kind": "person", "label": "Jiabo Ye", "url": "https://arxiv.org/a/jiabo_ye", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:ming_yan", "kind": "person", "label": "Ming Yan", "url": "https://arxiv.org/a/ming_yan", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:weizhou_shen", "kind": "person", "label": "Weizhou Shen", "url": "https://arxiv.org/a/weizhou_shen", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2402.04578", "kind": "paper", "label": "S-Agents: Self-organizing Agents in Open-ended Environments", "url": "https://arxiv.org/abs/2402.04578", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-02-07"}
{"type": "node", "id": "author:jiaqi_chen", "kind": "person", "label": "Jiaqi Chen", "url": "https://arxiv.org/a/jiaqi_chen", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yuxian_jiang", "kind": "person", "label": "Yuxian Jiang", "url": "https://arxiv.org/a/yuxian_jiang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:jiachen_lu", "kind": "person", "label": "Jiachen Lu", "url": "https://arxiv.org/a/jiachen_lu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:li_zhang", "kind": "person", "label": "Li Zhang", "url": "https://arxiv.org/a/li_zhang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2310.00034", "kind": "paper", "label": "PB-LLM: Partially Binarized Large Language Models", "url": "https://arxiv.org/abs/2310.00034", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2023-09-29"}
{"type": "node", "id": "author:yuzhang_shang", "kind": "person", "label": "Yuzhang Shang", "url": "https://arxiv.org/a/yuzhang_shang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:zhihang_yuan", "kind": "person", "label": "Zhihang Yuan", "url": "https://arxiv.org/a/zhihang_yuan", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:qiang_wu", "kind": "person", "label": "Qiang Wu", "url": "https://arxiv.org/a/qiang_wu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:zhen_dong", "kind": "person", "label": "Zhen Dong", "url": "https://arxiv.org/a/zhen_dong", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2512.06196", "kind": "paper", "label": "ARCANE: A Multi-Agent Framework for Interpretable and Configurable Alignment", "url": "https://arxiv.org/abs/2512.06196", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-12-05"}
{"type": "node", "id": "author:charlie_masters", "kind": "person", "label": "Charlie Masters", "url": "https://arxiv.org/a/charlie_masters", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:marta_grze_kiewicz", "kind": "person", "label": "Marta Grze\u015bkiewicz", "url": "https://arxiv.org/a/marta_grze_kiewicz", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:stefano_v_albrecht", "kind": "person", "label": "Stefano V. Albrecht", "url": "https://arxiv.org/a/stefano_v_albrecht", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2504.19565", "kind": "paper", "label": "Knowledge-Driven Agentic Scientific Corpus Distillation Framework for Biomedical Large Language Models Training", "url": "https://arxiv.org/abs/2504.19565", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-04-28"}
{"type": "node", "id": "author:meng_xiao", "kind": "person", "label": "Meng Xiao", "url": "https://arxiv.org/a/meng_xiao", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:xunxin_cai", "kind": "person", "label": "Xunxin Cai", "url": "https://arxiv.org/a/xunxin_cai", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:qingqing_long", "kind": "person", "label": "Qingqing Long", "url": "https://arxiv.org/a/qingqing_long", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:chengrui_wang", "kind": "person", "label": "Chengrui Wang", "url": "https://arxiv.org/a/chengrui_wang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yuanchun_zhou", "kind": "person", "label": "Yuanchun Zhou", "url": "https://arxiv.org/a/yuanchun_zhou", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2309.07870", "kind": "paper", "label": "Agents: An Open-source Framework for Autonomous Language Agents", "url": "https://arxiv.org/abs/2309.07870", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2023-09-14"}
{"type": "node", "id": "author:wangchunshu_zhou", "kind": "person", "label": "Wangchunshu Zhou", "url": "https://arxiv.org/a/wangchunshu_zhou", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yuchen_eleanor_jiang", "kind": "person", "label": "Yuchen Eleanor Jiang", "url": "https://arxiv.org/a/yuchen_eleanor_jiang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:long_li", "kind": "person", "label": "Long Li", "url": "https://arxiv.org/a/long_li", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:jialong_wu", "kind": "person", "label": "Jialong Wu", "url": "https://arxiv.org/a/jialong_wu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:tiannan_wang", "kind": "person", "label": "Tiannan Wang", "url": "https://arxiv.org/a/tiannan_wang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2308.16149", "kind": "paper", "label": "Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models", "url": "https://arxiv.org/abs/2308.16149", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2023-08-30"}
{"type": "node", "id": "author:neha_sengupta", "kind": "person", "label": "Neha Sengupta", "url": "https://arxiv.org/a/neha_sengupta", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:sunil_kumar_sahu", "kind": "person", "label": "Sunil Kumar Sahu", "url": "https://arxiv.org/a/sunil_kumar_sahu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:bokang_jia", "kind": "person", "label": "Bokang Jia", "url": "https://arxiv.org/a/bokang_jia", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:satheesh_katipomu", "kind": "person", "label": "Satheesh Katipomu", "url": "https://arxiv.org/a/satheesh_katipomu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2405.19266", "kind": "paper", "label": "PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications", "url": "https://arxiv.org/abs/2405.19266", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-05-29"}
{"type": "node", "id": "author:dingkang_yang", "kind": "person", "label": "Dingkang Yang", "url": "https://arxiv.org/a/dingkang_yang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:jinjie_wei", "kind": "person", "label": "Jinjie Wei", "url": "https://arxiv.org/a/jinjie_wei", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:dongling_xiao", "kind": "person", "label": "Dongling Xiao", "url": "https://arxiv.org/a/dongling_xiao", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:shunli_wang", "kind": "person", "label": "Shunli Wang", "url": "https://arxiv.org/a/shunli_wang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:tong_wu", "kind": "person", "label": "Tong Wu", "url": "https://arxiv.org/a/tong_wu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2203.08975", "kind": "paper", "label": "A Survey of Multi-Agent Deep Reinforcement Learning with Communication", "url": "https://arxiv.org/abs/2203.08975", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2022-03-16"}
{"type": "node", "id": "author:changxi_zhu", "kind": "person", "label": "Changxi Zhu", "url": "https://arxiv.org/a/changxi_zhu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:mehdi_dastani", "kind": "person", "label": "Mehdi Dastani", "url": "https://arxiv.org/a/mehdi_dastani", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:shihan_wang", "kind": "person", "label": "Shihan Wang", "url": "https://arxiv.org/a/shihan_wang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:1311.5108", "kind": "paper", "label": "A Methodology to Engineer and Validate Dynamic Multi-level Multi-agent Based Simulations", "url": "https://arxiv.org/abs/1311.5108", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2013-11-20"}
{"type": "node", "id": "author:jean_baptiste_soyez", "kind": "person", "label": "Jean-Baptiste Soyez", "url": "https://arxiv.org/a/jean_baptiste_soyez", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:gildas_morvan", "kind": "person", "label": "Gildas Morvan", "url": "https://arxiv.org/a/gildas_morvan", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:daniel_dupont", "kind": "person", "label": "Daniel Dupont", "url": "https://arxiv.org/a/daniel_dupont", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:rochdi_merzouki", "kind": "person", "label": "Rochdi Merzouki", "url": "https://arxiv.org/a/rochdi_merzouki", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2508.08322", "kind": "paper", "label": "Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Code", "url": "https://arxiv.org/abs/2508.08322", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-08-09"}
{"type": "node", "id": "author:muhammad_haseeb", "kind": "person", "label": "Muhammad Haseeb", "url": "https://arxiv.org/a/muhammad_haseeb", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2412.06333", "kind": "paper", "label": "Augmenting the action space with conventions to improve multi-agent cooperation in Hanabi", "url": "https://arxiv.org/abs/2412.06333", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-12-09"}
{"type": "node", "id": "author:f_bredell", "kind": "person", "label": "F. Bredell", "url": "https://arxiv.org/a/f_bredell", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:h_a_engelbrecht", "kind": "person", "label": "H. A. Engelbrecht", "url": "https://arxiv.org/a/h_a_engelbrecht", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:j_c_schoeman", "kind": "person", "label": "J. C. Schoeman", "url": "https://arxiv.org/a/j_c_schoeman", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2412.20138", "kind": "paper", "label": "TradingAgents: Multi-Agents LLM Financial Trading Framework", "url": "https://arxiv.org/abs/2412.20138", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-12-28"}
{"type": "node", "id": "author:yijia_xiao", "kind": "person", "label": "Yijia Xiao", "url": "https://arxiv.org/a/yijia_xiao", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:edward_sun", "kind": "person", "label": "Edward Sun", "url": "https://arxiv.org/a/edward_sun", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:di_luo", "kind": "person", "label": "Di Luo", "url": "https://arxiv.org/a/di_luo", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:wei_wang", "kind": "person", "label": "Wei Wang", "url": "https://arxiv.org/a/wei_wang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2401.07324", "kind": "paper", "label": "Small LLMs Are Weak Tool Learners: A Multi-LLM Agent", "url": "https://arxiv.org/abs/2401.07324", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-01-14"}
{"type": "node", "id": "author:chenliang_li", "kind": "person", "label": "Chenliang Li", "url": "https://arxiv.org/a/chenliang_li", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:hongzhan_chen", "kind": "person", "label": "Hongzhan Chen", "url": "https://arxiv.org/a/hongzhan_chen", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:xiaojun_quan", "kind": "person", "label": "Xiaojun Quan", "url": "https://arxiv.org/a/xiaojun_quan", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2506.15656", "kind": "paper", "label": "PhishDebate: An LLM-Based Multi-Agent Framework for Phishing Website Detection", "url": "https://arxiv.org/abs/2506.15656", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-06-18"}
{"type": "node", "id": "author:wenhao_li", "kind": "person", "label": "Wenhao Li", "url": "https://arxiv.org/a/wenhao_li", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:selvakumar_manickam", "kind": "person", "label": "Selvakumar Manickam", "url": "https://arxiv.org/a/selvakumar_manickam", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yung_wey_chong", "kind": "person", "label": "Yung-wey Chong", "url": "https://arxiv.org/a/yung_wey_chong", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:shankar_karuppayah", "kind": "person", "label": "Shankar Karuppayah", "url": "https://arxiv.org/a/shankar_karuppayah", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2510.13343", "kind": "paper", "label": "AOAD-MAT: Transformer-based multi-agent deep reinforcement learning model considering agents' order of action decisions", "url": "https://arxiv.org/abs/2510.13343", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-10-15"}
{"type": "node", "id": "author:shota_takayama", "kind": "person", "label": "Shota Takayama", "url": "https://arxiv.org/a/shota_takayama", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:katsuhide_fujita", "kind": "person", "label": "Katsuhide Fujita", "url": "https://arxiv.org/a/katsuhide_fujita", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2410.12532", "kind": "paper", "label": "MedAide: Information Fusion and Anatomy of Medical Intents via LLM-based Agent Collaboration", "url": "https://arxiv.org/abs/2410.12532", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-10-16"}
{"type": "node", "id": "author:mingcheng_li", "kind": "person", "label": "Mingcheng Li", "url": "https://arxiv.org/a/mingcheng_li", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:jiyao_liu", "kind": "person", "label": "Jiyao Liu", "url": "https://arxiv.org/a/jiyao_liu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:lihao_liu", "kind": "person", "label": "Lihao Liu", "url": "https://arxiv.org/a/lihao_liu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2604.03350", "kind": "paper", "label": "From Model-Based Screening to Data-Driven Surrogates: A Multi-Stage Workflow for Exploring Stochastic Agent-Based Models", "url": "https://arxiv.org/abs/2604.03350", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2026-04-03"}
{"type": "node", "id": "author:paul_saves", "kind": "person", "label": "Paul Saves", "url": "https://arxiv.org/a/paul_saves", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:matthieu_mastio", "kind": "person", "label": "Matthieu Mastio", "url": "https://arxiv.org/a/matthieu_mastio", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:nicolas_verstaevel", "kind": "person", "label": "Nicolas Verstaevel", "url": "https://arxiv.org/a/nicolas_verstaevel", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:benoit_gaudou", "kind": "person", "label": "Benoit Gaudou", "url": "https://arxiv.org/a/benoit_gaudou", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2602.03128", "kind": "paper", "label": "Understanding Multi-Agent LLM Frameworks: A Unified Benchmark and Experimental Analysis", "url": "https://arxiv.org/abs/2602.03128", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2026-02-03"}
{"type": "node", "id": "author:abdelghny_orogat", "kind": "person", "label": "Abdelghny Orogat", "url": "https://arxiv.org/a/abdelghny_orogat", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:ana_rostam", "kind": "person", "label": "Ana Rostam", "url": "https://arxiv.org/a/ana_rostam", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:essam_mansour", "kind": "person", "label": "Essam Mansour", "url": "https://arxiv.org/a/essam_mansour", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2502.07165", "kind": "paper", "label": "Don't Just Demo, Teach Me the Principles: A Principle-Based Multi-Agent Prompting Strategy for Text Classification", "url": "https://arxiv.org/abs/2502.07165", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-02-11"}
{"type": "node", "id": "author:peipei_wei", "kind": "person", "label": "Peipei Wei", "url": "https://arxiv.org/a/peipei_wei", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:dimitris_dimitriadis", "kind": "person", "label": "Dimitris Dimitriadis", "url": "https://arxiv.org/a/dimitris_dimitriadis", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yan_xu", "kind": "person", "label": "Yan Xu", "url": "https://arxiv.org/a/yan_xu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:mingwei_shen", "kind": "person", "label": "Mingwei Shen", "url": "https://arxiv.org/a/mingwei_shen", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2512.03278", "kind": "paper", "label": "Thucy: An LLM-based Multi-Agent System for Claim Verification across Relational Databases", "url": "https://arxiv.org/abs/2512.03278", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-12-02"}
{"type": "node", "id": "author:michael_theologitis", "kind": "person", "label": "Michael Theologitis", "url": "https://arxiv.org/a/michael_theologitis", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:dan_suciu", "kind": "person", "label": "Dan Suciu", "url": "https://arxiv.org/a/dan_suciu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2506.03053", "kind": "paper", "label": "MAEBE: Multi-Agent Emergent Behavior Framework", "url": "https://arxiv.org/abs/2506.03053", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-06-03"}
{"type": "node", "id": "author:sinem_erisken", "kind": "person", "label": "Sinem Erisken", "url": "https://arxiv.org/a/sinem_erisken", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:timothy_gothard", "kind": "person", "label": "Timothy Gothard", "url": "https://arxiv.org/a/timothy_gothard", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:martin_leitgab", "kind": "person", "label": "Martin Leitgab", "url": "https://arxiv.org/a/martin_leitgab", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:ram_potham", "kind": "person", "label": "Ram Potham", "url": "https://arxiv.org/a/ram_potham", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2601.08156", "kind": "paper", "label": "Project Synapse: A Hierarchical Multi-Agent Framework with Hybrid Memory for Autonomous Resolution of Last-Mile Delivery Disruptions", "url": "https://arxiv.org/abs/2601.08156", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2026-01-13"}
{"type": "node", "id": "author:arin_gopalan_yadav", "kind": "person", "label": "Arin Gopalan Yadav", "url": "https://arxiv.org/a/arin_gopalan_yadav", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:varad_dherange", "kind": "person", "label": "Varad Dherange", "url": "https://arxiv.org/a/varad_dherange", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:kumar_shivam", "kind": "person", "label": "Kumar Shivam", "url": "https://arxiv.org/a/kumar_shivam", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2606.20023", "kind": "paper", "label": "When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents", "url": "https://arxiv.org/abs/2606.20023", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2026-06-18"}
{"type": "node", "id": "author:kaiyue_yang", "kind": "person", "label": "Kaiyue Yang", "url": "https://arxiv.org/a/kaiyue_yang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yuyan_bu", "kind": "person", "label": "Yuyan Bu", "url": "https://arxiv.org/a/yuyan_bu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:jingwei_yi", "kind": "person", "label": "Jingwei Yi", "url": "https://arxiv.org/a/jingwei_yi", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yuchi_wang", "kind": "person", "label": "Yuchi Wang", "url": "https://arxiv.org/a/yuchi_wang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:biyu_zhou", "kind": "person", "label": "Biyu Zhou", "url": "https://arxiv.org/a/biyu_zhou", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2504.16021", "kind": "paper", "label": "Navigating the State of Cognitive Flow: Context-Aware AI Interventions for Effective Reasoning Support", "url": "https://arxiv.org/abs/2504.16021", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-04-22"}
{"type": "node", "id": "author:dinithi_dissanayake", "kind": "person", "label": "Dinithi Dissanayake", "url": "https://arxiv.org/a/dinithi_dissanayake", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:suranga_nanayakkara", "kind": "person", "label": "Suranga Nanayakkara", "url": "https://arxiv.org/a/suranga_nanayakkara", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2405.07551", "kind": "paper", "label": "MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning", "url": "https://arxiv.org/abs/2405.07551", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-05-13"}
{"type": "node", "id": "author:shuo_yin", "kind": "person", "label": "Shuo Yin", "url": "https://arxiv.org/a/shuo_yin", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:weihao_you", "kind": "person", "label": "Weihao You", "url": "https://arxiv.org/a/weihao_you", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:zhilong_ji", "kind": "person", "label": "Zhilong Ji", "url": "https://arxiv.org/a/zhilong_ji", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:guoqiang_zhong", "kind": "person", "label": "Guoqiang Zhong", "url": "https://arxiv.org/a/guoqiang_zhong", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:jinfeng_bai", "kind": "person", "label": "Jinfeng Bai", "url": "https://arxiv.org/a/jinfeng_bai", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2111.01762", "kind": "paper", "label": "AIRCC-Clim: a user-friendly tool for generating regional probabilistic climate change scenarios and risk measures", "url": "https://arxiv.org/abs/2111.01762", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2021-10-30"}
{"type": "node", "id": "author:francisco_estrada", "kind": "person", "label": "Francisco Estrada", "url": "https://arxiv.org/a/francisco_estrada", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:oscar_calder_n_bustamante", "kind": "person", "label": "Oscar Calder\u00f3n-Bustamante", "url": "https://arxiv.org/a/oscar_calder_n_bustamante", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:wouter_botzen", "kind": "person", "label": "Wouter Botzen", "url": "https://arxiv.org/a/wouter_botzen", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:juli_n_a_velasco", "kind": "person", "label": "Juli\u00e1n A. Velasco", "url": "https://arxiv.org/a/juli_n_a_velasco", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:richard_s_j_tol", "kind": "person", "label": "Richard S. J. Tol", "url": "https://arxiv.org/a/richard_s_j_tol", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2402.11163", "kind": "paper", "label": "KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph", "url": "https://arxiv.org/abs/2402.11163", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-02-17"}
{"type": "node", "id": "author:jinhao_jiang", "kind": "person", "label": "Jinhao Jiang", "url": "https://arxiv.org/a/jinhao_jiang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:kun_zhou", "kind": "person", "label": "Kun Zhou", "url": "https://arxiv.org/a/kun_zhou", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:wayne_xin_zhao", "kind": "person", "label": "Wayne Xin Zhao", "url": "https://arxiv.org/a/wayne_xin_zhao", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yang_song", "kind": "person", "label": "Yang Song", "url": "https://arxiv.org/a/yang_song", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:chen_zhu", "kind": "person", "label": "Chen Zhu", "url": "https://arxiv.org/a/chen_zhu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2606.30247", "kind": "paper", "label": "Grounding LLM Reasoning under Incomplete Graph Evidence", "url": "https://arxiv.org/abs/2606.30247", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2026-06-29"}
{"type": "node", "id": "author:jiaqi_li", "kind": "person", "label": "Jiaqi Li", "url": "https://arxiv.org/a/jiaqi_li", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:fanghui_song", "kind": "person", "label": "Fanghui Song", "url": "https://arxiv.org/a/fanghui_song", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2409.01907", "kind": "paper", "label": "Focus Agent: LLM-Powered Virtual Focus Group", "url": "https://arxiv.org/abs/2409.01907", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2024-09-03"}
{"type": "node", "id": "author:taiyu_zhang", "kind": "person", "label": "Taiyu Zhang", "url": "https://arxiv.org/a/taiyu_zhang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:xuesong_zhang", "kind": "person", "label": "Xuesong Zhang", "url": "https://arxiv.org/a/xuesong_zhang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:robbe_cools", "kind": "person", "label": "Robbe Cools", "url": "https://arxiv.org/a/robbe_cools", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:adalberto_l_simeone", "kind": "person", "label": "Adalberto L. Simeone", "url": "https://arxiv.org/a/adalberto_l_simeone", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2509.26306", "kind": "paper", "label": "Interactive Learning for LLM Reasoning", "url": "https://arxiv.org/abs/2509.26306", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-09-30"}
{"type": "node", "id": "author:hehai_lin", "kind": "person", "label": "Hehai Lin", "url": "https://arxiv.org/a/hehai_lin", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:shilei_cao", "kind": "person", "label": "Shilei Cao", "url": "https://arxiv.org/a/shilei_cao", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:sudong_wang", "kind": "person", "label": "Sudong Wang", "url": "https://arxiv.org/a/sudong_wang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:haotian_wu", "kind": "person", "label": "Haotian Wu", "url": "https://arxiv.org/a/haotian_wu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:minzhi_li", "kind": "person", "label": "Minzhi Li", "url": "https://arxiv.org/a/minzhi_li", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2512.21309", "kind": "paper", "label": "A Plan Reuse Mechanism for LLM-Driven Agent", "url": "https://arxiv.org/abs/2512.21309", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-12-24"}
{"type": "node", "id": "author:guopeng_li", "kind": "person", "label": "Guopeng Li", "url": "https://arxiv.org/a/guopeng_li", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:ruiqi_wu", "kind": "person", "label": "Ruiqi Wu", "url": "https://arxiv.org/a/ruiqi_wu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:haisheng_tan", "kind": "person", "label": "Haisheng Tan", "url": "https://arxiv.org/a/haisheng_tan", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2505.03786", "kind": "paper", "label": "When Reasoning Beats Scale: A 1.5B Reasoning Model Outranks 13B LLMs as Discriminator", "url": "https://arxiv.org/abs/2505.03786", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-04-30"}
{"type": "node", "id": "author:md_fahim_anjum", "kind": "person", "label": "Md Fahim Anjum", "url": "https://arxiv.org/a/md_fahim_anjum", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2512.13278", "kind": "paper", "label": "AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning", "url": "https://arxiv.org/abs/2512.13278", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-12-15"}
{"type": "node", "id": "author:jiaru_zou", "kind": "person", "label": "Jiaru Zou", "url": "https://arxiv.org/a/jiaru_zou", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:ling_yang", "kind": "person", "label": "Ling Yang", "url": "https://arxiv.org/a/ling_yang", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yunzhe_qi", "kind": "person", "label": "Yunzhe Qi", "url": "https://arxiv.org/a/yunzhe_qi", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:sirui_chen", "kind": "person", "label": "Sirui Chen", "url": "https://arxiv.org/a/sirui_chen", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:mengting_ai", "kind": "person", "label": "Mengting Ai", "url": "https://arxiv.org/a/mengting_ai", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2606.20515", "kind": "paper", "label": "S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence", "url": "https://arxiv.org/abs/2606.20515", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2026-06-18"}
{"type": "node", "id": "author:yalun_dai", "kind": "person", "label": "Yalun Dai", "url": "https://arxiv.org/a/yalun_dai", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:hao_li", "kind": "person", "label": "Hao Li", "url": "https://arxiv.org/a/hao_li", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:shulin_tian", "kind": "person", "label": "Shulin Tian", "url": "https://arxiv.org/a/shulin_tian", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:runmao_yao", "kind": "person", "label": "Runmao Yao", "url": "https://arxiv.org/a/runmao_yao", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:yuhao_dong", "kind": "person", "label": "Yuhao Dong", "url": "https://arxiv.org/a/yuhao_dong", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2601.10758", "kind": "paper", "label": "Agents at Risk: How Users Unwittingly Undermine LLM Safety", "url": "https://arxiv.org/abs/2601.10758", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2026-01-14"}
{"type": "node", "id": "author:fengchao_chen", "kind": "person", "label": "Fengchao Chen", "url": "https://arxiv.org/a/fengchao_chen", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:tingmin_wu", "kind": "person", "label": "Tingmin Wu", "url": "https://arxiv.org/a/tingmin_wu", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:van_nguyen", "kind": "person", "label": "Van Nguyen", "url": "https://arxiv.org/a/van_nguyen", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:carsten_rudolph", "kind": "person", "label": "Carsten Rudolph", "url": "https://arxiv.org/a/carsten_rudolph", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:2502.09809", "kind": "paper", "label": "AgentGuard: Repurposing Agentic Orchestrator for Safety Evaluation of Tool Orchestration", "url": "https://arxiv.org/abs/2502.09809", "source": "arxiv", "axis": "agents", "layer": 0, "published": "2025-02-13"}
{"type": "node", "id": "author:jizhou_chen", "kind": "person", "label": "Jizhou Chen", "url": "https://arxiv.org/a/jizhou_chen", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "author:samuel_lee_cong", "kind": "person", "label": "Samuel Lee Cong", "url": "https://arxiv.org/a/samuel_lee_cong", "source": "arxiv-author", "axis": "agents", "layer": 0}
{"type": "node", "id": "paper:1812.10968", "kind": "paper", "label": "Car Detection using Unmanned Aerial Vehicles: Comparison between Faster R-CNN and YOLOv3", "url": "https://arxiv.org/abs/1812.10968", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2018-12-28"}
{"type": "node", "id": "author:bilel_benjdira", "kind": "person", "label": "Bilel Benjdira", "url": "https://arxiv.org/a/bilel_benjdira", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:taha_khursheed", "kind": "person", "label": "Taha Khursheed", "url": "https://arxiv.org/a/taha_khursheed", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:anis_koubaa", "kind": "person", "label": "Anis Koubaa", "url": "https://arxiv.org/a/anis_koubaa", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:adel_ammar", "kind": "person", "label": "Adel Ammar", "url": "https://arxiv.org/a/adel_ammar", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:kais_ouni", "kind": "person", "label": "Kais Ouni", "url": "https://arxiv.org/a/kais_ouni", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2510.00995", "kind": "paper", "label": "ROSflight 2.0: Lean ROS 2-Based Autopilot for Unmanned Aerial Vehicles", "url": "https://arxiv.org/abs/2510.00995", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2025-10-01"}
{"type": "node", "id": "author:jacob_moore", "kind": "person", "label": "Jacob Moore", "url": "https://arxiv.org/a/jacob_moore", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:phil_tokumaru", "kind": "person", "label": "Phil Tokumaru", "url": "https://arxiv.org/a/phil_tokumaru", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:ian_reid", "kind": "person", "label": "Ian Reid", "url": "https://arxiv.org/a/ian_reid", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:brandon_sutherland", "kind": "person", "label": "Brandon Sutherland", "url": "https://arxiv.org/a/brandon_sutherland", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:joseph_ritchie", "kind": "person", "label": "Joseph Ritchie", "url": "https://arxiv.org/a/joseph_ritchie", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:1911.06073", "kind": "paper", "label": "Efficient ConvNet-based Object Detection for Unmanned Aerial Vehicles by Selective Tile Processing", "url": "https://arxiv.org/abs/1911.06073", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2019-11-14"}
{"type": "node", "id": "author:george_plastiras", "kind": "person", "label": "George Plastiras", "url": "https://arxiv.org/a/george_plastiras", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:christos_kyrkou", "kind": "person", "label": "Christos Kyrkou", "url": "https://arxiv.org/a/christos_kyrkou", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:theocharis_theocharides", "kind": "person", "label": "Theocharis Theocharides", "url": "https://arxiv.org/a/theocharis_theocharides", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2202.09661", "kind": "paper", "label": "Detection of Stealthy Adversaries for Networked Unmanned Aerial Vehicles*", "url": "https://arxiv.org/abs/2202.09661", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2022-02-19"}
{"type": "node", "id": "author:rayan_bahrami", "kind": "person", "label": "Rayan Bahrami", "url": "https://arxiv.org/a/rayan_bahrami", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:hamidreza_jafarnejadsani", "kind": "person", "label": "Hamidreza Jafarnejadsani", "url": "https://arxiv.org/a/hamidreza_jafarnejadsani", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2009.04234", "kind": "paper", "label": "Optimal Trajectory Planning for Cinematography with Multiple Unmanned Aerial Vehicles", "url": "https://arxiv.org/abs/2009.04234", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2020-09-09"}
{"type": "node", "id": "author:alfonso_alc_ntara", "kind": "person", "label": "Alfonso Alc\u00e1ntara", "url": "https://arxiv.org/a/alfonso_alc_ntara", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:jes_s_capit_n", "kind": "person", "label": "Jes\u00fas Capit\u00e1n", "url": "https://arxiv.org/a/jes_s_capit_n", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:rita_cunha", "kind": "person", "label": "Rita Cunha", "url": "https://arxiv.org/a/rita_cunha", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:an_bal_ollero", "kind": "person", "label": "An\u00edbal Ollero", "url": "https://arxiv.org/a/an_bal_ollero", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2001.06066", "kind": "paper", "label": "Tracking of Micro Unmanned Aerial Vehicles: A Comparative Study", "url": "https://arxiv.org/abs/2001.06066", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2020-01-16"}
{"type": "node", "id": "author:fatih_g_k_e", "kind": "person", "label": "Fatih G\u00f6k\u00e7e", "url": "https://arxiv.org/a/fatih_g_k_e", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:1006.1956", "kind": "paper", "label": "A Semi-distributed Reputation Based Intrusion Detection System for Mobile Adhoc Networks", "url": "https://arxiv.org/abs/1006.1956", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2010-06-10"}
{"type": "node", "id": "author:animesh_kr_trivedi", "kind": "person", "label": "Animesh Kr Trivedi", "url": "https://arxiv.org/a/animesh_kr_trivedi", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:rajan_arora", "kind": "person", "label": "Rajan Arora", "url": "https://arxiv.org/a/rajan_arora", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:rishi_kapoor", "kind": "person", "label": "Rishi Kapoor", "url": "https://arxiv.org/a/rishi_kapoor", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:sudip_sanyal", "kind": "person", "label": "Sudip Sanyal", "url": "https://arxiv.org/a/sudip_sanyal", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:sugata_sanyal", "kind": "person", "label": "Sugata Sanyal", "url": "https://arxiv.org/a/sugata_sanyal", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2009.10492", "kind": "paper", "label": "OpenREALM: Real-time Mapping for Unmanned Aerial Vehicles", "url": "https://arxiv.org/abs/2009.10492", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2020-09-22"}
{"type": "node", "id": "author:alexander_kern", "kind": "person", "label": "Alexander Kern", "url": "https://arxiv.org/a/alexander_kern", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:markus_bobbe", "kind": "person", "label": "Markus Bobbe", "url": "https://arxiv.org/a/markus_bobbe", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:yogesh_khedar", "kind": "person", "label": "Yogesh Khedar", "url": "https://arxiv.org/a/yogesh_khedar", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:ulf_bestmann", "kind": "person", "label": "Ulf Bestmann", "url": "https://arxiv.org/a/ulf_bestmann", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:1805.03358", "kind": "paper", "label": "A Collision-Free Path Planning Algorithm for Unmanned Aerial Vehicle Delivery", "url": "https://arxiv.org/abs/1805.03358", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2018-05-09"}
{"type": "node", "id": "author:ziji_shi", "kind": "person", "label": "Ziji Shi", "url": "https://arxiv.org/a/ziji_shi", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:wee_keong_ng", "kind": "person", "label": "Wee Keong Ng", "url": "https://arxiv.org/a/wee_keong_ng", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2401.06503", "kind": "paper", "label": "Improving the Detection of Small Oriented Objects in Aerial Images", "url": "https://arxiv.org/abs/2401.06503", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2024-01-12"}
{"type": "node", "id": "author:chandler_timm_c_doloriel", "kind": "person", "label": "Chandler Timm C. Doloriel", "url": "https://arxiv.org/a/chandler_timm_c_doloriel", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:rhandley_d_cajote", "kind": "person", "label": "Rhandley D. Cajote", "url": "https://arxiv.org/a/rhandley_d_cajote", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2206.01411", "kind": "paper", "label": "One-shot Learning for Autonomous Aerial Manipulation", "url": "https://arxiv.org/abs/2206.01411", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2022-06-03"}
{"type": "node", "id": "author:claudio_zito", "kind": "person", "label": "Claudio Zito", "url": "https://arxiv.org/a/claudio_zito", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:eliseo_ferrante", "kind": "person", "label": "Eliseo Ferrante", "url": "https://arxiv.org/a/eliseo_ferrante", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:0804.3894", "kind": "paper", "label": "Unmanned Aerial Vehicle Instrumentation for Rapid Aerial Photo System", "url": "https://arxiv.org/abs/0804.3894", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2008-04-24"}
{"type": "node", "id": "author:widyawardana_adiprawita", "kind": "person", "label": "Widyawardana Adiprawita", "url": "https://arxiv.org/a/widyawardana_adiprawita", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:adang_suwandi_ahmad", "kind": "person", "label": "Adang Suwandi Ahmad", "url": "https://arxiv.org/a/adang_suwandi_ahmad", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:jaka_semibiring", "kind": "person", "label": "Jaka Semibiring", "url": "https://arxiv.org/a/jaka_semibiring", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:1807.00435", "kind": "paper", "label": "Intrusion Detection Systems for Networked Unmanned Aerial Vehicles: A Survey", "url": "https://arxiv.org/abs/1807.00435", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2018-07-02"}
{"type": "node", "id": "author:gaurav_choudhary", "kind": "person", "label": "Gaurav Choudhary", "url": "https://arxiv.org/a/gaurav_choudhary", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:vishal_sharma", "kind": "person", "label": "Vishal Sharma", "url": "https://arxiv.org/a/vishal_sharma", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:ilsun_you", "kind": "person", "label": "Ilsun You", "url": "https://arxiv.org/a/ilsun_you", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:kangbin_yim", "kind": "person", "label": "Kangbin Yim", "url": "https://arxiv.org/a/kangbin_yim", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:ing_ray_chen", "kind": "person", "label": "Ing-Ray Chen", "url": "https://arxiv.org/a/ing_ray_chen", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2302.14543", "kind": "paper", "label": "RRT and Velocity Obstacles-based motion planning for Unmanned Aircraft Systems Traffic Management (UTM)", "url": "https://arxiv.org/abs/2302.14543", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2023-02-28"}
{"type": "node", "id": "author:himanshu", "kind": "person", "label": "Himanshu", "url": "https://arxiv.org/a/himanshu", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:jinraj_v_pushpangathan", "kind": "person", "label": "Jinraj V Pushpangathan", "url": "https://arxiv.org/a/jinraj_v_pushpangathan", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:harikumar_kandath", "kind": "person", "label": "Harikumar Kandath", "url": "https://arxiv.org/a/harikumar_kandath", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2112.11219", "kind": "paper", "label": "An Autonomous Self-Incremental Learning Approach for Detection of Cyber Attacks on Unmanned Aerial Vehicles (UAVs)", "url": "https://arxiv.org/abs/2112.11219", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2021-12-18"}
{"type": "node", "id": "author:yasir_ali_farrukh", "kind": "person", "label": "Yasir Ali Farrukh", "url": "https://arxiv.org/a/yasir_ali_farrukh", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:irfan_khan", "kind": "person", "label": "Irfan Khan", "url": "https://arxiv.org/a/irfan_khan", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2306.11113", "kind": "paper", "label": "Learn to Accumulate Evidence from All Training Samples: Theory and Practice", "url": "https://arxiv.org/abs/2306.11113", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2023-06-19"}
{"type": "node", "id": "author:deep_pandey", "kind": "person", "label": "Deep Pandey", "url": "https://arxiv.org/a/deep_pandey", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:qi_yu", "kind": "person", "label": "Qi Yu", "url": "https://arxiv.org/a/qi_yu", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2105.04026", "kind": "paper", "label": "The Modern Mathematics of Deep Learning", "url": "https://arxiv.org/abs/2105.04026", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2021-05-09"}
{"type": "node", "id": "author:julius_berner", "kind": "person", "label": "Julius Berner", "url": "https://arxiv.org/a/julius_berner", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:philipp_grohs", "kind": "person", "label": "Philipp Grohs", "url": "https://arxiv.org/a/philipp_grohs", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:gitta_kutyniok", "kind": "person", "label": "Gitta Kutyniok", "url": "https://arxiv.org/a/gitta_kutyniok", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:philipp_petersen", "kind": "person", "label": "Philipp Petersen", "url": "https://arxiv.org/a/philipp_petersen", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2406.04723", "kind": "paper", "label": "A Deep Automotive Radar Detector using the RaDelft Dataset", "url": "https://arxiv.org/abs/2406.04723", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2024-06-07"}
{"type": "node", "id": "author:ignacio_roldan", "kind": "person", "label": "Ignacio Roldan", "url": "https://arxiv.org/a/ignacio_roldan", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:andras_palffy", "kind": "person", "label": "Andras Palffy", "url": "https://arxiv.org/a/andras_palffy", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:julian_f_p_kooij", "kind": "person", "label": "Julian F. P. Kooij", "url": "https://arxiv.org/a/julian_f_p_kooij", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:dariu_m_gavrila", "kind": "person", "label": "Dariu M. Gavrila", "url": "https://arxiv.org/a/dariu_m_gavrila", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:francesco_fioranelli", "kind": "person", "label": "Francesco Fioranelli", "url": "https://arxiv.org/a/francesco_fioranelli", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2302.10473", "kind": "paper", "label": "Oriented object detection in optical remote sensing images using deep learning: a survey", "url": "https://arxiv.org/abs/2302.10473", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2023-02-21"}
{"type": "node", "id": "author:kun_wang", "kind": "person", "label": "Kun Wang", "url": "https://arxiv.org/a/kun_wang", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:zi_wang", "kind": "person", "label": "Zi Wang", "url": "https://arxiv.org/a/zi_wang", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:zhang_li", "kind": "person", "label": "Zhang Li", "url": "https://arxiv.org/a/zhang_li", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:ang_su", "kind": "person", "label": "Ang Su", "url": "https://arxiv.org/a/ang_su", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:xichao_teng", "kind": "person", "label": "Xichao Teng", "url": "https://arxiv.org/a/xichao_teng", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2301.00942", "kind": "paper", "label": "Deep Learning and Computational Physics (Lecture Notes)", "url": "https://arxiv.org/abs/2301.00942", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2023-01-03"}
{"type": "node", "id": "author:deep_ray", "kind": "person", "label": "Deep Ray", "url": "https://arxiv.org/a/deep_ray", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:orazio_pinti", "kind": "person", "label": "Orazio Pinti", "url": "https://arxiv.org/a/orazio_pinti", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:assad_a_oberai", "kind": "person", "label": "Assad A. Oberai", "url": "https://arxiv.org/a/assad_a_oberai", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2212.00966", "kind": "paper", "label": "A Hybrid Deep Learning Anomaly Detection Framework for Intrusion Detection", "url": "https://arxiv.org/abs/2212.00966", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2022-12-02"}
{"type": "node", "id": "author:rahul_kale", "kind": "person", "label": "Rahul Kale", "url": "https://arxiv.org/a/rahul_kale", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:zhi_lu", "kind": "person", "label": "Zhi Lu", "url": "https://arxiv.org/a/zhi_lu", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:kar_wai_fok", "kind": "person", "label": "Kar Wai Fok", "url": "https://arxiv.org/a/kar_wai_fok", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:vrizlynn_l_l_thing", "kind": "person", "label": "Vrizlynn L. L. Thing", "url": "https://arxiv.org/a/vrizlynn_l_l_thing", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:1706.05726", "kind": "paper", "label": "Using Deep Networks for Drone Detection", "url": "https://arxiv.org/abs/1706.05726", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2017-06-18"}
{"type": "node", "id": "author:cemal_aker", "kind": "person", "label": "Cemal Aker", "url": "https://arxiv.org/a/cemal_aker", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:sinan_kalkan", "kind": "person", "label": "Sinan Kalkan", "url": "https://arxiv.org/a/sinan_kalkan", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2512.13018", "kind": "paper", "label": "Comprehensive Deployment-Oriented Assessment for Cross-Environment Generalization in Deep Learning-Based mmWave Radar Sensing", "url": "https://arxiv.org/abs/2512.13018", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2025-12-15"}
{"type": "node", "id": "author:tomoya_tanaka", "kind": "person", "label": "Tomoya Tanaka", "url": "https://arxiv.org/a/tomoya_tanaka", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:tomonori_ikeda", "kind": "person", "label": "Tomonori Ikeda", "url": "https://arxiv.org/a/tomonori_ikeda", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:ryo_yonemoto", "kind": "person", "label": "Ryo Yonemoto", "url": "https://arxiv.org/a/ryo_yonemoto", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2210.11745", "kind": "paper", "label": "BC-IoDT: Blockchain-based Framework for Authentication in Internet of Drone Things", "url": "https://arxiv.org/abs/2210.11745", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2022-10-21"}
{"type": "node", "id": "author:junaid_akram", "kind": "person", "label": "Junaid Akram", "url": "https://arxiv.org/a/junaid_akram", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:awais_akram", "kind": "person", "label": "Awais Akram", "url": "https://arxiv.org/a/awais_akram", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:rutvij_h_jhaveri", "kind": "person", "label": "Rutvij H. Jhaveri", "url": "https://arxiv.org/a/rutvij_h_jhaveri", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:mamoun_alazab", "kind": "person", "label": "Mamoun Alazab", "url": "https://arxiv.org/a/mamoun_alazab", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:haoran_chi", "kind": "person", "label": "Haoran Chi", "url": "https://arxiv.org/a/haoran_chi", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2112.15454", "kind": "paper", "label": "Advanced Drone Swarm Security by Using Blockchain Governance Game", "url": "https://arxiv.org/abs/2112.15454", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2021-12-29"}
{"type": "node", "id": "author:song_kyoo_kim", "kind": "person", "label": "Song-Kyoo Kim", "url": "https://arxiv.org/a/song_kyoo_kim", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:1711.00146", "kind": "paper", "label": "A multitask deep learning model for real-time deployment in embedded systems", "url": "https://arxiv.org/abs/1711.00146", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2017-10-31"}
{"type": "node", "id": "author:miquel_mart", "kind": "person", "label": "Miquel Mart\u00ed", "url": "https://arxiv.org/a/miquel_mart", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:atsuto_maki", "kind": "person", "label": "Atsuto Maki", "url": "https://arxiv.org/a/atsuto_maki", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2511.20003", "kind": "paper", "label": "Redefining Radar Segmentation: Simultaneous Static-Moving Segmentation and Ego-Motion Estimation using Radar Point Clouds", "url": "https://arxiv.org/abs/2511.20003", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2025-11-25"}
{"type": "node", "id": "author:simin_zhu", "kind": "person", "label": "Simin Zhu", "url": "https://arxiv.org/a/simin_zhu", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:satish_ravindran", "kind": "person", "label": "Satish Ravindran", "url": "https://arxiv.org/a/satish_ravindran", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:alexander_yarovoy", "kind": "person", "label": "Alexander Yarovoy", "url": "https://arxiv.org/a/alexander_yarovoy", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2603.29261", "kind": "paper", "label": "Monodense Deep Neural Model for Determining Item Price Elasticity", "url": "https://arxiv.org/abs/2603.29261", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2026-03-31"}
{"type": "node", "id": "author:lakshya_garg", "kind": "person", "label": "Lakshya Garg", "url": "https://arxiv.org/a/lakshya_garg", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:sai_yaswanth", "kind": "person", "label": "Sai Yaswanth", "url": "https://arxiv.org/a/sai_yaswanth", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:deep_narayan_mishra", "kind": "person", "label": "Deep Narayan Mishra", "url": "https://arxiv.org/a/deep_narayan_mishra", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:karthik_kumaran", "kind": "person", "label": "Karthik Kumaran", "url": "https://arxiv.org/a/karthik_kumaran", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:anupriya_sharma", "kind": "person", "label": "Anupriya Sharma", "url": "https://arxiv.org/a/anupriya_sharma", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:1903.03040", "kind": "paper", "label": "Deep learning observables in computational fluid dynamics", "url": "https://arxiv.org/abs/1903.03040", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2019-03-07"}
{"type": "node", "id": "author:kjetil_o_lye", "kind": "person", "label": "Kjetil O. Lye", "url": "https://arxiv.org/a/kjetil_o_lye", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:siddhartha_mishra", "kind": "person", "label": "Siddhartha Mishra", "url": "https://arxiv.org/a/siddhartha_mishra", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2012.06469", "kind": "paper", "label": "DILIE: Deep Internal Learning for Image Enhancement", "url": "https://arxiv.org/abs/2012.06469", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2020-12-11"}
{"type": "node", "id": "author:indra_deep_mastan", "kind": "person", "label": "Indra Deep Mastan", "url": "https://arxiv.org/a/indra_deep_mastan", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:shanmuganathan_raman", "kind": "person", "label": "Shanmuganathan Raman", "url": "https://arxiv.org/a/shanmuganathan_raman", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2503.00853", "kind": "paper", "label": "MTReD: 3D Reconstruction Dataset for Fly-over Videos of Maritime Domain", "url": "https://arxiv.org/abs/2503.00853", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2025-03-02"}
{"type": "node", "id": "author:rui_yi_yong", "kind": "person", "label": "Rui Yi Yong", "url": "https://arxiv.org/a/rui_yi_yong", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:samuel_picosson", "kind": "person", "label": "Samuel Picosson", "url": "https://arxiv.org/a/samuel_picosson", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:arnold_wiliem", "kind": "person", "label": "Arnold Wiliem", "url": "https://arxiv.org/a/arnold_wiliem", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2004.03722", "kind": "paper", "label": "Challenges in Vessel Behavior and Anomaly Detection: From Classical Machine Learning to Deep Learning", "url": "https://arxiv.org/abs/2004.03722", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2020-04-07"}
{"type": "node", "id": "author:lucas_may_petry", "kind": "person", "label": "Lucas May Petry", "url": "https://arxiv.org/a/lucas_may_petry", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:amilcar_soares", "kind": "person", "label": "Amilcar Soares", "url": "https://arxiv.org/a/amilcar_soares", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:vania_bogorny", "kind": "person", "label": "Vania Bogorny", "url": "https://arxiv.org/a/vania_bogorny", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:bruno_brandoli", "kind": "person", "label": "Bruno Brandoli", "url": "https://arxiv.org/a/bruno_brandoli", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:stan_matwin", "kind": "person", "label": "Stan Matwin", "url": "https://arxiv.org/a/stan_matwin", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2406.08294", "kind": "paper", "label": "Vessel Re-identification and Activity Detection in Thermal Domain for Maritime Surveillance", "url": "https://arxiv.org/abs/2406.08294", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2024-06-12"}
{"type": "node", "id": "author:yasod_ginige", "kind": "person", "label": "Yasod Ginige", "url": "https://arxiv.org/a/yasod_ginige", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:ransika_gunasekara", "kind": "person", "label": "Ransika Gunasekara", "url": "https://arxiv.org/a/ransika_gunasekara", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:darsha_hewavitharana", "kind": "person", "label": "Darsha Hewavitharana", "url": "https://arxiv.org/a/darsha_hewavitharana", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:manjula_ariyarathne", "kind": "person", "label": "Manjula Ariyarathne", "url": "https://arxiv.org/a/manjula_ariyarathne", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:ranga_rodrigo", "kind": "person", "label": "Ranga Rodrigo", "url": "https://arxiv.org/a/ranga_rodrigo", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2311.14764", "kind": "paper", "label": "SafeSea: Synthetic Data Generation for Adverse &amp; Low Probability Maritime Conditions", "url": "https://arxiv.org/abs/2311.14764", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2023-11-24"}
{"type": "node", "id": "author:martin_tran", "kind": "person", "label": "Martin Tran", "url": "https://arxiv.org/a/martin_tran", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:jordan_shipard", "kind": "person", "label": "Jordan Shipard", "url": "https://arxiv.org/a/jordan_shipard", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:hermawan_mulyono", "kind": "person", "label": "Hermawan Mulyono", "url": "https://arxiv.org/a/hermawan_mulyono", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:clinton_fookes", "kind": "person", "label": "Clinton Fookes", "url": "https://arxiv.org/a/clinton_fookes", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2507.01274", "kind": "paper", "label": "AI Meets Maritime Training: Precision Analytics for Enhanced Safety and Performance", "url": "https://arxiv.org/abs/2507.01274", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2025-07-02"}
{"type": "node", "id": "author:vishakha_lall", "kind": "person", "label": "Vishakha Lall", "url": "https://arxiv.org/a/vishakha_lall", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:yisi_liu", "kind": "person", "label": "Yisi Liu", "url": "https://arxiv.org/a/yisi_liu", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2602.00124", "kind": "paper", "label": "Context-Aware Autoencoders for Anomaly Detection in Maritime Surveillance", "url": "https://arxiv.org/abs/2602.00124", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2026-01-27"}
{"type": "node", "id": "author:divya_acharya", "kind": "person", "label": "Divya Acharya", "url": "https://arxiv.org/a/divya_acharya", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:pierre_bernab_e", "kind": "person", "label": "Pierre Bernab'e", "url": "https://arxiv.org/a/pierre_bernab_e", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:antoine_chevrot", "kind": "person", "label": "Antoine Chevrot", "url": "https://arxiv.org/a/antoine_chevrot", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:helge_spieker", "kind": "person", "label": "Helge Spieker", "url": "https://arxiv.org/a/helge_spieker", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:arnaud_gotlieb", "kind": "person", "label": "Arnaud Gotlieb", "url": "https://arxiv.org/a/arnaud_gotlieb", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2403.05778", "kind": "paper", "label": "Spatial Clustering Approach for Vessel Path Identification", "url": "https://arxiv.org/abs/2403.05778", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2024-03-09"}
{"type": "node", "id": "author:mohamed_abuella", "kind": "person", "label": "Mohamed Abuella", "url": "https://arxiv.org/a/mohamed_abuella", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:m_amine_atoui", "kind": "person", "label": "M. Amine Atoui", "url": "https://arxiv.org/a/m_amine_atoui", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:slawomir_nowaczyk", "kind": "person", "label": "Slawomir Nowaczyk", "url": "https://arxiv.org/a/slawomir_nowaczyk", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:simon_johansson", "kind": "person", "label": "Simon Johansson", "url": "https://arxiv.org/a/simon_johansson", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:ethan_faghan", "kind": "person", "label": "Ethan Faghan", "url": "https://arxiv.org/a/ethan_faghan", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2507.07153", "kind": "paper", "label": "Aerial Maritime Vessel Detection and Identification", "url": "https://arxiv.org/abs/2507.07153", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2025-07-09"}
{"type": "node", "id": "author:antonella_barisic_kulas", "kind": "person", "label": "Antonella Barisic Kulas", "url": "https://arxiv.org/a/antonella_barisic_kulas", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:frano_petric", "kind": "person", "label": "Frano Petric", "url": "https://arxiv.org/a/frano_petric", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:stjepan_bogdan", "kind": "person", "label": "Stjepan Bogdan", "url": "https://arxiv.org/a/stjepan_bogdan", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2510.11449", "kind": "paper", "label": "Enhancing Maritime Domain Awareness on Inland Waterways: A YOLO-Based Fusion of Satellite and AIS for Vessel Characterization", "url": "https://arxiv.org/abs/2510.11449", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2025-10-13"}
{"type": "node", "id": "author:geoffery_agorku", "kind": "person", "label": "Geoffery Agorku", "url": "https://arxiv.org/a/geoffery_agorku", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:sarah_hernandez", "kind": "person", "label": "Sarah Hernandez", "url": "https://arxiv.org/a/sarah_hernandez", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:hayley_hames", "kind": "person", "label": "Hayley Hames", "url": "https://arxiv.org/a/hayley_hames", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:cade_wagner", "kind": "person", "label": "Cade Wagner", "url": "https://arxiv.org/a/cade_wagner", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2102.05869", "kind": "paper", "label": "ABOShips -- An Inshore and Offshore Maritime Vessel Detection Dataset with Precise Annotations", "url": "https://arxiv.org/abs/2102.05869", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2021-02-11"}
{"type": "node", "id": "author:bogdan_iancu", "kind": "person", "label": "Bogdan Iancu", "url": "https://arxiv.org/a/bogdan_iancu", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:valentin_soloviev", "kind": "person", "label": "Valentin Soloviev", "url": "https://arxiv.org/a/valentin_soloviev", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:luca_zelioli", "kind": "person", "label": "Luca Zelioli", "url": "https://arxiv.org/a/luca_zelioli", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:johan_lilius", "kind": "person", "label": "Johan Lilius", "url": "https://arxiv.org/a/johan_lilius", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2306.13894", "kind": "paper", "label": "OUXT Polaris: Autonomous Navigation System for the 2022 Maritime RobotX Challenge", "url": "https://arxiv.org/abs/2306.13894", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2023-06-24"}
{"type": "node", "id": "author:kenta_okamoto", "kind": "person", "label": "Kenta Okamoto", "url": "https://arxiv.org/a/kenta_okamoto", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:akihisa_nagata", "kind": "person", "label": "Akihisa Nagata", "url": "https://arxiv.org/a/akihisa_nagata", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:kyoma_arai", "kind": "person", "label": "Kyoma Arai", "url": "https://arxiv.org/a/kyoma_arai", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:yusei_nagao", "kind": "person", "label": "Yusei Nagao", "url": "https://arxiv.org/a/yusei_nagao", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:tatsuki_nishimura", "kind": "person", "label": "Tatsuki Nishimura", "url": "https://arxiv.org/a/tatsuki_nishimura", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2306.12767", "kind": "paper", "label": "A Search Strategy and Vessel Detection in Maritime Environment Using Fixed-Wing UAVs", "url": "https://arxiv.org/abs/2306.12767", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2023-06-22"}
{"type": "node", "id": "author:marijana_peti", "kind": "person", "label": "Marijana Peti", "url": "https://arxiv.org/a/marijana_peti", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:ana_milas", "kind": "person", "label": "Ana Milas", "url": "https://arxiv.org/a/ana_milas", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:natko_kra_evac", "kind": "person", "label": "Natko Kra\u0161evac", "url": "https://arxiv.org/a/natko_kra_evac", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:marko_kri_man_i", "kind": "person", "label": "Marko Kri\u017eman\u010di\u0107", "url": "https://arxiv.org/a/marko_kri_man_i", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:ivan_lon_ar", "kind": "person", "label": "Ivan Lon\u010dar", "url": "https://arxiv.org/a/ivan_lon_ar", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2511.14203", "kind": "paper", "label": "Multi-Scale Correlation-Aware Transformer for Maritime Vessel Re-Identification", "url": "https://arxiv.org/abs/2511.14203", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2025-11-18"}
{"type": "node", "id": "author:yunhe_liu", "kind": "person", "label": "Yunhe Liu", "url": "https://arxiv.org/a/yunhe_liu", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2311.14762", "kind": "paper", "label": "The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024", "url": "https://arxiv.org/abs/2311.14762", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2023-11-23"}
{"type": "node", "id": "author:benjamin_kiefer", "kind": "person", "label": "Benjamin Kiefer", "url": "https://arxiv.org/a/benjamin_kiefer", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:lojze_ust", "kind": "person", "label": "Lojze \u017dust", "url": "https://arxiv.org/a/lojze_ust", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:matej_kristan", "kind": "person", "label": "Matej Kristan", "url": "https://arxiv.org/a/matej_kristan", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:janez_per", "kind": "person", "label": "Janez Per\u0161", "url": "https://arxiv.org/a/janez_per", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:matija_ter_ek", "kind": "person", "label": "Matija Ter\u0161ek", "url": "https://arxiv.org/a/matija_ter_ek", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2312.05270", "kind": "paper", "label": "Image and AIS Data Fusion Technique for Maritime Computer Vision Applications", "url": "https://arxiv.org/abs/2312.05270", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2023-12-07"}
{"type": "node", "id": "author:emre_g_lsoylu", "kind": "person", "label": "Emre G\u00fclsoylu", "url": "https://arxiv.org/a/emre_g_lsoylu", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:paul_koch", "kind": "person", "label": "Paul Koch", "url": "https://arxiv.org/a/paul_koch", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:mert_y_ld_z", "kind": "person", "label": "Mert Y\u0131ld\u0131z", "url": "https://arxiv.org/a/mert_y_ld_z", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:manfred_constapel", "kind": "person", "label": "Manfred Constapel", "url": "https://arxiv.org/a/manfred_constapel", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:andr_peter_kelm", "kind": "person", "label": "Andr\u00e9 Peter Kelm", "url": "https://arxiv.org/a/andr_peter_kelm", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:1609.04846", "kind": "paper", "label": "A Tutorial about Random Neural Networks in Supervised Learning", "url": "https://arxiv.org/abs/1609.04846", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2016-09-15"}
{"type": "node", "id": "author:sebasti_n_basterrech", "kind": "person", "label": "Sebasti\u00e1n Basterrech", "url": "https://arxiv.org/a/sebasti_n_basterrech", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:gerardo_rubino", "kind": "person", "label": "Gerardo Rubino", "url": "https://arxiv.org/a/gerardo_rubino", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2502.01654", "kind": "paper", "label": "Predicting concentration levels of air pollutants by transfer learning and recurrent neural network", "url": "https://arxiv.org/abs/2502.01654", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2025-01-30"}
{"type": "node", "id": "author:iat_hang_fong", "kind": "person", "label": "Iat Hang Fong", "url": "https://arxiv.org/a/iat_hang_fong", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:tengyue_li", "kind": "person", "label": "Tengyue Li", "url": "https://arxiv.org/a/tengyue_li", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:simon_fong", "kind": "person", "label": "Simon Fong", "url": "https://arxiv.org/a/simon_fong", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:raymond_k_wong", "kind": "person", "label": "Raymond K. Wong", "url": "https://arxiv.org/a/raymond_k_wong", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:antonio_j_tall_n_ballesteros", "kind": "person", "label": "Antonio J. Tall\u00f3n-Ballesteros", "url": "https://arxiv.org/a/antonio_j_tall_n_ballesteros", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:1807.06789", "kind": "paper", "label": "DroNet: Efficient convolutional neural network detector for real-time UAV applications", "url": "https://arxiv.org/abs/1807.06789", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2018-07-18"}
{"type": "node", "id": "author:stylianos_venieris", "kind": "person", "label": "Stylianos Venieris", "url": "https://arxiv.org/a/stylianos_venieris", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:christos_savvas_bouganis", "kind": "person", "label": "Christos-Savvas Bouganis", "url": "https://arxiv.org/a/christos_savvas_bouganis", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:1803.02421", "kind": "paper", "label": "Masked Conditional Neural Networks for Audio Classification", "url": "https://arxiv.org/abs/1803.02421", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2018-03-06"}
{"type": "node", "id": "author:fady_medhat", "kind": "person", "label": "Fady Medhat", "url": "https://arxiv.org/a/fady_medhat", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:david_chesmore", "kind": "person", "label": "David Chesmore", "url": "https://arxiv.org/a/david_chesmore", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:john_robinson", "kind": "person", "label": "John Robinson", "url": "https://arxiv.org/a/john_robinson", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2311.03561", "kind": "paper", "label": "Sea You Later: Metadata-Guided Long-Term Re-Identification for UAV-Based Multi-Object Tracking", "url": "https://arxiv.org/abs/2311.03561", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2023-11-06"}
{"type": "node", "id": "author:cheng_yen_yang", "kind": "person", "label": "Cheng-Yen Yang", "url": "https://arxiv.org/a/cheng_yen_yang", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:hsiang_wei_huang", "kind": "person", "label": "Hsiang-Wei Huang", "url": "https://arxiv.org/a/hsiang_wei_huang", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:zhongyu_jiang", "kind": "person", "label": "Zhongyu Jiang", "url": "https://arxiv.org/a/zhongyu_jiang", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:heng_cheng_kuo", "kind": "person", "label": "Heng-Cheng Kuo", "url": "https://arxiv.org/a/heng_cheng_kuo", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:jie_mei", "kind": "person", "label": "Jie Mei", "url": "https://arxiv.org/a/jie_mei", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2002.04849", "kind": "paper", "label": "Combining LoRaWAN and a New 3D Motion Model for Remote UAV Tracking", "url": "https://arxiv.org/abs/2002.04849", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2020-02-12"}
{"type": "node", "id": "author:federico_mason", "kind": "person", "label": "Federico Mason", "url": "https://arxiv.org/a/federico_mason", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:federico_chiariotti", "kind": "person", "label": "Federico Chiariotti", "url": "https://arxiv.org/a/federico_chiariotti", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:martina_capuzzo", "kind": "person", "label": "Martina Capuzzo", "url": "https://arxiv.org/a/martina_capuzzo", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:davide_magrin", "kind": "person", "label": "Davide Magrin", "url": "https://arxiv.org/a/davide_magrin", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:andrea_zanella", "kind": "person", "label": "Andrea Zanella", "url": "https://arxiv.org/a/andrea_zanella", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2008.02834", "kind": "paper", "label": "Integration of the 3D Environment for UAV Onboard Visual Object Tracking", "url": "https://arxiv.org/abs/2008.02834", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2020-08-06"}
{"type": "node", "id": "author:st_phane_vujasinovi", "kind": "person", "label": "St\u00e9phane Vujasinovi\u0107", "url": "https://arxiv.org/a/st_phane_vujasinovi", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:stefan_becker", "kind": "person", "label": "Stefan Becker", "url": "https://arxiv.org/a/stefan_becker", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:timo_breuer", "kind": "person", "label": "Timo Breuer", "url": "https://arxiv.org/a/timo_breuer", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:sebastian_bullinger", "kind": "person", "label": "Sebastian Bullinger", "url": "https://arxiv.org/a/sebastian_bullinger", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:norbert_scherer_negenborn", "kind": "person", "label": "Norbert Scherer-Negenborn", "url": "https://arxiv.org/a/norbert_scherer_negenborn", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2306.14753", "kind": "paper", "label": "The Deep Arbitrary Polynomial Chaos Neural Network or how Deep Artificial Neural Networks could benefit from Data-Driven Homogeneous Chaos Theory", "url": "https://arxiv.org/abs/2306.14753", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2023-06-26"}
{"type": "node", "id": "author:sergey_oladyshkin", "kind": "person", "label": "Sergey Oladyshkin", "url": "https://arxiv.org/a/sergey_oladyshkin", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:timothy_praditia", "kind": "person", "label": "Timothy Praditia", "url": "https://arxiv.org/a/timothy_praditia", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:ilja_kr_ker", "kind": "person", "label": "Ilja Kr\u00f6ker", "url": "https://arxiv.org/a/ilja_kr_ker", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:farid_mohammadi", "kind": "person", "label": "Farid Mohammadi", "url": "https://arxiv.org/a/farid_mohammadi", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:wolfgang_nowak", "kind": "person", "label": "Wolfgang Nowak", "url": "https://arxiv.org/a/wolfgang_nowak", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2512.14608", "kind": "paper", "label": "Fusion of Cellular ISAC and Passive RF Sensing for UAV Detection and Tracking", "url": "https://arxiv.org/abs/2512.14608", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2025-12-16"}
{"type": "node", "id": "author:cole_dickerson", "kind": "person", "label": "Cole Dickerson", "url": "https://arxiv.org/a/cole_dickerson", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:sean_kearney", "kind": "person", "label": "Sean Kearney", "url": "https://arxiv.org/a/sean_kearney", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:sultan_manjur", "kind": "person", "label": "Sultan Manjur", "url": "https://arxiv.org/a/sultan_manjur", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:ismail_guvenc", "kind": "person", "label": "Ismail Guvenc", "url": "https://arxiv.org/a/ismail_guvenc", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:sevgi_gurbuz", "kind": "person", "label": "Sevgi Gurbuz", "url": "https://arxiv.org/a/sevgi_gurbuz", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2603.27493", "kind": "paper", "label": "Fully Spiking Neural Networks with Target Awareness for Energy-Efficient UAV Tracking", "url": "https://arxiv.org/abs/2603.27493", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2026-03-29"}
{"type": "node", "id": "author:pengzhi_zhong", "kind": "person", "label": "Pengzhi Zhong", "url": "https://arxiv.org/a/pengzhi_zhong", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:jiwei_mo", "kind": "person", "label": "Jiwei Mo", "url": "https://arxiv.org/a/jiwei_mo", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:dan_zeng", "kind": "person", "label": "Dan Zeng", "url": "https://arxiv.org/a/dan_zeng", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:feixiang_he", "kind": "person", "label": "Feixiang He", "url": "https://arxiv.org/a/feixiang_he", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:shuiwang_li", "kind": "person", "label": "Shuiwang Li", "url": "https://arxiv.org/a/shuiwang_li", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2107.00962", "kind": "paper", "label": "Brain over Brawn: Using a Stereo Camera to Detect, Track, and Intercept a Faster UAV by Reconstructing the Intruder's Trajectory", "url": "https://arxiv.org/abs/2107.00962", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2021-07-02"}
{"type": "node", "id": "author:antonella_barisic", "kind": "person", "label": "Antonella Barisic", "url": "https://arxiv.org/a/antonella_barisic", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2110.02772", "kind": "paper", "label": "The Challenge of Appearance-Free Object Tracking with Feedforward Neural Networks", "url": "https://arxiv.org/abs/2110.02772", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2021-09-30"}
{"type": "node", "id": "author:girik_malik", "kind": "person", "label": "Girik Malik", "url": "https://arxiv.org/a/girik_malik", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:drew_linsley", "kind": "person", "label": "Drew Linsley", "url": "https://arxiv.org/a/drew_linsley", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:thomas_serre", "kind": "person", "label": "Thomas Serre", "url": "https://arxiv.org/a/thomas_serre", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:ennio_mingolla", "kind": "person", "label": "Ennio Mingolla", "url": "https://arxiv.org/a/ennio_mingolla", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:1408.3438", "kind": "paper", "label": "On the Role of Identity in Surveillance", "url": "https://arxiv.org/abs/1408.3438", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2014-08-14"}
{"type": "node", "id": "author:victoria_wang", "kind": "person", "label": "Victoria Wang", "url": "https://arxiv.org/a/victoria_wang", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:john_v_tucker", "kind": "person", "label": "John V. Tucker", "url": "https://arxiv.org/a/john_v_tucker", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:1912.03600", "kind": "paper", "label": "Repeatedly Energy-Efficient and Fair Service Coverage: UAV Slicing (Proactive UAV Network Slicing for URLLC and Mobile Broadband Service Multiplexing)", "url": "https://arxiv.org/abs/1912.03600", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2019-12-08"}
{"type": "node", "id": "author:peng_yang", "kind": "person", "label": "Peng Yang", "url": "https://arxiv.org/a/peng_yang", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:xing_xi", "kind": "person", "label": "Xing Xi", "url": "https://arxiv.org/a/xing_xi", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:tony_q_s_quek", "kind": "person", "label": "Tony Q. S. Quek", "url": "https://arxiv.org/a/tony_q_s_quek", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:jingxuan_chen", "kind": "person", "label": "Jingxuan Chen", "url": "https://arxiv.org/a/jingxuan_chen", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:xianbin_cao", "kind": "person", "label": "Xianbin Cao", "url": "https://arxiv.org/a/xianbin_cao", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:1807.02477", "kind": "paper", "label": "Development of a sensory-neural network for medical diagnosing", "url": "https://arxiv.org/abs/1807.02477", "source": "arxiv", "axis": "defense", "layer": 0, "published": "2018-07-06"}
{"type": "node", "id": "author:igor_grabec", "kind": "person", "label": "Igor Grabec", "url": "https://arxiv.org/a/igor_grabec", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:eva_vegl", "kind": "person", "label": "Eva \u0160vegl", "url": "https://arxiv.org/a/eva_vegl", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "author:mihael_sok", "kind": "person", "label": "Mihael Sok", "url": "https://arxiv.org/a/mihael_sok", "source": "arxiv-author", "axis": "defense", "layer": 0}
{"type": "node", "id": "paper:2306.04338", "kind": "paper", "label": "Changing Data Sources in the Age of Machine Learning for Official Statistics", "url": "https://arxiv.org/abs/2306.04338", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2023-06-07"}
{"type": "node", "id": "author:cedric_de_boom", "kind": "person", "label": "Cedric De Boom", "url": "https://arxiv.org/a/cedric_de_boom", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:michael_reusens", "kind": "person", "label": "Michael Reusens", "url": "https://arxiv.org/a/michael_reusens", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2006.16189", "kind": "paper", "label": "DOME: Recommendations for supervised machine learning validation in biology", "url": "https://arxiv.org/abs/2006.16189", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2020-06-25"}
{"type": "node", "id": "author:ian_walsh", "kind": "person", "label": "Ian Walsh", "url": "https://arxiv.org/a/ian_walsh", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:dmytro_fishman", "kind": "person", "label": "Dmytro Fishman", "url": "https://arxiv.org/a/dmytro_fishman", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:dario_garcia_gasulla", "kind": "person", "label": "Dario Garcia-Gasulla", "url": "https://arxiv.org/a/dario_garcia_gasulla", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:tiina_titma", "kind": "person", "label": "Tiina Titma", "url": "https://arxiv.org/a/tiina_titma", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:gianluca_pollastri", "kind": "person", "label": "Gianluca Pollastri", "url": "https://arxiv.org/a/gianluca_pollastri", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2201.12150", "kind": "paper", "label": "Learning Curves for Decision Making in Supervised Machine Learning: A Survey", "url": "https://arxiv.org/abs/2201.12150", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2022-01-28"}
{"type": "node", "id": "author:felix_mohr", "kind": "person", "label": "Felix Mohr", "url": "https://arxiv.org/a/felix_mohr", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jan_n_van_rijn", "kind": "person", "label": "Jan N. van Rijn", "url": "https://arxiv.org/a/jan_n_van_rijn", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2302.08893", "kind": "paper", "label": "Active learning for data streams: a survey", "url": "https://arxiv.org/abs/2302.08893", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2023-02-17"}
{"type": "node", "id": "author:davide_cacciarelli", "kind": "person", "label": "Davide Cacciarelli", "url": "https://arxiv.org/a/davide_cacciarelli", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:murat_kulahci", "kind": "person", "label": "Murat Kulahci", "url": "https://arxiv.org/a/murat_kulahci", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2303.15563", "kind": "paper", "label": "Privacy-preserving machine learning for healthcare: open challenges and future perspectives", "url": "https://arxiv.org/abs/2303.15563", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2023-03-27"}
{"type": "node", "id": "author:alejandro_guerra_manzanares", "kind": "person", "label": "Alejandro Guerra-Manzanares", "url": "https://arxiv.org/a/alejandro_guerra_manzanares", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:l_julian_lechuga_lopez", "kind": "person", "label": "L. Julian Lechuga Lopez", "url": "https://arxiv.org/a/l_julian_lechuga_lopez", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:michail_maniatakos", "kind": "person", "label": "Michail Maniatakos", "url": "https://arxiv.org/a/michail_maniatakos", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:farah_e_shamout", "kind": "person", "label": "Farah E. Shamout", "url": "https://arxiv.org/a/farah_e_shamout", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2304.02381", "kind": "paper", "label": "Physics-Inspired Interpretability Of Machine Learning Models", "url": "https://arxiv.org/abs/2304.02381", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2023-04-05"}
{"type": "node", "id": "author:maximilian_p_niroomand", "kind": "person", "label": "Maximilian P Niroomand", "url": "https://arxiv.org/a/maximilian_p_niroomand", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:david_j_wales", "kind": "person", "label": "David J Wales", "url": "https://arxiv.org/a/david_j_wales", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:1905.04749", "kind": "paper", "label": "A Benchmark Study of Machine Learning Models for Online Fake News Detection", "url": "https://arxiv.org/abs/1905.04749", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2019-05-12"}
{"type": "node", "id": "author:junaed_younus_khan", "kind": "person", "label": "Junaed Younus Khan", "url": "https://arxiv.org/a/junaed_younus_khan", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:md_tawkat_islam_khondaker", "kind": "person", "label": "Md. Tawkat Islam Khondaker", "url": "https://arxiv.org/a/md_tawkat_islam_khondaker", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:sadia_afroz", "kind": "person", "label": "Sadia Afroz", "url": "https://arxiv.org/a/sadia_afroz", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:gias_uddin", "kind": "person", "label": "Gias Uddin", "url": "https://arxiv.org/a/gias_uddin", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:anindya_iqbal", "kind": "person", "label": "Anindya Iqbal", "url": "https://arxiv.org/a/anindya_iqbal", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2602.11092", "kind": "paper", "label": "MerLin: A Discovery Engine for Photonic and Hybrid Quantum Machine Learning", "url": "https://arxiv.org/abs/2602.11092", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2026-02-11"}
{"type": "node", "id": "author:cassandre_notton", "kind": "person", "label": "Cassandre Notton", "url": "https://arxiv.org/a/cassandre_notton", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:benjamin_stott", "kind": "person", "label": "Benjamin Stott", "url": "https://arxiv.org/a/benjamin_stott", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:philippe_schoeb", "kind": "person", "label": "Philippe Schoeb", "url": "https://arxiv.org/a/philippe_schoeb", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:anthony_walsh", "kind": "person", "label": "Anthony Walsh", "url": "https://arxiv.org/a/anthony_walsh", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:gr_goire_leboucher", "kind": "person", "label": "Gr\u00e9goire Leboucher", "url": "https://arxiv.org/a/gr_goire_leboucher", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:1705.05172", "kind": "paper", "label": "Emotion in Reinforcement Learning Agents and Robots: A Survey", "url": "https://arxiv.org/abs/1705.05172", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2017-05-15"}
{"type": "node", "id": "author:thomas_m_moerland", "kind": "person", "label": "Thomas M. Moerland", "url": "https://arxiv.org/a/thomas_m_moerland", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:joost_broekens", "kind": "person", "label": "Joost Broekens", "url": "https://arxiv.org/a/joost_broekens", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:catholijn_m_jonker", "kind": "person", "label": "Catholijn M. Jonker", "url": "https://arxiv.org/a/catholijn_m_jonker", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2509.08759", "kind": "paper", "label": "Fourier Learning Machines: Nonharmonic Fourier-Based Neural Networks for Scientific Machine Learning", "url": "https://arxiv.org/abs/2509.08759", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2025-09-10"}
{"type": "node", "id": "author:mominul_rubel", "kind": "person", "label": "Mominul Rubel", "url": "https://arxiv.org/a/mominul_rubel", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:adam_meyers", "kind": "person", "label": "Adam Meyers", "url": "https://arxiv.org/a/adam_meyers", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:gabriel_nicolosi", "kind": "person", "label": "Gabriel Nicolosi", "url": "https://arxiv.org/a/gabriel_nicolosi", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:1906.01101", "kind": "paper", "label": "MEMe: An Accurate Maximum Entropy Method for Efficient Approximations in Large-Scale Machine Learning", "url": "https://arxiv.org/abs/1906.01101", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2019-06-03"}
{"type": "node", "id": "author:diego_granziol", "kind": "person", "label": "Diego Granziol", "url": "https://arxiv.org/a/diego_granziol", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:binxin_ru", "kind": "person", "label": "Binxin Ru", "url": "https://arxiv.org/a/binxin_ru", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:stefan_zohren", "kind": "person", "label": "Stefan Zohren", "url": "https://arxiv.org/a/stefan_zohren", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:xiaowen_doing", "kind": "person", "label": "Xiaowen Doing", "url": "https://arxiv.org/a/xiaowen_doing", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:michael_osborne", "kind": "person", "label": "Michael Osborne", "url": "https://arxiv.org/a/michael_osborne", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2404.12511", "kind": "paper", "label": "Generalizing Machine Learning Evaluation through the Integration of Shannon Entropy and Rough Set Theory", "url": "https://arxiv.org/abs/2404.12511", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2024-04-18"}
{"type": "node", "id": "author:olga_cherednichenko", "kind": "person", "label": "Olga Cherednichenko", "url": "https://arxiv.org/a/olga_cherednichenko", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:dmytro_chernyshov", "kind": "person", "label": "Dmytro Chernyshov", "url": "https://arxiv.org/a/dmytro_chernyshov", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:dmytro_sytnikov", "kind": "person", "label": "Dmytro Sytnikov", "url": "https://arxiv.org/a/dmytro_sytnikov", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:polina_sytnikova", "kind": "person", "label": "Polina Sytnikova", "url": "https://arxiv.org/a/polina_sytnikova", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2402.01393", "kind": "paper", "label": "ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data", "url": "https://arxiv.org/abs/2402.01393", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2024-02-02"}
{"type": "node", "id": "author:carmen_martin_turrero", "kind": "person", "label": "Carmen Martin-Turrero", "url": "https://arxiv.org/a/carmen_martin_turrero", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:maxence_bouvier", "kind": "person", "label": "Maxence Bouvier", "url": "https://arxiv.org/a/maxence_bouvier", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:manuel_breitenstein", "kind": "person", "label": "Manuel Breitenstein", "url": "https://arxiv.org/a/manuel_breitenstein", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:pietro_zanuttigh", "kind": "person", "label": "Pietro Zanuttigh", "url": "https://arxiv.org/a/pietro_zanuttigh", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:vincent_parret", "kind": "person", "label": "Vincent Parret", "url": "https://arxiv.org/a/vincent_parret", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2204.12833", "kind": "paper", "label": "Transfer Learning with Pre-trained Conditional Generative Models", "url": "https://arxiv.org/abs/2204.12833", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2022-04-27"}
{"type": "node", "id": "author:shin_ya_yamaguchi", "kind": "person", "label": "Shin'ya Yamaguchi", "url": "https://arxiv.org/a/shin_ya_yamaguchi", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:sekitoshi_kanai", "kind": "person", "label": "Sekitoshi Kanai", "url": "https://arxiv.org/a/sekitoshi_kanai", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:atsutoshi_kumagai", "kind": "person", "label": "Atsutoshi Kumagai", "url": "https://arxiv.org/a/atsutoshi_kumagai", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:daiki_chijiwa", "kind": "person", "label": "Daiki Chijiwa", "url": "https://arxiv.org/a/daiki_chijiwa", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:hisashi_kashima", "kind": "person", "label": "Hisashi Kashima", "url": "https://arxiv.org/a/hisashi_kashima", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:1905.10345", "kind": "paper", "label": "Automatic Machine Learning by Pipeline Synthesis using Model-Based Reinforcement Learning and a Grammar", "url": "https://arxiv.org/abs/1905.10345", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2019-05-24"}
{"type": "node", "id": "author:iddo_drori", "kind": "person", "label": "Iddo Drori", "url": "https://arxiv.org/a/iddo_drori", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yamuna_krishnamurthy", "kind": "person", "label": "Yamuna Krishnamurthy", "url": "https://arxiv.org/a/yamuna_krishnamurthy", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:raoni_lourenco", "kind": "person", "label": "Raoni Lourenco", "url": "https://arxiv.org/a/raoni_lourenco", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:remi_rampin", "kind": "person", "label": "Remi Rampin", "url": "https://arxiv.org/a/remi_rampin", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:kyunghyun_cho", "kind": "person", "label": "Kyunghyun Cho", "url": "https://arxiv.org/a/kyunghyun_cho", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:1910.09700", "kind": "paper", "label": "Quantifying the Carbon Emissions of Machine Learning", "url": "https://arxiv.org/abs/1910.09700", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2019-10-21"}
{"type": "node", "id": "author:alexandre_lacoste", "kind": "person", "label": "Alexandre Lacoste", "url": "https://arxiv.org/a/alexandre_lacoste", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:alexandra_luccioni", "kind": "person", "label": "Alexandra Luccioni", "url": "https://arxiv.org/a/alexandra_luccioni", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:victor_schmidt", "kind": "person", "label": "Victor Schmidt", "url": "https://arxiv.org/a/victor_schmidt", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:thomas_dandres", "kind": "person", "label": "Thomas Dandres", "url": "https://arxiv.org/a/thomas_dandres", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2103.00286", "kind": "paper", "label": "A Novel Adaptive Deep Network for Building Footprint Segmentation", "url": "https://arxiv.org/abs/2103.00286", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2021-02-27"}
{"type": "node", "id": "author:a_ziaee", "kind": "person", "label": "A. Ziaee", "url": "https://arxiv.org/a/a_ziaee", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:r_dehbozorgi", "kind": "person", "label": "R. Dehbozorgi", "url": "https://arxiv.org/a/r_dehbozorgi", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:m_d_ller", "kind": "person", "label": "M. D\u00f6ller", "url": "https://arxiv.org/a/m_d_ller", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2403.12562", "kind": "paper", "label": "PePR: Performance Per Resource Unit as a Metric to Promote Small-Scale Deep Learning in Medical Image Analysis", "url": "https://arxiv.org/abs/2403.12562", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2024-03-19"}
{"type": "node", "id": "author:raghavendra_selvan", "kind": "person", "label": "Raghavendra Selvan", "url": "https://arxiv.org/a/raghavendra_selvan", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:bob_pepin", "kind": "person", "label": "Bob Pepin", "url": "https://arxiv.org/a/bob_pepin", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:christian_igel", "kind": "person", "label": "Christian Igel", "url": "https://arxiv.org/a/christian_igel", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:gabrielle_samuel", "kind": "person", "label": "Gabrielle Samuel", "url": "https://arxiv.org/a/gabrielle_samuel", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:erik_b_dam", "kind": "person", "label": "Erik B Dam", "url": "https://arxiv.org/a/erik_b_dam", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2007.03051", "kind": "paper", "label": "Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models", "url": "https://arxiv.org/abs/2007.03051", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2020-07-06"}
{"type": "node", "id": "author:lasse_f_wolff_anthony", "kind": "person", "label": "Lasse F. Wolff Anthony", "url": "https://arxiv.org/a/lasse_f_wolff_anthony", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:benjamin_kanding", "kind": "person", "label": "Benjamin Kanding", "url": "https://arxiv.org/a/benjamin_kanding", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2109.13918", "kind": "paper", "label": "Toxicity of Carbon Nanomaterials", "url": "https://arxiv.org/abs/2109.13918", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2021-09-20"}
{"type": "node", "id": "author:arpita_adhikari", "kind": "person", "label": "Arpita Adhikari", "url": "https://arxiv.org/a/arpita_adhikari", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:joydip_sengupta", "kind": "person", "label": "Joydip Sengupta", "url": "https://arxiv.org/a/joydip_sengupta", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2512.23753", "kind": "paper", "label": "Generalized Regularized Evidential Deep Learning Models: Theory and Comprehensive Evaluation", "url": "https://arxiv.org/abs/2512.23753", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2025-12-27"}
{"type": "node", "id": "author:deep_shankar_pandey", "kind": "person", "label": "Deep Shankar Pandey", "url": "https://arxiv.org/a/deep_shankar_pandey", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:hyomin_choi", "kind": "person", "label": "Hyomin Choi", "url": "https://arxiv.org/a/hyomin_choi", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:1903.04717", "kind": "paper", "label": "Activation Analysis of a Byte-Based Deep Neural Network for Malware Classification", "url": "https://arxiv.org/abs/1903.04717", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2019-03-12"}
{"type": "node", "id": "author:scott_e_coull", "kind": "person", "label": "Scott E. Coull", "url": "https://arxiv.org/a/scott_e_coull", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:christopher_gardner", "kind": "person", "label": "Christopher Gardner", "url": "https://arxiv.org/a/christopher_gardner", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2302.04143", "kind": "paper", "label": "Predicting Thrombectomy Recanalization from CT Imaging Using Deep Learning Models", "url": "https://arxiv.org/abs/2302.04143", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2023-02-08"}
{"type": "node", "id": "author:haoyue_zhang", "kind": "person", "label": "Haoyue Zhang", "url": "https://arxiv.org/a/haoyue_zhang", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jennifer_s_polson", "kind": "person", "label": "Jennifer S. Polson", "url": "https://arxiv.org/a/jennifer_s_polson", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:eric_j_yang", "kind": "person", "label": "Eric J. Yang", "url": "https://arxiv.org/a/eric_j_yang", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:kambiz_nael", "kind": "person", "label": "Kambiz Nael", "url": "https://arxiv.org/a/kambiz_nael", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:william_speier", "kind": "person", "label": "William Speier", "url": "https://arxiv.org/a/william_speier", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2109.05472", "kind": "paper", "label": "Compute and Energy Consumption Trends in Deep Learning Inference", "url": "https://arxiv.org/abs/2109.05472", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2021-09-12"}
{"type": "node", "id": "author:radosvet_desislavov", "kind": "person", "label": "Radosvet Desislavov", "url": "https://arxiv.org/a/radosvet_desislavov", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:fernando_mart_nez_plumed", "kind": "person", "label": "Fernando Mart\u00ednez-Plumed", "url": "https://arxiv.org/a/fernando_mart_nez_plumed", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jos_hern_ndez_orallo", "kind": "person", "label": "Jos\u00e9 Hern\u00e1ndez-Orallo", "url": "https://arxiv.org/a/jos_hern_ndez_orallo", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2107.02926", "kind": "paper", "label": "Solution of Physics-based Bayesian Inverse Problems with Deep Generative Priors", "url": "https://arxiv.org/abs/2107.02926", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2021-07-06"}
{"type": "node", "id": "author:dhruv_v_patel", "kind": "person", "label": "Dhruv V Patel", "url": "https://arxiv.org/a/dhruv_v_patel", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2011.03712", "kind": "paper", "label": "DeepCFL: Deep Contextual Features Learning from a Single Image", "url": "https://arxiv.org/abs/2011.03712", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2020-11-07"}
{"type": "node", "id": "paper:2412.03084", "kind": "paper", "label": "Hybrid deep learning-based strategy for the hepatocellular carcinoma cancer grade classification of H&amp;E stained liver histopathology images", "url": "https://arxiv.org/abs/2412.03084", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2024-12-04"}
{"type": "node", "id": "author:ajinkya_deshpande", "kind": "person", "label": "Ajinkya Deshpande", "url": "https://arxiv.org/a/ajinkya_deshpande", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:deep_gupta", "kind": "person", "label": "Deep Gupta", "url": "https://arxiv.org/a/deep_gupta", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:ankit_bhurane", "kind": "person", "label": "Ankit Bhurane", "url": "https://arxiv.org/a/ankit_bhurane", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:nisha_meshram", "kind": "person", "label": "Nisha Meshram", "url": "https://arxiv.org/a/nisha_meshram", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:sneha_singh", "kind": "person", "label": "Sneha Singh", "url": "https://arxiv.org/a/sneha_singh", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2603.28944", "kind": "paper", "label": "Faith in AI can narrow the futures individuals consider", "url": "https://arxiv.org/abs/2603.28944", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2026-03-30"}
{"type": "node", "id": "author:aoi_naito", "kind": "person", "label": "Aoi Naito", "url": "https://arxiv.org/a/aoi_naito", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:hirokazu_shirado", "kind": "person", "label": "Hirokazu Shirado", "url": "https://arxiv.org/a/hirokazu_shirado", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2501.02842", "kind": "paper", "label": "Foundations of GenIR", "url": "https://arxiv.org/abs/2501.02842", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2025-01-06"}
{"type": "node", "id": "author:qingyao_ai", "kind": "person", "label": "Qingyao Ai", "url": "https://arxiv.org/a/qingyao_ai", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jingtao_zhan", "kind": "person", "label": "Jingtao Zhan", "url": "https://arxiv.org/a/jingtao_zhan", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yiqun_liu", "kind": "person", "label": "Yiqun Liu", "url": "https://arxiv.org/a/yiqun_liu", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2601.16513", "kind": "paper", "label": "Competing Visions of Ethical AI: A Case Study of OpenAI", "url": "https://arxiv.org/abs/2601.16513", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2026-01-23"}
{"type": "node", "id": "author:melissa_wilfley", "kind": "person", "label": "Melissa Wilfley", "url": "https://arxiv.org/a/melissa_wilfley", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:madelyn_rose_sanfilippo", "kind": "person", "label": "Madelyn Rose Sanfilippo", "url": "https://arxiv.org/a/madelyn_rose_sanfilippo", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2509.19996", "kind": "paper", "label": "Choosing to Be Green: Advancing Green AI via Dynamic Model Selection", "url": "https://arxiv.org/abs/2509.19996", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2025-09-24"}
{"type": "node", "id": "author:emilio_cruciani", "kind": "person", "label": "Emilio Cruciani", "url": "https://arxiv.org/a/emilio_cruciani", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:roberto_verdecchia", "kind": "person", "label": "Roberto Verdecchia", "url": "https://arxiv.org/a/roberto_verdecchia", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2205.01128", "kind": "paper", "label": "Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems", "url": "https://arxiv.org/abs/2205.01128", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2022-05-02"}
{"type": "node", "id": "author:paul_smolensky", "kind": "person", "label": "Paul Smolensky", "url": "https://arxiv.org/a/paul_smolensky", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:r_thomas_mccoy", "kind": "person", "label": "R. Thomas McCoy", "url": "https://arxiv.org/a/r_thomas_mccoy", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:roland_fernandez", "kind": "person", "label": "Roland Fernandez", "url": "https://arxiv.org/a/roland_fernandez", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:matthew_goldrick", "kind": "person", "label": "Matthew Goldrick", "url": "https://arxiv.org/a/matthew_goldrick", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jianfeng_gao", "kind": "person", "label": "Jianfeng Gao", "url": "https://arxiv.org/a/jianfeng_gao", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2501.14776", "kind": "paper", "label": "Green AI: Which Programming Language Consumes the Most?", "url": "https://arxiv.org/abs/2501.14776", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2024-12-31"}
{"type": "node", "id": "author:niccol_marini", "kind": "person", "label": "Niccol\u00f2 Marini", "url": "https://arxiv.org/a/niccol_marini", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:leonardo_pampaloni", "kind": "person", "label": "Leonardo Pampaloni", "url": "https://arxiv.org/a/leonardo_pampaloni", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:filippo_di_martino", "kind": "person", "label": "Filippo Di Martino", "url": "https://arxiv.org/a/filippo_di_martino", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:enrico_vicario", "kind": "person", "label": "Enrico Vicario", "url": "https://arxiv.org/a/enrico_vicario", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2512.20902", "kind": "paper", "label": "Embodied AI-Enhanced IoMT Edge Computing: UAV Trajectory Optimization and Task Offloading with Mobility Prediction", "url": "https://arxiv.org/abs/2512.20902", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2025-12-24"}
{"type": "node", "id": "author:siqi_mu", "kind": "person", "label": "Siqi Mu", "url": "https://arxiv.org/a/siqi_mu", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:shuo_wen", "kind": "person", "label": "Shuo Wen", "url": "https://arxiv.org/a/shuo_wen", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yang_lu", "kind": "person", "label": "Yang Lu", "url": "https://arxiv.org/a/yang_lu", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:ruihong_jiang", "kind": "person", "label": "Ruihong Jiang", "url": "https://arxiv.org/a/ruihong_jiang", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:bo_ai", "kind": "person", "label": "Bo Ai", "url": "https://arxiv.org/a/bo_ai", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2308.12400", "kind": "paper", "label": "Towards The Ultimate Brain: Exploring Scientific Discovery with ChatGPT AI", "url": "https://arxiv.org/abs/2308.12400", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2023-07-08"}
{"type": "node", "id": "author:gerardo_adesso", "kind": "person", "label": "Gerardo Adesso", "url": "https://arxiv.org/a/gerardo_adesso", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2407.10237", "kind": "paper", "label": "Towards Green AI: Current status and future research", "url": "https://arxiv.org/abs/2407.10237", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2024-05-01"}
{"type": "node", "id": "author:christian_clemm", "kind": "person", "label": "Christian Clemm", "url": "https://arxiv.org/a/christian_clemm", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:lutz_stobbe", "kind": "person", "label": "Lutz Stobbe", "url": "https://arxiv.org/a/lutz_stobbe", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:kishan_wimalawarne", "kind": "person", "label": "Kishan Wimalawarne", "url": "https://arxiv.org/a/kishan_wimalawarne", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jan_druschke", "kind": "person", "label": "Jan Druschke", "url": "https://arxiv.org/a/jan_druschke", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2112.01298", "kind": "paper", "label": "Meaningful human control: actionable properties for AI system development", "url": "https://arxiv.org/abs/2112.01298", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2021-11-25"}
{"type": "node", "id": "author:luciano_cavalcante_siebert", "kind": "person", "label": "Luciano Cavalcante Siebert", "url": "https://arxiv.org/a/luciano_cavalcante_siebert", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:maria_luce_lupetti", "kind": "person", "label": "Maria Luce Lupetti", "url": "https://arxiv.org/a/maria_luce_lupetti", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:evgeni_aizenberg", "kind": "person", "label": "Evgeni Aizenberg", "url": "https://arxiv.org/a/evgeni_aizenberg", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:niek_beckers", "kind": "person", "label": "Niek Beckers", "url": "https://arxiv.org/a/niek_beckers", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:arkady_zgonnikov", "kind": "person", "label": "Arkady Zgonnikov", "url": "https://arxiv.org/a/arkady_zgonnikov", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2607.04282", "kind": "paper", "label": "The New Shape of Search: How Conversational AI Recomposes Information Seeking", "url": "https://arxiv.org/abs/2607.04282", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2026-07-05"}
{"type": "node", "id": "author:michael_iannelli", "kind": "person", "label": "Michael Iannelli", "url": "https://arxiv.org/a/michael_iannelli", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:alan_ai", "kind": "person", "label": "Alan Ai", "url": "https://arxiv.org/a/alan_ai", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2408.00025", "kind": "paper", "label": "Need of AI in Modern Education: in the Eyes of Explainable AI (xAI)", "url": "https://arxiv.org/abs/2408.00025", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2024-07-31"}
{"type": "node", "id": "author:supriya_manna", "kind": "person", "label": "Supriya Manna", "url": "https://arxiv.org/a/supriya_manna", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:niladri_sett", "kind": "person", "label": "Niladri Sett", "url": "https://arxiv.org/a/niladri_sett", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2401.15284", "kind": "paper", "label": "Beyond principlism: Practical strategies for ethical AI use in research practices", "url": "https://arxiv.org/abs/2401.15284", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2024-01-27"}
{"type": "node", "id": "author:zhicheng_lin", "kind": "person", "label": "Zhicheng Lin", "url": "https://arxiv.org/a/zhicheng_lin", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2504.16770", "kind": "paper", "label": "DeBiasMe: De-biasing Human-AI Interactions with Metacognitive AIED (AI in Education) Interventions", "url": "https://arxiv.org/abs/2504.16770", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2025-04-23"}
{"type": "node", "id": "author:chaeyeon_lim", "kind": "person", "label": "Chaeyeon Lim", "url": "https://arxiv.org/a/chaeyeon_lim", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2504.08817", "kind": "paper", "label": "Exploring utilization of generative AI for research and education in data-driven materials science", "url": "https://arxiv.org/abs/2504.08817", "source": "arxiv", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "published": "2025-04-09"}
{"type": "node", "id": "author:takahiro_misawa", "kind": "person", "label": "Takahiro Misawa", "url": "https://arxiv.org/a/takahiro_misawa", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:ai_koizumi", "kind": "person", "label": "Ai Koizumi", "url": "https://arxiv.org/a/ai_koizumi", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:ryo_tamura", "kind": "person", "label": "Ryo Tamura", "url": "https://arxiv.org/a/ryo_tamura", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:kazuyoshi_yoshimi", "kind": "person", "label": "Kazuyoshi Yoshimi", "url": "https://arxiv.org/a/kazuyoshi_yoshimi", "source": "arxiv-author", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2606.15897", "kind": "paper", "label": "Topological Flow Matching", "url": "https://arxiv.org/abs/2606.15897", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2026-06-14"}
{"type": "node", "id": "author:kacper_wyrwal", "kind": "person", "label": "Kacper Wyrwal", "url": "https://arxiv.org/a/kacper_wyrwal", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:i_smail_i_lkan_ceylan", "kind": "person", "label": "\u0130smail \u0130lkan Ceylan", "url": "https://arxiv.org/a/i_smail_i_lkan_ceylan", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:alexander_tong", "kind": "person", "label": "Alexander Tong", "url": "https://arxiv.org/a/alexander_tong", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2307.03672", "kind": "paper", "label": "Simulation-free Schr\u00f6dinger bridges via score and flow matching", "url": "https://arxiv.org/abs/2307.03672", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2023-07-07"}
{"type": "node", "id": "author:nikolay_malkin", "kind": "person", "label": "Nikolay Malkin", "url": "https://arxiv.org/a/nikolay_malkin", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:kilian_fatras", "kind": "person", "label": "Kilian Fatras", "url": "https://arxiv.org/a/kilian_fatras", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:lazar_atanackovic", "kind": "person", "label": "Lazar Atanackovic", "url": "https://arxiv.org/a/lazar_atanackovic", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:yanlei_zhang", "kind": "person", "label": "Yanlei Zhang", "url": "https://arxiv.org/a/yanlei_zhang", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2305.17161", "kind": "paper", "label": "Flow Matching for Scalable Simulation-Based Inference", "url": "https://arxiv.org/abs/2305.17161", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2023-05-26"}
{"type": "node", "id": "author:maximilian_dax", "kind": "person", "label": "Maximilian Dax", "url": "https://arxiv.org/a/maximilian_dax", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:jonas_wildberger", "kind": "person", "label": "Jonas Wildberger", "url": "https://arxiv.org/a/jonas_wildberger", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:simon_buchholz", "kind": "person", "label": "Simon Buchholz", "url": "https://arxiv.org/a/simon_buchholz", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:stephen_r_green", "kind": "person", "label": "Stephen R. Green", "url": "https://arxiv.org/a/stephen_r_green", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:jakob_h_macke", "kind": "person", "label": "Jakob H. Macke", "url": "https://arxiv.org/a/jakob_h_macke", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2504.17872", "kind": "paper", "label": "Flow Matching Ergodic Coverage", "url": "https://arxiv.org/abs/2504.17872", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2025-04-24"}
{"type": "node", "id": "author:max_muchen_sun", "kind": "person", "label": "Max Muchen Sun", "url": "https://arxiv.org/a/max_muchen_sun", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:allison_pinosky", "kind": "person", "label": "Allison Pinosky", "url": "https://arxiv.org/a/allison_pinosky", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:todd_murphey", "kind": "person", "label": "Todd Murphey", "url": "https://arxiv.org/a/todd_murphey", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2605.16239", "kind": "paper", "label": "Dynamics-Level Watermarking of Flow Matching Models with Random Codes", "url": "https://arxiv.org/abs/2605.16239", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2026-05-15"}
{"type": "node", "id": "author:shuchan_wang", "kind": "person", "label": "Shuchan Wang", "url": "https://arxiv.org/a/shuchan_wang", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2502.17119", "kind": "paper", "label": "Diffusion and Flow Matching Models for Tabular Data: A Survey", "url": "https://arxiv.org/abs/2502.17119", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2025-02-24"}
{"type": "node", "id": "author:zhong_li", "kind": "person", "label": "Zhong Li", "url": "https://arxiv.org/a/zhong_li", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:qi_huang", "kind": "person", "label": "Qi Huang", "url": "https://arxiv.org/a/qi_huang", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:lincen_yang", "kind": "person", "label": "Lincen Yang", "url": "https://arxiv.org/a/lincen_yang", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:jiayang_shi", "kind": "person", "label": "Jiayang Shi", "url": "https://arxiv.org/a/jiayang_shi", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:zhao_yang", "kind": "person", "label": "Zhao Yang", "url": "https://arxiv.org/a/zhao_yang", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:1903.01434", "kind": "paper", "label": "VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation", "url": "https://arxiv.org/abs/1903.01434", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2019-03-04"}
{"type": "node", "id": "author:manoj_kumar", "kind": "person", "label": "Manoj Kumar", "url": "https://arxiv.org/a/manoj_kumar", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:mohammad_babaeizadeh", "kind": "person", "label": "Mohammad Babaeizadeh", "url": "https://arxiv.org/a/mohammad_babaeizadeh", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:dumitru_erhan", "kind": "person", "label": "Dumitru Erhan", "url": "https://arxiv.org/a/dumitru_erhan", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:chelsea_finn", "kind": "person", "label": "Chelsea Finn", "url": "https://arxiv.org/a/chelsea_finn", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:sergey_levine", "kind": "person", "label": "Sergey Levine", "url": "https://arxiv.org/a/sergey_levine", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2110.02266", "kind": "paper", "label": "Time-averaged velocity and scalar fields of the flow surrounding a group of cylinders", "url": "https://arxiv.org/abs/2110.02266", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2021-10-05"}
{"type": "node", "id": "author:dea_daniella_wangsawijaya", "kind": "person", "label": "Dea Daniella Wangsawijaya", "url": "https://arxiv.org/a/dea_daniella_wangsawijaya", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:claudia_nicolai", "kind": "person", "label": "Claudia Nicolai", "url": "https://arxiv.org/a/claudia_nicolai", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:bharathram_ganapathisubramani", "kind": "person", "label": "Bharathram Ganapathisubramani", "url": "https://arxiv.org/a/bharathram_ganapathisubramani", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2512.06112", "kind": "paper", "label": "WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving", "url": "https://arxiv.org/abs/2512.06112", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2025-12-05"}
{"type": "node", "id": "author:yifang_xu", "kind": "person", "label": "Yifang Xu", "url": "https://arxiv.org/a/yifang_xu", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:jiahao_cui", "kind": "person", "label": "Jiahao Cui", "url": "https://arxiv.org/a/jiahao_cui", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:feipeng_cai", "kind": "person", "label": "Feipeng Cai", "url": "https://arxiv.org/a/feipeng_cai", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:zhihao_zhu", "kind": "person", "label": "Zhihao Zhu", "url": "https://arxiv.org/a/zhihao_zhu", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:hanlin_shang", "kind": "person", "label": "Hanlin Shang", "url": "https://arxiv.org/a/hanlin_shang", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2302.00482", "kind": "paper", "label": "Improving and generalizing flow-based generative models with minibatch optimal transport", "url": "https://arxiv.org/abs/2302.00482", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2023-02-01"}
{"type": "node", "id": "author:guillaume_huguet", "kind": "person", "label": "Guillaume Huguet", "url": "https://arxiv.org/a/guillaume_huguet", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2605.08063", "kind": "paper", "label": "Flow-OPD: On-Policy Distillation for Flow Matching Models", "url": "https://arxiv.org/abs/2605.08063", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2026-05-08"}
{"type": "node", "id": "author:zhen_fang", "kind": "person", "label": "Zhen Fang", "url": "https://arxiv.org/a/zhen_fang", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:wenxuan_huang", "kind": "person", "label": "Wenxuan Huang", "url": "https://arxiv.org/a/wenxuan_huang", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:yu_zeng", "kind": "person", "label": "Yu Zeng", "url": "https://arxiv.org/a/yu_zeng", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:yiming_zhao", "kind": "person", "label": "Yiming Zhao", "url": "https://arxiv.org/a/yiming_zhao", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:shuang_chen", "kind": "person", "label": "Shuang Chen", "url": "https://arxiv.org/a/shuang_chen", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:1403.4969", "kind": "paper", "label": "Crowd Flow Modeling of Athletes in Mass Sports Events -- a Macroscopic Approach", "url": "https://arxiv.org/abs/1403.4969", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2014-03-19"}
{"type": "node", "id": "author:martin_treiber", "kind": "person", "label": "Martin Treiber", "url": "https://arxiv.org/a/martin_treiber", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:1902.07351", "kind": "paper", "label": "Phase-field simulation of core-annular pipe flow", "url": "https://arxiv.org/abs/1902.07351", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2019-02-19"}
{"type": "node", "id": "author:baofang_song", "kind": "person", "label": "Baofang Song", "url": "https://arxiv.org/a/baofang_song", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:carlos_plana", "kind": "person", "label": "Carlos Plana", "url": "https://arxiv.org/a/carlos_plana", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:jose_m_lopez", "kind": "person", "label": "Jose M. Lopez", "url": "https://arxiv.org/a/jose_m_lopez", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:marc_avila", "kind": "person", "label": "Marc Avila", "url": "https://arxiv.org/a/marc_avila", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2506.06952", "kind": "paper", "label": "LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer", "url": "https://arxiv.org/abs/2506.06952", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2025-06-08"}
{"type": "node", "id": "author:ying_shen", "kind": "person", "label": "Ying Shen", "url": "https://arxiv.org/a/ying_shen", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:zhiyang_xu", "kind": "person", "label": "Zhiyang Xu", "url": "https://arxiv.org/a/zhiyang_xu", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:jiuhai_chen", "kind": "person", "label": "Jiuhai Chen", "url": "https://arxiv.org/a/jiuhai_chen", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:shizhe_diao", "kind": "person", "label": "Shizhe Diao", "url": "https://arxiv.org/a/shizhe_diao", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:jiaxin_zhang", "kind": "person", "label": "Jiaxin Zhang", "url": "https://arxiv.org/a/jiaxin_zhang", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:1908.03540", "kind": "paper", "label": "Enriching MRI mean flow data of inclined jets in crossflow with Large Eddy Simulations", "url": "https://arxiv.org/abs/1908.03540", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2019-08-09"}
{"type": "node", "id": "author:pedro_m_milani", "kind": "person", "label": "Pedro M. Milani", "url": "https://arxiv.org/a/pedro_m_milani", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:ian_e_gunady", "kind": "person", "label": "Ian E. Gunady", "url": "https://arxiv.org/a/ian_e_gunady", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:david_s_ching", "kind": "person", "label": "David S. Ching", "url": "https://arxiv.org/a/david_s_ching", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:andrew_j_banko", "kind": "person", "label": "Andrew J. Banko", "url": "https://arxiv.org/a/andrew_j_banko", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:christopher_j_elkins", "kind": "person", "label": "Christopher J. Elkins", "url": "https://arxiv.org/a/christopher_j_elkins", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2506.05282", "kind": "paper", "label": "Rectified Point Flow: Generic Point Cloud Pose Estimation", "url": "https://arxiv.org/abs/2506.05282", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2025-06-05"}
{"type": "node", "id": "author:tao_sun", "kind": "person", "label": "Tao Sun", "url": "https://arxiv.org/a/tao_sun", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:liyuan_zhu", "kind": "person", "label": "Liyuan Zhu", "url": "https://arxiv.org/a/liyuan_zhu", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:shengyu_huang", "kind": "person", "label": "Shengyu Huang", "url": "https://arxiv.org/a/shengyu_huang", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:shuran_song", "kind": "person", "label": "Shuran Song", "url": "https://arxiv.org/a/shuran_song", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:iro_armeni", "kind": "person", "label": "Iro Armeni", "url": "https://arxiv.org/a/iro_armeni", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2511.19835", "kind": "paper", "label": "Rectified SpaAttn: Revisiting Attention Sparsity for Efficient Video Generation", "url": "https://arxiv.org/abs/2511.19835", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2025-11-25"}
{"type": "node", "id": "author:xuewen_liu", "kind": "person", "label": "Xuewen Liu", "url": "https://arxiv.org/a/xuewen_liu", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:zhikai_li", "kind": "person", "label": "Zhikai Li", "url": "https://arxiv.org/a/zhikai_li", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:jing_zhang", "kind": "person", "label": "Jing Zhang", "url": "https://arxiv.org/a/jing_zhang", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:mengjuan_chen", "kind": "person", "label": "Mengjuan Chen", "url": "https://arxiv.org/a/mengjuan_chen", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:qingyi_gu", "kind": "person", "label": "Qingyi Gu", "url": "https://arxiv.org/a/qingyi_gu", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2207.02679", "kind": "paper", "label": "Experimental study of cavitating flow influenced by heat transfer from heated hydrofoil", "url": "https://arxiv.org/abs/2207.02679", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2022-07-01"}
{"type": "node", "id": "author:junnosuke_okajima", "kind": "person", "label": "Junnosuke Okajima", "url": "https://arxiv.org/a/junnosuke_okajima", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:masaki_ito", "kind": "person", "label": "Masaki Ito", "url": "https://arxiv.org/a/masaki_ito", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:yuka_iga", "kind": "person", "label": "Yuka Iga", "url": "https://arxiv.org/a/yuka_iga", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:1205.3624", "kind": "paper", "label": "DNS of vertical plane channel flow with finite-size particles: Voronoi analysis, acceleration statistics and particle-conditioned averaging", "url": "https://arxiv.org/abs/1205.3624", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2012-05-16"}
{"type": "node", "id": "author:manuel_garcia_villalba", "kind": "person", "label": "Manuel Garcia-Villalba", "url": "https://arxiv.org/a/manuel_garcia_villalba", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:aman_g_kidanemariam", "kind": "person", "label": "Aman G. Kidanemariam", "url": "https://arxiv.org/a/aman_g_kidanemariam", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:markus_uhlmann", "kind": "person", "label": "Markus Uhlmann", "url": "https://arxiv.org/a/markus_uhlmann", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2512.24757", "kind": "paper", "label": "Generalization Capability of Deep Learning for Predicting Drag Reduction in Pulsating Turbulent Pipe Flow with Arbitrary Acceleration and Deceleration", "url": "https://arxiv.org/abs/2512.24757", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2025-12-31"}
{"type": "node", "id": "author:sota_kumazawa", "kind": "person", "label": "Sota Kumazawa", "url": "https://arxiv.org/a/sota_kumazawa", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:yasuhiro_yoshida", "kind": "person", "label": "Yasuhiro Yoshida", "url": "https://arxiv.org/a/yasuhiro_yoshida", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:tomohiro_nimura", "kind": "person", "label": "Tomohiro Nimura", "url": "https://arxiv.org/a/tomohiro_nimura", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:akira_murata", "kind": "person", "label": "Akira Murata", "url": "https://arxiv.org/a/akira_murata", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:kaoru_iwamoto", "kind": "person", "label": "Kaoru Iwamoto", "url": "https://arxiv.org/a/kaoru_iwamoto", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2009.01541", "kind": "paper", "label": "Sediment transport under oscillatory flows", "url": "https://arxiv.org/abs/2009.01541", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2020-09-03"}
{"type": "node", "id": "author:giovanna_vittori", "kind": "person", "label": "Giovanna Vittori", "url": "https://arxiv.org/a/giovanna_vittori", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:paolo_blondeaux", "kind": "person", "label": "Paolo Blondeaux", "url": "https://arxiv.org/a/paolo_blondeaux", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:marco_mazzuoli", "kind": "person", "label": "Marco Mazzuoli", "url": "https://arxiv.org/a/marco_mazzuoli", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:julian_simeonov", "kind": "person", "label": "Julian Simeonov", "url": "https://arxiv.org/a/julian_simeonov", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:joseph_calantoni", "kind": "person", "label": "Joseph Calantoni", "url": "https://arxiv.org/a/joseph_calantoni", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:1408.6107", "kind": "paper", "label": "Experimental Analysis of Two-Dimensional Pedestrian Flow in front of the Bottleneck", "url": "https://arxiv.org/abs/1408.6107", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2014-08-26"}
{"type": "node", "id": "author:marek_buk_ek", "kind": "person", "label": "Marek Buk\u00e1\u010dek", "url": "https://arxiv.org/a/marek_buk_ek", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:pavel_hrab_k", "kind": "person", "label": "Pavel Hrab\u00e1k", "url": "https://arxiv.org/a/pavel_hrab_k", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:milan_krb_lek", "kind": "person", "label": "Milan Krb\u00e1lek", "url": "https://arxiv.org/a/milan_krb_lek", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2209.03003", "kind": "paper", "label": "Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow", "url": "https://arxiv.org/abs/2209.03003", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2022-09-07"}
{"type": "node", "id": "author:xingchao_liu", "kind": "person", "label": "Xingchao Liu", "url": "https://arxiv.org/a/xingchao_liu", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:chengyue_gong", "kind": "person", "label": "Chengyue Gong", "url": "https://arxiv.org/a/chengyue_gong", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:qiang_liu", "kind": "person", "label": "Qiang Liu", "url": "https://arxiv.org/a/qiang_liu", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2403.16995", "kind": "paper", "label": "Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows", "url": "https://arxiv.org/abs/2403.16995", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2024-03-25"}
{"type": "node", "id": "author:shujian_zhang", "kind": "person", "label": "Shujian Zhang", "url": "https://arxiv.org/a/shujian_zhang", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:lemeng_wu", "kind": "person", "label": "Lemeng Wu", "url": "https://arxiv.org/a/lemeng_wu", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2405.20320", "kind": "paper", "label": "Improving the Training of Rectified Flows", "url": "https://arxiv.org/abs/2405.20320", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2024-05-30"}
{"type": "node", "id": "author:sangyun_lee", "kind": "person", "label": "Sangyun Lee", "url": "https://arxiv.org/a/sangyun_lee", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:zinan_lin", "kind": "person", "label": "Zinan Lin", "url": "https://arxiv.org/a/zinan_lin", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:giulia_fanti", "kind": "person", "label": "Giulia Fanti", "url": "https://arxiv.org/a/giulia_fanti", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:1804.04562", "kind": "paper", "label": "Relative dispersion of particle pairs in turbulent channel flow", "url": "https://arxiv.org/abs/1804.04562", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2018-04-12"}
{"type": "node", "id": "author:juan_ignacio_polanco", "kind": "person", "label": "Juan Ignacio Polanco", "url": "https://arxiv.org/a/juan_ignacio_polanco", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:ivana_vinkovic", "kind": "person", "label": "Ivana Vinkovic", "url": "https://arxiv.org/a/ivana_vinkovic", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:nickolas_stelzenmuller", "kind": "person", "label": "Nickolas Stelzenmuller", "url": "https://arxiv.org/a/nickolas_stelzenmuller", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:nicolas_mordant", "kind": "person", "label": "Nicolas Mordant", "url": "https://arxiv.org/a/nicolas_mordant", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:micka_l_bourgoin", "kind": "person", "label": "Micka\u00ebl Bourgoin", "url": "https://arxiv.org/a/micka_l_bourgoin", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:1303.0217", "kind": "paper", "label": "A stochastic diffusion process for the Dirichlet distribution", "url": "https://arxiv.org/abs/1303.0217", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2013-03-01"}
{"type": "node", "id": "author:j_bakosi", "kind": "person", "label": "J. Bakosi", "url": "https://arxiv.org/a/j_bakosi", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:j_r_ristorcelli", "kind": "person", "label": "J. R. Ristorcelli", "url": "https://arxiv.org/a/j_r_ristorcelli", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:http://arxi", "kind": "paper", "label": "Stochastic inequalities for single-server loss queueing systems", "url": "https://arxiv.org/abs/http://arxi", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2005-05-04"}
{"type": "node", "id": "author:vyacheslav_m_abramov", "kind": "person", "label": "Vyacheslav M. Abramov", "url": "https://arxiv.org/a/vyacheslav_m_abramov", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2509.26282", "kind": "paper", "label": "Reframing Generative Models for Physical Systems using Stochastic Interpolants", "url": "https://arxiv.org/abs/2509.26282", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2025-09-30"}
{"type": "node", "id": "author:anthony_zhou", "kind": "person", "label": "Anthony Zhou", "url": "https://arxiv.org/a/anthony_zhou", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:alexander_wikner", "kind": "person", "label": "Alexander Wikner", "url": "https://arxiv.org/a/alexander_wikner", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:amaury_lancelin", "kind": "person", "label": "Amaury Lancelin", "url": "https://arxiv.org/a/amaury_lancelin", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:pedram_hassanzadeh", "kind": "person", "label": "Pedram Hassanzadeh", "url": "https://arxiv.org/a/pedram_hassanzadeh", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:amir_barati_farimani", "kind": "person", "label": "Amir Barati Farimani", "url": "https://arxiv.org/a/amir_barati_farimani", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:1602.00257", "kind": "paper", "label": "Stochastic PDEs with heavy-tailed noise", "url": "https://arxiv.org/abs/1602.00257", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2016-01-31"}
{"type": "node", "id": "author:carsten_chong", "kind": "person", "label": "Carsten Chong", "url": "https://arxiv.org/a/carsten_chong", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:1110.3250", "kind": "paper", "label": "On a stochastic differential equation arising in a price impact model", "url": "https://arxiv.org/abs/1110.3250", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2011-10-14"}
{"type": "node", "id": "author:peter_bank", "kind": "person", "label": "Peter Bank", "url": "https://arxiv.org/a/peter_bank", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:dmitry_kramkov", "kind": "person", "label": "Dmitry Kramkov", "url": "https://arxiv.org/a/dmitry_kramkov", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:1810.10520", "kind": "paper", "label": "Stochastic temporal data upscaling using the generalized k-nearest neighbor algorithm", "url": "https://arxiv.org/abs/1810.10520", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2018-10-19"}
{"type": "node", "id": "author:john_mashford", "kind": "person", "label": "John Mashford", "url": "https://arxiv.org/a/john_mashford", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:jan_pospisil", "kind": "person", "label": "Jan Pospisil", "url": "https://arxiv.org/a/jan_pospisil", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:roger_tribe", "kind": "person", "label": "Roger Tribe", "url": "https://arxiv.org/a/roger_tribe", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2504.05852", "kind": "paper", "label": "Physics-aware generative models for turbulent fluid flows through energy-consistent stochastic interpolants", "url": "https://arxiv.org/abs/2504.05852", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2025-04-08"}
{"type": "node", "id": "author:nikolaj_t_m_cke", "kind": "person", "label": "Nikolaj T. M\u00fccke", "url": "https://arxiv.org/a/nikolaj_t_m_cke", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:benjamin_sanderse", "kind": "person", "label": "Benjamin Sanderse", "url": "https://arxiv.org/a/benjamin_sanderse", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2508.07333", "kind": "paper", "label": "Finite-Time Convergence Analysis of ODE-based Generative Models for Stochastic Interpolants", "url": "https://arxiv.org/abs/2508.07333", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2025-08-10"}
{"type": "node", "id": "author:yuhao_liu", "kind": "person", "label": "Yuhao Liu", "url": "https://arxiv.org/a/yuhao_liu", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:rui_hu", "kind": "person", "label": "Rui Hu", "url": "https://arxiv.org/a/rui_hu", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:yu_chen", "kind": "person", "label": "Yu Chen", "url": "https://arxiv.org/a/yu_chen", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:longbo_huang", "kind": "person", "label": "Longbo Huang", "url": "https://arxiv.org/a/longbo_huang", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2006.04939", "kind": "paper", "label": "Stochastic solutions of Stefan problems", "url": "https://arxiv.org/abs/2006.04939", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2020-06-05"}
{"type": "node", "id": "author:m_ogren", "kind": "person", "label": "M. Ogren", "url": "https://arxiv.org/a/m_ogren", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2602.20070", "kind": "paper", "label": "Generative Modeling via Kernelized Stochastic Interpolants", "url": "https://arxiv.org/abs/2602.20070", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2026-02-23"}
{"type": "node", "id": "author:florentin_coeurdoux", "kind": "person", "label": "Florentin Coeurdoux", "url": "https://arxiv.org/a/florentin_coeurdoux", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:etienne_lempereur", "kind": "person", "label": "Etienne Lempereur", "url": "https://arxiv.org/a/etienne_lempereur", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:nathana_l_cuvelle_magar", "kind": "person", "label": "Nathana\u00ebl Cuvelle-Magar", "url": "https://arxiv.org/a/nathana_l_cuvelle_magar", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:st_phane_mallat", "kind": "person", "label": "St\u00e9phane Mallat", "url": "https://arxiv.org/a/st_phane_mallat", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:eric_vanden_eijnden", "kind": "person", "label": "Eric Vanden-Eijnden", "url": "https://arxiv.org/a/eric_vanden_eijnden", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2508.13770", "kind": "paper", "label": "Generative Super-Resolution of Turbulent Flows via Stochastic Interpolants", "url": "https://arxiv.org/abs/2508.13770", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2025-08-19"}
{"type": "node", "id": "author:martin_schi_dt", "kind": "person", "label": "Martin Schi\u00f8dt", "url": "https://arxiv.org/a/martin_schi_dt", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:nikolaj_takata_m_cke", "kind": "person", "label": "Nikolaj Takata M\u00fccke", "url": "https://arxiv.org/a/nikolaj_takata_m_cke", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:clara_marika_velte", "kind": "person", "label": "Clara Marika Velte", "url": "https://arxiv.org/a/clara_marika_velte", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2009.09171", "kind": "paper", "label": "Stochastic Threshold Model Trees: A Tree-Based Ensemble Method for Dealing with Extrapolation", "url": "https://arxiv.org/abs/2009.09171", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2020-09-19"}
{"type": "node", "id": "author:kohei_numata", "kind": "person", "label": "Kohei Numata", "url": "https://arxiv.org/a/kohei_numata", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:kenichi_tanaka", "kind": "person", "label": "Kenichi Tanaka", "url": "https://arxiv.org/a/kenichi_tanaka", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2007.02736", "kind": "paper", "label": "Living Without Beth and Craig: Definitions and Interpolants in Description and Modal Logics with Nominals and Role Inclusions", "url": "https://arxiv.org/abs/2007.02736", "source": "arxiv", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "published": "2020-07-06"}
{"type": "node", "id": "author:alessandro_artale", "kind": "person", "label": "Alessandro Artale", "url": "https://arxiv.org/a/alessandro_artale", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:jean_christoph_jung", "kind": "person", "label": "Jean Christoph Jung", "url": "https://arxiv.org/a/jean_christoph_jung", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:andrea_mazzullo", "kind": "person", "label": "Andrea Mazzullo", "url": "https://arxiv.org/a/andrea_mazzullo", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:ana_ozaki", "kind": "person", "label": "Ana Ozaki", "url": "https://arxiv.org/a/ana_ozaki", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "author:frank_wolter", "kind": "person", "label": "Frank Wolter", "url": "https://arxiv.org/a/frank_wolter", "source": "arxiv-author", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "paper:2203.08195", "kind": "paper", "label": "DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection", "url": "https://arxiv.org/abs/2203.08195", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2022-03-15"}
{"type": "node", "id": "author:yingwei_li", "kind": "person", "label": "Yingwei Li", "url": "https://arxiv.org/a/yingwei_li", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:adams_wei_yu", "kind": "person", "label": "Adams Wei Yu", "url": "https://arxiv.org/a/adams_wei_yu", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:tianjian_meng", "kind": "person", "label": "Tianjian Meng", "url": "https://arxiv.org/a/tianjian_meng", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:ben_caine", "kind": "person", "label": "Ben Caine", "url": "https://arxiv.org/a/ben_caine", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:jiquan_ngiam", "kind": "person", "label": "Jiquan Ngiam", "url": "https://arxiv.org/a/jiquan_ngiam", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2411.05292", "kind": "paper", "label": "SimpleBEV: Improved LiDAR-Camera Fusion Architecture for 3D Object Detection", "url": "https://arxiv.org/abs/2411.05292", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2024-11-08"}
{"type": "node", "id": "author:yun_zhao", "kind": "person", "label": "Yun Zhao", "url": "https://arxiv.org/a/yun_zhao", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:zhan_gong", "kind": "person", "label": "Zhan Gong", "url": "https://arxiv.org/a/zhan_gong", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:peiru_zheng", "kind": "person", "label": "Peiru Zheng", "url": "https://arxiv.org/a/peiru_zheng", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:hong_zhu", "kind": "person", "label": "Hong Zhu", "url": "https://arxiv.org/a/hong_zhu", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:shaohua_wu", "kind": "person", "label": "Shaohua Wu", "url": "https://arxiv.org/a/shaohua_wu", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2206.07705", "kind": "paper", "label": "LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection", "url": "https://arxiv.org/abs/2206.07705", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2022-06-15"}
{"type": "node", "id": "author:wei_chih_hung", "kind": "person", "label": "Wei-Chih Hung", "url": "https://arxiv.org/a/wei_chih_hung", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:vincent_casser", "kind": "person", "label": "Vincent Casser", "url": "https://arxiv.org/a/vincent_casser", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:henrik_kretzschmar", "kind": "person", "label": "Henrik Kretzschmar", "url": "https://arxiv.org/a/henrik_kretzschmar", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:jyh_jing_hwang", "kind": "person", "label": "Jyh-Jing Hwang", "url": "https://arxiv.org/a/jyh_jing_hwang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:dragomir_anguelov", "kind": "person", "label": "Dragomir Anguelov", "url": "https://arxiv.org/a/dragomir_anguelov", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2406.19048", "kind": "paper", "label": "BiCo-Fusion: Bidirectional Complementary LiDAR-Camera Fusion for Semantic- and Spatial-Aware 3D Object Detection", "url": "https://arxiv.org/abs/2406.19048", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2024-06-27"}
{"type": "node", "id": "author:lin_wang", "kind": "person", "label": "Lin Wang", "url": "https://arxiv.org/a/lin_wang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2211.13529", "kind": "paper", "label": "3D Dual-Fusion: Dual-Domain Dual-Query Camera-LiDAR Fusion for 3D Object Detection", "url": "https://arxiv.org/abs/2211.13529", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2022-11-24"}
{"type": "node", "id": "author:yecheol_kim", "kind": "person", "label": "Yecheol Kim", "url": "https://arxiv.org/a/yecheol_kim", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:konyul_park", "kind": "person", "label": "Konyul Park", "url": "https://arxiv.org/a/konyul_park", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:minwook_kim", "kind": "person", "label": "Minwook Kim", "url": "https://arxiv.org/a/minwook_kim", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:dongsuk_kum", "kind": "person", "label": "Dongsuk Kum", "url": "https://arxiv.org/a/dongsuk_kum", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:jun_won_choi", "kind": "person", "label": "Jun Won Choi", "url": "https://arxiv.org/a/jun_won_choi", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2004.12636", "kind": "paper", "label": "3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection", "url": "https://arxiv.org/abs/2004.12636", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2020-04-27"}
{"type": "node", "id": "author:jin_hyeok_yoo", "kind": "person", "label": "Jin Hyeok Yoo", "url": "https://arxiv.org/a/jin_hyeok_yoo", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:jisong_kim", "kind": "person", "label": "Jisong Kim", "url": "https://arxiv.org/a/jisong_kim", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2212.04675", "kind": "paper", "label": "SemanticBEVFusion: Rethink LiDAR-Camera Fusion in Unified Bird's-Eye View Representation for 3D Object Detection", "url": "https://arxiv.org/abs/2212.04675", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2022-12-09"}
{"type": "node", "id": "author:qi_jiang", "kind": "person", "label": "Qi Jiang", "url": "https://arxiv.org/a/qi_jiang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:hao_sun", "kind": "person", "label": "Hao Sun", "url": "https://arxiv.org/a/hao_sun", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:xi_zhang", "kind": "person", "label": "Xi Zhang", "url": "https://arxiv.org/a/xi_zhang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2312.14919", "kind": "paper", "label": "Lift-Attend-Splat: Bird's-eye-view camera-lidar fusion using transformers", "url": "https://arxiv.org/abs/2312.14919", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2023-12-22"}
{"type": "node", "id": "author:james_gunn", "kind": "person", "label": "James Gunn", "url": "https://arxiv.org/a/james_gunn", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:zygmunt_lenyk", "kind": "person", "label": "Zygmunt Lenyk", "url": "https://arxiv.org/a/zygmunt_lenyk", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:anuj_sharma", "kind": "person", "label": "Anuj Sharma", "url": "https://arxiv.org/a/anuj_sharma", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:andrea_donati", "kind": "person", "label": "Andrea Donati", "url": "https://arxiv.org/a/andrea_donati", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:alexandru_buburuzan", "kind": "person", "label": "Alexandru Buburuzan", "url": "https://arxiv.org/a/alexandru_buburuzan", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2408.14600", "kind": "paper", "label": "PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection", "url": "https://arxiv.org/abs/2408.14600", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2024-08-26"}
{"type": "node", "id": "author:yidi_li", "kind": "person", "label": "Yidi Li", "url": "https://arxiv.org/a/yidi_li", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:jiahao_wen", "kind": "person", "label": "Jiahao Wen", "url": "https://arxiv.org/a/jiahao_wen", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:bin_ren", "kind": "person", "label": "Bin Ren", "url": "https://arxiv.org/a/bin_ren", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:zhenhuan_xu", "kind": "person", "label": "Zhenhuan Xu", "url": "https://arxiv.org/a/zhenhuan_xu", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2009.12276", "kind": "paper", "label": "SemanticVoxels: Sequential Fusion for 3D Pedestrian Detection using LiDAR Point Cloud and Semantic Segmentation", "url": "https://arxiv.org/abs/2009.12276", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2020-09-25"}
{"type": "node", "id": "author:juncong_fei", "kind": "person", "label": "Juncong Fei", "url": "https://arxiv.org/a/juncong_fei", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:wenbo_chen", "kind": "person", "label": "Wenbo Chen", "url": "https://arxiv.org/a/wenbo_chen", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:philipp_heidenreich", "kind": "person", "label": "Philipp Heidenreich", "url": "https://arxiv.org/a/philipp_heidenreich", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:sascha_wirges", "kind": "person", "label": "Sascha Wirges", "url": "https://arxiv.org/a/sascha_wirges", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:christoph_stiller", "kind": "person", "label": "Christoph Stiller", "url": "https://arxiv.org/a/christoph_stiller", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2502.01856", "kind": "paper", "label": "Reliability-Driven LiDAR-Camera Fusion for Robust 3D Object Detection", "url": "https://arxiv.org/abs/2502.01856", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2025-02-03"}
{"type": "node", "id": "author:reza_sadeghian", "kind": "person", "label": "Reza Sadeghian", "url": "https://arxiv.org/a/reza_sadeghian", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:niloofar_hooshyaripour", "kind": "person", "label": "Niloofar Hooshyaripour", "url": "https://arxiv.org/a/niloofar_hooshyaripour", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:chris_joslin", "kind": "person", "label": "Chris Joslin", "url": "https://arxiv.org/a/chris_joslin", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:wonsook_lee", "kind": "person", "label": "WonSook Lee", "url": "https://arxiv.org/a/wonsook_lee", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2006.09738", "kind": "paper", "label": "LRPD: Long Range 3D Pedestrian Detection Leveraging Specific Strengths of LiDAR and RGB", "url": "https://arxiv.org/abs/2006.09738", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2020-06-17"}
{"type": "node", "id": "author:michael_f_rst", "kind": "person", "label": "Michael F\u00fcrst", "url": "https://arxiv.org/a/michael_f_rst", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:oliver_wasenm_ller", "kind": "person", "label": "Oliver Wasenm\u00fcller", "url": "https://arxiv.org/a/oliver_wasenm_ller", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:didier_stricker", "kind": "person", "label": "Didier Stricker", "url": "https://arxiv.org/a/didier_stricker", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2607.04587", "kind": "paper", "label": "RAF: Reliability-Aware Fusion of Camera, LiDAR, and 4D RADAR for Robust 3D Object Detection in Adverse Weather", "url": "https://arxiv.org/abs/2607.04587", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2026-07-06"}
{"type": "node", "id": "author:heejun_park", "kind": "person", "label": "Heejun Park", "url": "https://arxiv.org/a/heejun_park", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:jaeseok_jeong", "kind": "person", "label": "Jaeseok Jeong", "url": "https://arxiv.org/a/jaeseok_jeong", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:kuk_jin_yoon", "kind": "person", "label": "Kuk-Jin Yoon", "url": "https://arxiv.org/a/kuk_jin_yoon", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2205.14951", "kind": "paper", "label": "Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection", "url": "https://arxiv.org/abs/2205.14951", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2022-05-30"}
{"type": "node", "id": "author:kaicheng_yu", "kind": "person", "label": "Kaicheng Yu", "url": "https://arxiv.org/a/kaicheng_yu", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:tang_tao", "kind": "person", "label": "Tang Tao", "url": "https://arxiv.org/a/tang_tao", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:hongwei_xie", "kind": "person", "label": "Hongwei Xie", "url": "https://arxiv.org/a/hongwei_xie", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:zhiwei_lin", "kind": "person", "label": "Zhiwei Lin", "url": "https://arxiv.org/a/zhiwei_lin", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:zhongwei_wu", "kind": "person", "label": "Zhongwei Wu", "url": "https://arxiv.org/a/zhongwei_wu", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2110.00464", "kind": "paper", "label": "MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentation", "url": "https://arxiv.org/abs/2110.00464", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2021-10-01"}
{"type": "node", "id": "author:jonas_heylen", "kind": "person", "label": "Jonas Heylen", "url": "https://arxiv.org/a/jonas_heylen", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:mark_de_wolf", "kind": "person", "label": "Mark De Wolf", "url": "https://arxiv.org/a/mark_de_wolf", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:bruno_dawagne", "kind": "person", "label": "Bruno Dawagne", "url": "https://arxiv.org/a/bruno_dawagne", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:marc_proesmans", "kind": "person", "label": "Marc Proesmans", "url": "https://arxiv.org/a/marc_proesmans", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:luc_van_gool", "kind": "person", "label": "Luc Van Gool", "url": "https://arxiv.org/a/luc_van_gool", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2409.12034", "kind": "paper", "label": "Multi-Sensor Deep Learning for Glacier Mapping", "url": "https://arxiv.org/abs/2409.12034", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2024-09-18"}
{"type": "node", "id": "author:codru_andrei_diaconu", "kind": "person", "label": "Codru\u0163-Andrei Diaconu", "url": "https://arxiv.org/a/codru_andrei_diaconu", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:konrad_heidler", "kind": "person", "label": "Konrad Heidler", "url": "https://arxiv.org/a/konrad_heidler", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:jonathan_l_bamber", "kind": "person", "label": "Jonathan L. Bamber", "url": "https://arxiv.org/a/jonathan_l_bamber", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:harry_zekollari", "kind": "person", "label": "Harry Zekollari", "url": "https://arxiv.org/a/harry_zekollari", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:1901.10610", "kind": "paper", "label": "Robust Deep Multi-Modal Sensor Fusion using Fusion Weight Regularization and Target Learning", "url": "https://arxiv.org/abs/1901.10610", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2019-01-29"}
{"type": "node", "id": "author:myung_seok_shim", "kind": "person", "label": "Myung Seok Shim", "url": "https://arxiv.org/a/myung_seok_shim", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:chenye_zhao", "kind": "person", "label": "Chenye Zhao", "url": "https://arxiv.org/a/chenye_zhao", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:yang_li", "kind": "person", "label": "Yang Li", "url": "https://arxiv.org/a/yang_li", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:xuchong_zhang", "kind": "person", "label": "Xuchong Zhang", "url": "https://arxiv.org/a/xuchong_zhang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:wenrui_zhang", "kind": "person", "label": "Wenrui Zhang", "url": "https://arxiv.org/a/wenrui_zhang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2005.07431", "kind": "paper", "label": "A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detection", "url": "https://arxiv.org/abs/2005.07431", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2020-05-15"}
{"type": "node", "id": "author:felix_nobis", "kind": "person", "label": "Felix Nobis", "url": "https://arxiv.org/a/felix_nobis", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:maximilian_geisslinger", "kind": "person", "label": "Maximilian Geisslinger", "url": "https://arxiv.org/a/maximilian_geisslinger", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:markus_weber", "kind": "person", "label": "Markus Weber", "url": "https://arxiv.org/a/markus_weber", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:johannes_betz", "kind": "person", "label": "Johannes Betz", "url": "https://arxiv.org/a/johannes_betz", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:markus_lienkamp", "kind": "person", "label": "Markus Lienkamp", "url": "https://arxiv.org/a/markus_lienkamp", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2307.10249", "kind": "paper", "label": "RCM-Fusion: Radar-Camera Multi-Level Fusion for 3D Object Detection", "url": "https://arxiv.org/abs/2307.10249", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2023-07-17"}
{"type": "node", "id": "author:minjae_seong", "kind": "person", "label": "Minjae Seong", "url": "https://arxiv.org/a/minjae_seong", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:geonho_bang", "kind": "person", "label": "Geonho Bang", "url": "https://arxiv.org/a/geonho_bang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2410.19872", "kind": "paper", "label": "Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey", "url": "https://arxiv.org/abs/2410.19872", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2024-10-24"}
{"type": "node", "id": "author:kun_shi", "kind": "person", "label": "Kun Shi", "url": "https://arxiv.org/a/kun_shi", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:shibo_he", "kind": "person", "label": "Shibo He", "url": "https://arxiv.org/a/shibo_he", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:zhenyu_shi", "kind": "person", "label": "Zhenyu Shi", "url": "https://arxiv.org/a/zhenyu_shi", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:anjun_chen", "kind": "person", "label": "Anjun Chen", "url": "https://arxiv.org/a/anjun_chen", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:zehui_xiong", "kind": "person", "label": "Zehui Xiong", "url": "https://arxiv.org/a/zehui_xiong", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2403.16440", "kind": "paper", "label": "RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection", "url": "https://arxiv.org/abs/2403.16440", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2024-03-25"}
{"type": "node", "id": "author:zhe_liu", "kind": "person", "label": "Zhe Liu", "url": "https://arxiv.org/a/zhe_liu", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:zhongyu_xia", "kind": "person", "label": "Zhongyu Xia", "url": "https://arxiv.org/a/zhongyu_xia", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:xinhao_wang", "kind": "person", "label": "Xinhao Wang", "url": "https://arxiv.org/a/xinhao_wang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:yongtao_wang", "kind": "person", "label": "Yongtao Wang", "url": "https://arxiv.org/a/yongtao_wang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2305.00397", "kind": "paper", "label": "TransCAR: Transformer-based Camera-And-Radar Fusion for 3D Object Detection", "url": "https://arxiv.org/abs/2305.00397", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2023-04-30"}
{"type": "node", "id": "author:su_pang", "kind": "person", "label": "Su Pang", "url": "https://arxiv.org/a/su_pang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:daniel_morris", "kind": "person", "label": "Daniel Morris", "url": "https://arxiv.org/a/daniel_morris", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:hayder_radha", "kind": "person", "label": "Hayder Radha", "url": "https://arxiv.org/a/hayder_radha", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2011.04841", "kind": "paper", "label": "CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection", "url": "https://arxiv.org/abs/2011.04841", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2020-11-10"}
{"type": "node", "id": "author:ramin_nabati", "kind": "person", "label": "Ramin Nabati", "url": "https://arxiv.org/a/ramin_nabati", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:hairong_qi", "kind": "person", "label": "Hairong Qi", "url": "https://arxiv.org/a/hairong_qi", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2209.06535", "kind": "paper", "label": "CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer", "url": "https://arxiv.org/abs/2209.06535", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2022-09-14"}
{"type": "node", "id": "author:youngseok_kim", "kind": "person", "label": "Youngseok Kim", "url": "https://arxiv.org/a/youngseok_kim", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:sanmin_kim", "kind": "person", "label": "Sanmin Kim", "url": "https://arxiv.org/a/sanmin_kim", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2102.05150", "kind": "paper", "label": "RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localization", "url": "https://arxiv.org/abs/2102.05150", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2021-02-09"}
{"type": "node", "id": "author:yizhou_wang", "kind": "person", "label": "Yizhou Wang", "url": "https://arxiv.org/a/yizhou_wang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:yudong_li", "kind": "person", "label": "Yudong Li", "url": "https://arxiv.org/a/yudong_li", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:jenq_neng_hwang", "kind": "person", "label": "Jenq-Neng Hwang", "url": "https://arxiv.org/a/jenq_neng_hwang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:guanbin_xing", "kind": "person", "label": "Guanbin Xing", "url": "https://arxiv.org/a/guanbin_xing", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2501.17977", "kind": "paper", "label": "TransRAD: Retentive Vision Transformer for Enhanced Radar Object Detection", "url": "https://arxiv.org/abs/2501.17977", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2025-01-29"}
{"type": "node", "id": "author:lei_cheng", "kind": "person", "label": "Lei Cheng", "url": "https://arxiv.org/a/lei_cheng", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:siyang_cao", "kind": "person", "label": "Siyang Cao", "url": "https://arxiv.org/a/siyang_cao", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2411.10293", "kind": "paper", "label": "RETR: Multi-View Radar Detection Transformer for Indoor Perception", "url": "https://arxiv.org/abs/2411.10293", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2024-11-15"}
{"type": "node", "id": "author:ryoma_yataka", "kind": "person", "label": "Ryoma Yataka", "url": "https://arxiv.org/a/ryoma_yataka", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:adriano_cardace", "kind": "person", "label": "Adriano Cardace", "url": "https://arxiv.org/a/adriano_cardace", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:pu_perry_wang", "kind": "person", "label": "Pu Perry Wang", "url": "https://arxiv.org/a/pu_perry_wang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:petros_boufounos", "kind": "person", "label": "Petros Boufounos", "url": "https://arxiv.org/a/petros_boufounos", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:ryuhei_takahashi", "kind": "person", "label": "Ryuhei Takahashi", "url": "https://arxiv.org/a/ryuhei_takahashi", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2302.10511", "kind": "paper", "label": "MVFusion: Multi-View 3D Object Detection with Semantic-aligned Radar and Camera Fusion", "url": "https://arxiv.org/abs/2302.10511", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2023-02-21"}
{"type": "node", "id": "author:zizhang_wu", "kind": "person", "label": "Zizhang Wu", "url": "https://arxiv.org/a/zizhang_wu", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:guilian_chen", "kind": "person", "label": "Guilian Chen", "url": "https://arxiv.org/a/guilian_chen", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:yuanzhu_gan", "kind": "person", "label": "Yuanzhu Gan", "url": "https://arxiv.org/a/yuanzhu_gan", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:lei_wang", "kind": "person", "label": "Lei Wang", "url": "https://arxiv.org/a/lei_wang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:jian_pu", "kind": "person", "label": "Jian Pu", "url": "https://arxiv.org/a/jian_pu", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:1907.06067", "kind": "paper", "label": "ALFA: Agglomerative Late Fusion Algorithm for Object Detection", "url": "https://arxiv.org/abs/1907.06067", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2019-07-13"}
{"type": "node", "id": "author:evgenii_razinkov", "kind": "person", "label": "Evgenii Razinkov", "url": "https://arxiv.org/a/evgenii_razinkov", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:iuliia_saveleva", "kind": "person", "label": "Iuliia Saveleva", "url": "https://arxiv.org/a/iuliia_saveleva", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:ji_i_matas", "kind": "person", "label": "Ji\u0159i Matas", "url": "https://arxiv.org/a/ji_i_matas", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2510.19215", "kind": "paper", "label": "SFGFusion: Surface Fitting Guided 3D Object Detection with 4D Radar and Camera Fusion", "url": "https://arxiv.org/abs/2510.19215", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2025-10-22"}
{"type": "node", "id": "author:xiaozhi_li", "kind": "person", "label": "Xiaozhi Li", "url": "https://arxiv.org/a/xiaozhi_li", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:huijun_di", "kind": "person", "label": "Huijun Di", "url": "https://arxiv.org/a/huijun_di", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:jian_li", "kind": "person", "label": "Jian Li", "url": "https://arxiv.org/a/jian_li", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:feng_liu", "kind": "person", "label": "Feng Liu", "url": "https://arxiv.org/a/feng_liu", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:wei_liang", "kind": "person", "label": "Wei Liang", "url": "https://arxiv.org/a/wei_liang", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:2606.27556", "kind": "paper", "label": "Radar Guided Camera Verification for Automatic Emergency Braking Rethinking Object Detection in Radar Camera Fusion", "url": "https://arxiv.org/abs/2606.27556", "source": "arxiv", "axis": "fusion", "layer": 0, "published": "2026-06-25"}
{"type": "node", "id": "author:ram_charan_akula", "kind": "person", "label": "Ram Charan Akula", "url": "https://arxiv.org/a/ram_charan_akula", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:sivanathan_kandhasamy", "kind": "person", "label": "Sivanathan Kandhasamy", "url": "https://arxiv.org/a/sivanathan_kandhasamy", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "author:manikandan_ganesan", "kind": "person", "label": "Manikandan Ganesan", "url": "https://arxiv.org/a/manikandan_ganesan", "source": "arxiv-author", "axis": "fusion", "layer": 0}
{"type": "node", "id": "paper:1606.00825", "kind": "paper", "label": "Training a Hidden Markov Model with a Bayesian Spiking Neural Network", "url": "https://arxiv.org/abs/1606.00825", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2016-06-02"}
{"type": "node", "id": "author:amirhossein_tavanaei", "kind": "person", "label": "Amirhossein Tavanaei", "url": "https://arxiv.org/a/amirhossein_tavanaei", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:anthony_s_maida", "kind": "person", "label": "Anthony S Maida", "url": "https://arxiv.org/a/anthony_s_maida", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2506.14138", "kind": "paper", "label": "NeuroCoreX: An Open-Source FPGA-Based Spiking Neural Network Emulator with On-Chip Learning", "url": "https://arxiv.org/abs/2506.14138", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2025-06-17"}
{"type": "node", "id": "author:ashish_gautam", "kind": "person", "label": "Ashish Gautam", "url": "https://arxiv.org/a/ashish_gautam", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:prasanna_date", "kind": "person", "label": "Prasanna Date", "url": "https://arxiv.org/a/prasanna_date", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:shruti_kulkarni", "kind": "person", "label": "Shruti Kulkarni", "url": "https://arxiv.org/a/shruti_kulkarni", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:robert_patton", "kind": "person", "label": "Robert Patton", "url": "https://arxiv.org/a/robert_patton", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:thomas_potok", "kind": "person", "label": "Thomas Potok", "url": "https://arxiv.org/a/thomas_potok", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:1810.03199", "kind": "paper", "label": "Pre-Synaptic Pool Modification (PSPM): A Supervised Learning Procedure for Spiking Neural Networks", "url": "https://arxiv.org/abs/1810.03199", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2018-10-07"}
{"type": "node", "id": "author:bryce_bagley", "kind": "person", "label": "Bryce Bagley", "url": "https://arxiv.org/a/bryce_bagley", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:blake_bordelon", "kind": "person", "label": "Blake Bordelon", "url": "https://arxiv.org/a/blake_bordelon", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:benjamin_moseley", "kind": "person", "label": "Benjamin Moseley", "url": "https://arxiv.org/a/benjamin_moseley", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:ralf_wessel", "kind": "person", "label": "Ralf Wessel", "url": "https://arxiv.org/a/ralf_wessel", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2503.17111", "kind": "paper", "label": "A Digital Machine Learning Algorithm Simulating Spiking Neural Network CoLaNET", "url": "https://arxiv.org/abs/2503.17111", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2025-03-21"}
{"type": "node", "id": "author:mikhail_kiselev", "kind": "person", "label": "Mikhail Kiselev", "url": "https://arxiv.org/a/mikhail_kiselev", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2104.12579", "kind": "paper", "label": "Learning from Event Cameras with Sparse Spiking Convolutional Neural Networks", "url": "https://arxiv.org/abs/2104.12579", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2021-04-26"}
{"type": "node", "id": "author:lo_c_cordone", "kind": "person", "label": "Lo\u00efc Cordone", "url": "https://arxiv.org/a/lo_c_cordone", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:beno_t_miramond", "kind": "person", "label": "Beno\u00eet Miramond", "url": "https://arxiv.org/a/beno_t_miramond", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:sonia_ferrante", "kind": "person", "label": "Sonia Ferrante", "url": "https://arxiv.org/a/sonia_ferrante", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2505.14841", "kind": "paper", "label": "Learning with Spike Synchrony in Spiking Neural Networks", "url": "https://arxiv.org/abs/2505.14841", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2025-04-14"}
{"type": "node", "id": "author:yuchen_tian", "kind": "person", "label": "Yuchen Tian", "url": "https://arxiv.org/a/yuchen_tian", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:assel_kembay", "kind": "person", "label": "Assel Kembay", "url": "https://arxiv.org/a/assel_kembay", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:samuel_tensingh", "kind": "person", "label": "Samuel Tensingh", "url": "https://arxiv.org/a/samuel_tensingh", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:nhan_duy_truong", "kind": "person", "label": "Nhan Duy Truong", "url": "https://arxiv.org/a/nhan_duy_truong", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:jason_k_eshraghian", "kind": "person", "label": "Jason K. Eshraghian", "url": "https://arxiv.org/a/jason_k_eshraghian", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2001.10696", "kind": "paper", "label": "Spiking Inception Module for Multi-layer Unsupervised Spiking Neural Networks", "url": "https://arxiv.org/abs/2001.10696", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2020-01-29"}
{"type": "node", "id": "author:mingyuan_meng", "kind": "person", "label": "Mingyuan Meng", "url": "https://arxiv.org/a/mingyuan_meng", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:xingyu_yang", "kind": "person", "label": "Xingyu Yang", "url": "https://arxiv.org/a/xingyu_yang", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:shanlin_xiao", "kind": "person", "label": "Shanlin Xiao", "url": "https://arxiv.org/a/shanlin_xiao", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:zhiyi_yu", "kind": "person", "label": "Zhiyi Yu", "url": "https://arxiv.org/a/zhiyi_yu", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2501.17172", "kind": "paper", "label": "Towards spiking analog hardware implementation of a trajectory interpolation mechanism for smooth closed-loop control of a spiking robot arm", "url": "https://arxiv.org/abs/2501.17172", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2025-01-23"}
{"type": "node", "id": "author:daniel_casanueva_morato", "kind": "person", "label": "Daniel Casanueva-Morato", "url": "https://arxiv.org/a/daniel_casanueva_morato", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:chenxi_wu", "kind": "person", "label": "Chenxi Wu", "url": "https://arxiv.org/a/chenxi_wu", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:giacomo_indiveri", "kind": "person", "label": "Giacomo Indiveri", "url": "https://arxiv.org/a/giacomo_indiveri", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:juan_p_dominguez_morales", "kind": "person", "label": "Juan P. Dominguez-Morales", "url": "https://arxiv.org/a/juan_p_dominguez_morales", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:alejandro_linares_barranco", "kind": "person", "label": "Alejandro Linares-Barranco", "url": "https://arxiv.org/a/alejandro_linares_barranco", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2010.06746", "kind": "paper", "label": "Analogical and Relational Reasoning with Spiking Neural Networks", "url": "https://arxiv.org/abs/2010.06746", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2020-10-14"}
{"type": "node", "id": "author:rollin_omari", "kind": "person", "label": "Rollin Omari", "url": "https://arxiv.org/a/rollin_omari", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:r_i_mckay", "kind": "person", "label": "R. I. McKay", "url": "https://arxiv.org/a/r_i_mckay", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:tom_gedeon", "kind": "person", "label": "Tom Gedeon", "url": "https://arxiv.org/a/tom_gedeon", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2307.11555", "kind": "paper", "label": "Accurate Detection of Spiking Motifs by Learning Heterogeneous Delays of a Spiking Neural Network", "url": "https://arxiv.org/abs/2307.11555", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2023-07-21"}
{"type": "node", "id": "author:laurent_u_perrinet", "kind": "person", "label": "Laurent U Perrinet", "url": "https://arxiv.org/a/laurent_u_perrinet", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2603.12060", "kind": "paper", "label": "Chemical Reaction Networks Learn Better than Spiking Neural Networks", "url": "https://arxiv.org/abs/2603.12060", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2026-03-12"}
{"type": "node", "id": "author:sophie_jaffard", "kind": "person", "label": "Sophie Jaffard", "url": "https://arxiv.org/a/sophie_jaffard", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:ivo_f_sbalzarini", "kind": "person", "label": "Ivo F. Sbalzarini", "url": "https://arxiv.org/a/ivo_f_sbalzarini", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2407.20633", "kind": "paper", "label": "Spiking-DD: Neuromorphic Event Camera based Driver Distraction Detection with Spiking Neural Network", "url": "https://arxiv.org/abs/2407.20633", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2024-07-30"}
{"type": "node", "id": "author:waseem_shariff", "kind": "person", "label": "Waseem Shariff", "url": "https://arxiv.org/a/waseem_shariff", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:paul_kielty", "kind": "person", "label": "Paul Kielty", "url": "https://arxiv.org/a/paul_kielty", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:joseph_lemley", "kind": "person", "label": "Joseph Lemley", "url": "https://arxiv.org/a/joseph_lemley", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:peter_corcoran", "kind": "person", "label": "Peter Corcoran", "url": "https://arxiv.org/a/peter_corcoran", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2205.04339", "kind": "paper", "label": "Object Detection with Spiking Neural Networks on Automotive Event Data", "url": "https://arxiv.org/abs/2205.04339", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2022-05-09"}
{"type": "node", "id": "author:philippe_thierion", "kind": "person", "label": "Philippe Thierion", "url": "https://arxiv.org/a/philippe_thierion", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2006.09985", "kind": "paper", "label": "An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic Processor", "url": "https://arxiv.org/abs/2006.09985", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2020-05-16"}
{"type": "node", "id": "author:riccardo_massa", "kind": "person", "label": "Riccardo Massa", "url": "https://arxiv.org/a/riccardo_massa", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:alberto_marchisio", "kind": "person", "label": "Alberto Marchisio", "url": "https://arxiv.org/a/alberto_marchisio", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:maurizio_martina", "kind": "person", "label": "Maurizio Martina", "url": "https://arxiv.org/a/maurizio_martina", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:muhammad_shafique", "kind": "person", "label": "Muhammad Shafique", "url": "https://arxiv.org/a/muhammad_shafique", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2006.04765", "kind": "paper", "label": "An Astrocyte-Modulated Neuromorphic Central Pattern Generator for Hexapod Robot Locomotion on Intel's Loihi", "url": "https://arxiv.org/abs/2006.04765", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2020-06-08"}
{"type": "node", "id": "author:ioannis_polykretis", "kind": "person", "label": "Ioannis Polykretis", "url": "https://arxiv.org/a/ioannis_polykretis", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:konstantinos_p_michmizos", "kind": "person", "label": "Konstantinos P. Michmizos", "url": "https://arxiv.org/a/konstantinos_p_michmizos", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2306.03369", "kind": "paper", "label": "Event Encryption: Rethinking Privacy Exposure for Neuromorphic Imaging", "url": "https://arxiv.org/abs/2306.03369", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2023-06-06"}
{"type": "node", "id": "author:pei_zhang", "kind": "person", "label": "Pei Zhang", "url": "https://arxiv.org/a/pei_zhang", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:shuo_zhu", "kind": "person", "label": "Shuo Zhu", "url": "https://arxiv.org/a/shuo_zhu", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:edmund_y_lam", "kind": "person", "label": "Edmund Y. Lam", "url": "https://arxiv.org/a/edmund_y_lam", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2109.12308", "kind": "paper", "label": "Brian2Loihi: An emulator for the neuromorphic chip Loihi using the spiking neural network simulator Brian", "url": "https://arxiv.org/abs/2109.12308", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2021-09-25"}
{"type": "node", "id": "author:carlo_michaelis", "kind": "person", "label": "Carlo Michaelis", "url": "https://arxiv.org/a/carlo_michaelis", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:andrew_b_lehr", "kind": "person", "label": "Andrew B. Lehr", "url": "https://arxiv.org/a/andrew_b_lehr", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:winfried_oed", "kind": "person", "label": "Winfried Oed", "url": "https://arxiv.org/a/winfried_oed", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:christian_tetzlaff", "kind": "person", "label": "Christian Tetzlaff", "url": "https://arxiv.org/a/christian_tetzlaff", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2008.11642", "kind": "paper", "label": "Robust trajectory generation for robotic control on the neuromorphic research chip Loihi", "url": "https://arxiv.org/abs/2008.11642", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2020-08-26"}
{"type": "node", "id": "paper:2602.13747", "kind": "paper", "label": "The More the Merrier: Running Multiple Neuromorphic Components On-Chip for Robotic Control", "url": "https://arxiv.org/abs/2602.13747", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2026-02-14"}
{"type": "node", "id": "author:evan_eames", "kind": "person", "label": "Evan Eames", "url": "https://arxiv.org/a/evan_eames", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:priyadarshini_kannan", "kind": "person", "label": "Priyadarshini Kannan", "url": "https://arxiv.org/a/priyadarshini_kannan", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:ronan_sangouard", "kind": "person", "label": "Ronan Sangouard", "url": "https://arxiv.org/a/ronan_sangouard", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:philipp_plank", "kind": "person", "label": "Philipp Plank", "url": "https://arxiv.org/a/philipp_plank", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:elvin_hajizada", "kind": "person", "label": "Elvin Hajizada", "url": "https://arxiv.org/a/elvin_hajizada", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2504.10053", "kind": "paper", "label": "Synthetic Biology meets Neuromorphic Computing: Towards a bio-inspired Olfactory Perception System", "url": "https://arxiv.org/abs/2504.10053", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2025-04-14"}
{"type": "node", "id": "author:kevin_max", "kind": "person", "label": "Kevin Max", "url": "https://arxiv.org/a/kevin_max", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:larissa_sames", "kind": "person", "label": "Larissa Sames", "url": "https://arxiv.org/a/larissa_sames", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:shimeng_ye", "kind": "person", "label": "Shimeng Ye", "url": "https://arxiv.org/a/shimeng_ye", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:jan_steink_hler", "kind": "person", "label": "Jan Steink\u00fchler", "url": "https://arxiv.org/a/jan_steink_hler", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:federico_corradi", "kind": "person", "label": "Federico Corradi", "url": "https://arxiv.org/a/federico_corradi", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2408.03076", "kind": "paper", "label": "Solving QUBO on the Loihi 2 Neuromorphic Processor", "url": "https://arxiv.org/abs/2408.03076", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2024-08-06"}
{"type": "node", "id": "author:alessandro_pierro", "kind": "person", "label": "Alessandro Pierro", "url": "https://arxiv.org/a/alessandro_pierro", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:philipp_stratmann", "kind": "person", "label": "Philipp Stratmann", "url": "https://arxiv.org/a/philipp_stratmann", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:gabriel_andres_fonseca_guerra", "kind": "person", "label": "Gabriel Andres Fonseca Guerra", "url": "https://arxiv.org/a/gabriel_andres_fonseca_guerra", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:sumedh_risbud", "kind": "person", "label": "Sumedh Risbud", "url": "https://arxiv.org/a/sumedh_risbud", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:timothy_shea", "kind": "person", "label": "Timothy Shea", "url": "https://arxiv.org/a/timothy_shea", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2307.13762", "kind": "paper", "label": "Implementing and Benchmarking the Locally Competitive Algorithm on the Loihi 2 Neuromorphic Processor", "url": "https://arxiv.org/abs/2307.13762", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2023-07-25"}
{"type": "node", "id": "author:gavin_parpart", "kind": "person", "label": "Gavin Parpart", "url": "https://arxiv.org/a/gavin_parpart", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:sumedh_r_risbud", "kind": "person", "label": "Sumedh R. Risbud", "url": "https://arxiv.org/a/sumedh_r_risbud", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:garrett_t_kenyon", "kind": "person", "label": "Garrett T. Kenyon", "url": "https://arxiv.org/a/garrett_t_kenyon", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:yijing_watkins", "kind": "person", "label": "Yijing Watkins", "url": "https://arxiv.org/a/yijing_watkins", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2011.00534", "kind": "paper", "label": "Neuromorphic control for optic-flow-based landings of MAVs using the Loihi processor", "url": "https://arxiv.org/abs/2011.00534", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2020-11-01"}
{"type": "node", "id": "author:julien_dupeyroux", "kind": "person", "label": "Julien Dupeyroux", "url": "https://arxiv.org/a/julien_dupeyroux", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:jesse_hagenaars", "kind": "person", "label": "Jesse Hagenaars", "url": "https://arxiv.org/a/jesse_hagenaars", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:federico_paredes_vall_s", "kind": "person", "label": "Federico Paredes-Vall\u00e9s", "url": "https://arxiv.org/a/federico_paredes_vall_s", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:guido_de_croon", "kind": "person", "label": "Guido de Croon", "url": "https://arxiv.org/a/guido_de_croon", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2109.10835", "kind": "paper", "label": "Mapping and Validating a Point Neuron Model on Intel's Neuromorphic Hardware Loihi", "url": "https://arxiv.org/abs/2109.10835", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2021-09-22"}
{"type": "node", "id": "author:srijanie_dey", "kind": "person", "label": "Srijanie Dey", "url": "https://arxiv.org/a/srijanie_dey", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:alexander_dimitrov", "kind": "person", "label": "Alexander Dimitrov", "url": "https://arxiv.org/a/alexander_dimitrov", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2508.09466", "kind": "paper", "label": "Event-driven Robust Fitting on Neuromorphic Hardware", "url": "https://arxiv.org/abs/2508.09466", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2025-08-13"}
{"type": "node", "id": "author:tam_ngoc_bang_nguyen", "kind": "person", "label": "Tam Ngoc-Bang Nguyen", "url": "https://arxiv.org/a/tam_ngoc_bang_nguyen", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:anh_dzung_doan", "kind": "person", "label": "Anh-Dzung Doan", "url": "https://arxiv.org/a/anh_dzung_doan", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:zhipeng_cai", "kind": "person", "label": "Zhipeng Cai", "url": "https://arxiv.org/a/zhipeng_cai", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:tat_jun_chin", "kind": "person", "label": "Tat-Jun Chin", "url": "https://arxiv.org/a/tat_jun_chin", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2508.16792", "kind": "paper", "label": "Neuromorphic Simulation of Drosophila Melanogaster Brain Connectome on Loihi 2", "url": "https://arxiv.org/abs/2508.16792", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2025-08-22"}
{"type": "node", "id": "author:felix_wang", "kind": "person", "label": "Felix Wang", "url": "https://arxiv.org/a/felix_wang", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:bradley_h_theilman", "kind": "person", "label": "Bradley H. Theilman", "url": "https://arxiv.org/a/bradley_h_theilman", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:fred_rothganger", "kind": "person", "label": "Fred Rothganger", "url": "https://arxiv.org/a/fred_rothganger", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:william_severa", "kind": "person", "label": "William Severa", "url": "https://arxiv.org/a/william_severa", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:craig_m_vineyard", "kind": "person", "label": "Craig M. Vineyard", "url": "https://arxiv.org/a/craig_m_vineyard", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:1812.01739", "kind": "paper", "label": "Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware", "url": "https://arxiv.org/abs/1812.01739", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2018-12-04"}
{"type": "node", "id": "author:peter_blouw", "kind": "person", "label": "Peter Blouw", "url": "https://arxiv.org/a/peter_blouw", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:xuan_choo", "kind": "person", "label": "Xuan Choo", "url": "https://arxiv.org/a/xuan_choo", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:eric_hunsberger", "kind": "person", "label": "Eric Hunsberger", "url": "https://arxiv.org/a/eric_hunsberger", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:chris_eliasmith", "kind": "person", "label": "Chris Eliasmith", "url": "https://arxiv.org/a/chris_eliasmith", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2107.00401", "kind": "paper", "label": "CarSNN: An Efficient Spiking Neural Network for Event-Based Autonomous Cars on the Loihi Neuromorphic Research Processor", "url": "https://arxiv.org/abs/2107.00401", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2021-07-01"}
{"type": "node", "id": "author:alberto_viale", "kind": "person", "label": "Alberto Viale", "url": "https://arxiv.org/a/alberto_viale", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:guido_masera", "kind": "person", "label": "Guido Masera", "url": "https://arxiv.org/a/guido_masera", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2512.03911", "kind": "paper", "label": "Autonomous Reinforcement Learning Robot Control with Intel's Loihi 2 Neuromorphic Hardware", "url": "https://arxiv.org/abs/2512.03911", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2025-12-03"}
{"type": "node", "id": "author:kenneth_stewart", "kind": "person", "label": "Kenneth Stewart", "url": "https://arxiv.org/a/kenneth_stewart", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:roxana_leontie", "kind": "person", "label": "Roxana Leontie", "url": "https://arxiv.org/a/roxana_leontie", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:samantha_chapin", "kind": "person", "label": "Samantha Chapin", "url": "https://arxiv.org/a/samantha_chapin", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:joe_hays", "kind": "person", "label": "Joe Hays", "url": "https://arxiv.org/a/joe_hays", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:sumit_bam_shrestha", "kind": "person", "label": "Sumit Bam Shrestha", "url": "https://arxiv.org/a/sumit_bam_shrestha", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2304.04640", "kind": "paper", "label": "NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems", "url": "https://arxiv.org/abs/2304.04640", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2023-04-10"}
{"type": "node", "id": "author:jason_yik", "kind": "person", "label": "Jason Yik", "url": "https://arxiv.org/a/jason_yik", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:korneel_van_den_berghe", "kind": "person", "label": "Korneel Van den Berghe", "url": "https://arxiv.org/a/korneel_van_den_berghe", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:douwe_den_blanken", "kind": "person", "label": "Douwe den Blanken", "url": "https://arxiv.org/a/douwe_den_blanken", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:younes_bouhadjar", "kind": "person", "label": "Younes Bouhadjar", "url": "https://arxiv.org/a/younes_bouhadjar", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:maxime_fabre", "kind": "person", "label": "Maxime Fabre", "url": "https://arxiv.org/a/maxime_fabre", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2502.20729", "kind": "paper", "label": "NeuroMorse: A Temporally Structured Dataset For Neuromorphic Computing", "url": "https://arxiv.org/abs/2502.20729", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2025-02-28"}
{"type": "node", "id": "author:ben_walters", "kind": "person", "label": "Ben Walters", "url": "https://arxiv.org/a/ben_walters", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:yeshwanth_bethi", "kind": "person", "label": "Yeshwanth Bethi", "url": "https://arxiv.org/a/yeshwanth_bethi", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:taylor_kergan", "kind": "person", "label": "Taylor Kergan", "url": "https://arxiv.org/a/taylor_kergan", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:binh_nguyen", "kind": "person", "label": "Binh Nguyen", "url": "https://arxiv.org/a/binh_nguyen", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:amirali_amirsoleimani", "kind": "person", "label": "Amirali Amirsoleimani", "url": "https://arxiv.org/a/amirali_amirsoleimani", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2601.10742", "kind": "paper", "label": "Line-based Event Preprocessing: Towards Low-Energy Neuromorphic Computer Vision", "url": "https://arxiv.org/abs/2601.10742", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2026-01-10"}
{"type": "node", "id": "author:am_lie_gruel", "kind": "person", "label": "Am\u00e9lie Gruel", "url": "https://arxiv.org/a/am_lie_gruel", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:pierre_lewden", "kind": "person", "label": "Pierre Lewden", "url": "https://arxiv.org/a/pierre_lewden", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:adrien_f_vincent", "kind": "person", "label": "Adrien F. Vincent", "url": "https://arxiv.org/a/adrien_f_vincent", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:sylvain_sa_ghi", "kind": "person", "label": "Sylvain Sa\u00efghi", "url": "https://arxiv.org/a/sylvain_sa_ghi", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2401.12055", "kind": "paper", "label": "NEUROSEC: FPGA-Based Neuromorphic Audio Security", "url": "https://arxiv.org/abs/2401.12055", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2024-01-22"}
{"type": "node", "id": "author:murat_isik", "kind": "person", "label": "Murat Isik", "url": "https://arxiv.org/a/murat_isik", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:hiruna_vishwamith", "kind": "person", "label": "Hiruna Vishwamith", "url": "https://arxiv.org/a/hiruna_vishwamith", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:yusuf_sur", "kind": "person", "label": "Yusuf Sur", "url": "https://arxiv.org/a/yusuf_sur", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:kayode_inadagbo", "kind": "person", "label": "Kayode Inadagbo", "url": "https://arxiv.org/a/kayode_inadagbo", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:i_can_dikmen", "kind": "person", "label": "I. Can Dikmen", "url": "https://arxiv.org/a/i_can_dikmen", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2011.12013", "kind": "paper", "label": "Exploring the landscapes of \"computing\": digital, neuromorphic, unconventional -- and beyond", "url": "https://arxiv.org/abs/2011.12013", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2020-11-24"}
{"type": "node", "id": "author:herbert_jaeger", "kind": "person", "label": "Herbert Jaeger", "url": "https://arxiv.org/a/herbert_jaeger", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2304.08802", "kind": "paper", "label": "Neuromorphic computing for attitude estimation onboard quadrotors", "url": "https://arxiv.org/abs/2304.08802", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2023-04-18"}
{"type": "node", "id": "author:stein_stroobants", "kind": "person", "label": "Stein Stroobants", "url": "https://arxiv.org/a/stein_stroobants", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:guido_c_h_e_de_croon", "kind": "person", "label": "Guido C. H. E. de Croon", "url": "https://arxiv.org/a/guido_c_h_e_de_croon", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2405.01305", "kind": "paper", "label": "Distributed Representations Enable Robust Multi-Timescale Symbolic Computation in Neuromorphic Hardware", "url": "https://arxiv.org/abs/2405.01305", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2024-05-02"}
{"type": "node", "id": "author:madison_cotteret", "kind": "person", "label": "Madison Cotteret", "url": "https://arxiv.org/a/madison_cotteret", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:hugh_greatorex", "kind": "person", "label": "Hugh Greatorex", "url": "https://arxiv.org/a/hugh_greatorex", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:alpha_renner", "kind": "person", "label": "Alpha Renner", "url": "https://arxiv.org/a/alpha_renner", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:junren_chen", "kind": "person", "label": "Junren Chen", "url": "https://arxiv.org/a/junren_chen", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:emre_neftci", "kind": "person", "label": "Emre Neftci", "url": "https://arxiv.org/a/emre_neftci", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2004.14942", "kind": "paper", "label": "Memristors -- from In-memory computing, Deep Learning Acceleration, Spiking Neural Networks, to the Future of Neuromorphic and Bio-inspired Computing", "url": "https://arxiv.org/abs/2004.14942", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2020-04-30"}
{"type": "node", "id": "author:adnan_mehonic", "kind": "person", "label": "Adnan Mehonic", "url": "https://arxiv.org/a/adnan_mehonic", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:abu_sebastian", "kind": "person", "label": "Abu Sebastian", "url": "https://arxiv.org/a/abu_sebastian", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:bipin_rajendran", "kind": "person", "label": "Bipin Rajendran", "url": "https://arxiv.org/a/bipin_rajendran", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:osvaldo_simeone", "kind": "person", "label": "Osvaldo Simeone", "url": "https://arxiv.org/a/osvaldo_simeone", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:eleni_vasilaki", "kind": "person", "label": "Eleni Vasilaki", "url": "https://arxiv.org/a/eleni_vasilaki", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:1211.0310", "kind": "paper", "label": "Large Synoptic Survey Telescope: Dark Energy Science Collaboration", "url": "https://arxiv.org/abs/1211.0310", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2012-11-01"}
{"type": "node", "id": "author:lsst_dark_energy_science_collaboration", "kind": "person", "label": "LSST Dark Energy Science Collaboration", "url": "https://arxiv.org/a/lsst_dark_energy_science_collaboration", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2604.04727", "kind": "paper", "label": "Neuromorphic Computing for Low-Power Artificial Intelligence", "url": "https://arxiv.org/abs/2604.04727", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2026-04-06"}
{"type": "node", "id": "author:keshava_katti", "kind": "person", "label": "Keshava Katti", "url": "https://arxiv.org/a/keshava_katti", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:pratik_chaudhari", "kind": "person", "label": "Pratik Chaudhari", "url": "https://arxiv.org/a/pratik_chaudhari", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:deep_jariwala", "kind": "person", "label": "Deep Jariwala", "url": "https://arxiv.org/a/deep_jariwala", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:the_dark_energy_survey_collaboration", "kind": "person", "label": "The Dark Energy Survey Collaboration", "url": "https://arxiv.org/a/the_dark_energy_survey_collaboration", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:1810.12640", "kind": "paper", "label": "Neuromorphic hardware as a self-organizing computing system", "url": "https://arxiv.org/abs/1810.12640", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2018-10-30"}
{"type": "node", "id": "author:lyes_khacef", "kind": "person", "label": "Lyes Khacef", "url": "https://arxiv.org/a/lyes_khacef", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:bernard_girau", "kind": "person", "label": "Bernard Girau", "url": "https://arxiv.org/a/bernard_girau", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:nicolas_rougier", "kind": "person", "label": "Nicolas Rougier", "url": "https://arxiv.org/a/nicolas_rougier", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:andres_upegui", "kind": "person", "label": "Andres Upegui", "url": "https://arxiv.org/a/andres_upegui", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:benoit_miramond", "kind": "person", "label": "Benoit Miramond", "url": "https://arxiv.org/a/benoit_miramond", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2410.22352", "kind": "paper", "label": "Neuromorphic Programming: Emerging Directions for Brain-Inspired Hardware", "url": "https://arxiv.org/abs/2410.22352", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2024-10-15"}
{"type": "node", "id": "author:steven_abreu", "kind": "person", "label": "Steven Abreu", "url": "https://arxiv.org/a/steven_abreu", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:jens_e_pedersen", "kind": "person", "label": "Jens E. Pedersen", "url": "https://arxiv.org/a/jens_e_pedersen", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:1609.02545", "kind": "paper", "label": "Supervised Learning in Spiking Neural Networks with FORCE Training", "url": "https://arxiv.org/abs/1609.02545", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2016-09-08"}
{"type": "node", "id": "author:wilten_nicola", "kind": "person", "label": "Wilten Nicola", "url": "https://arxiv.org/a/wilten_nicola", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:claudia_clopath", "kind": "person", "label": "Claudia Clopath", "url": "https://arxiv.org/a/claudia_clopath", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2302.00232", "kind": "paper", "label": "SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural Networks", "url": "https://arxiv.org/abs/2302.00232", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2023-02-01"}
{"type": "node", "id": "author:mingqing_xiao", "kind": "person", "label": "Mingqing Xiao", "url": "https://arxiv.org/a/mingqing_xiao", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:qingyan_meng", "kind": "person", "label": "Qingyan Meng", "url": "https://arxiv.org/a/qingyan_meng", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:zongpeng_zhang", "kind": "person", "label": "Zongpeng Zhang", "url": "https://arxiv.org/a/zongpeng_zhang", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:yisen_wang", "kind": "person", "label": "Yisen Wang", "url": "https://arxiv.org/a/yisen_wang", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:zhouchen_lin", "kind": "person", "label": "Zhouchen Lin", "url": "https://arxiv.org/a/zhouchen_lin", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:1908.06378", "kind": "paper", "label": "Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks", "url": "https://arxiv.org/abs/1908.06378", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2019-08-18"}
{"type": "node", "id": "author:peng_li", "kind": "person", "label": "Peng Li", "url": "https://arxiv.org/a/peng_li", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2104.00035", "kind": "paper", "label": "Strengthening the Training of Convolutional Neural Networks By Using Walsh Matrix", "url": "https://arxiv.org/abs/2104.00035", "source": "arxiv", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "published": "2021-03-31"}
{"type": "node", "id": "author:tamer_lmez", "kind": "person", "label": "Tamer \u00d6lmez", "url": "https://arxiv.org/a/tamer_lmez", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "author:z_mray_dokur", "kind": "person", "label": "Z\u00fcmray Dokur", "url": "https://arxiv.org/a/z_mray_dokur", "source": "arxiv-author", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "paper:2405.11907", "kind": "paper", "label": "Ensemble and Mixture-of-Experts DeepONets For Operator Learning", "url": "https://arxiv.org/abs/2405.11907", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2024-05-20"}
{"type": "node", "id": "author:ramansh_sharma", "kind": "person", "label": "Ramansh Sharma", "url": "https://arxiv.org/a/ramansh_sharma", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:varun_shankar", "kind": "person", "label": "Varun Shankar", "url": "https://arxiv.org/a/varun_shankar", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:arupkumar_pal", "kind": "person", "label": "Arupkumar Pal", "url": "https://arxiv.org/a/arupkumar_pal", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2204.03193", "kind": "paper", "label": "MultiAuto-DeepONet: A Multi-resolution Autoencoder DeepONet for Nonlinear Dimension Reduction, Uncertainty Quantification and Operator Learning of Forward and Inverse Stochastic Problems", "url": "https://arxiv.org/abs/2204.03193", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2022-04-07"}
{"type": "node", "id": "author:jiahao_zhang", "kind": "person", "label": "Jiahao Zhang", "url": "https://arxiv.org/a/jiahao_zhang", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:shiqi_zhang", "kind": "person", "label": "Shiqi Zhang", "url": "https://arxiv.org/a/shiqi_zhang", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:guang_lin", "kind": "person", "label": "Guang Lin", "url": "https://arxiv.org/a/guang_lin", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2509.12344", "kind": "paper", "label": "FEDONet : Fourier-Embedded DeepONet for Spectrally Accurate Operator Learning", "url": "https://arxiv.org/abs/2509.12344", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2025-09-15"}
{"type": "node", "id": "author:arth_sojitra", "kind": "person", "label": "Arth Sojitra", "url": "https://arxiv.org/a/arth_sojitra", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:mrigank_dhingra", "kind": "person", "label": "Mrigank Dhingra", "url": "https://arxiv.org/a/mrigank_dhingra", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:omer_san", "kind": "person", "label": "Omer San", "url": "https://arxiv.org/a/omer_san", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2507.10368", "kind": "paper", "label": "Operator Learning for Consolidation: An Architectural Comparison for DeepONet Variants", "url": "https://arxiv.org/abs/2507.10368", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2025-07-14"}
{"type": "node", "id": "author:yongjin_choi", "kind": "person", "label": "Yongjin Choi", "url": "https://arxiv.org/a/yongjin_choi", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:chenying_liu", "kind": "person", "label": "Chenying Liu", "url": "https://arxiv.org/a/chenying_liu", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:jorge_macedo", "kind": "person", "label": "Jorge Macedo", "url": "https://arxiv.org/a/jorge_macedo", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2501.09395", "kind": "paper", "label": "ELM-DeepONets: Backpropagation-Free Training of Deep Operator Networks via Extreme Learning Machines", "url": "https://arxiv.org/abs/2501.09395", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2025-01-16"}
{"type": "node", "id": "author:hwijae_son", "kind": "person", "label": "Hwijae Son", "url": "https://arxiv.org/a/hwijae_son", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1510.08231", "kind": "paper", "label": "Operator-valued Kernels for Learning from Functional Response Data", "url": "https://arxiv.org/abs/1510.08231", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2015-10-28"}
{"type": "node", "id": "author:hachem_kadri", "kind": "person", "label": "Hachem Kadri", "url": "https://arxiv.org/a/hachem_kadri", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:emmanuel_duflos", "kind": "person", "label": "Emmanuel Duflos", "url": "https://arxiv.org/a/emmanuel_duflos", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:philippe_preux", "kind": "person", "label": "Philippe Preux", "url": "https://arxiv.org/a/philippe_preux", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:st_phane_canu", "kind": "person", "label": "St\u00e9phane Canu", "url": "https://arxiv.org/a/st_phane_canu", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:alain_rakotomamonjy", "kind": "person", "label": "Alain Rakotomamonjy", "url": "https://arxiv.org/a/alain_rakotomamonjy", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2503.00317", "kind": "paper", "label": "DeepONet Augmented by Randomized Neural Networks for Efficient Operator Learning in PDEs", "url": "https://arxiv.org/abs/2503.00317", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2025-03-01"}
{"type": "node", "id": "author:zhaoxi_jiang", "kind": "person", "label": "Zhaoxi Jiang", "url": "https://arxiv.org/a/zhaoxi_jiang", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:fei_wang", "kind": "person", "label": "Fei Wang", "url": "https://arxiv.org/a/fei_wang", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2409.12293", "kind": "paper", "label": "In-Context Learning of Linear Systems: Generalization Theory and Applications to Operator Learning", "url": "https://arxiv.org/abs/2409.12293", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2024-09-18"}
{"type": "node", "id": "author:frank_cole", "kind": "person", "label": "Frank Cole", "url": "https://arxiv.org/a/frank_cole", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:yulong_lu", "kind": "person", "label": "Yulong Lu", "url": "https://arxiv.org/a/yulong_lu", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:wuzhe_xu", "kind": "person", "label": "Wuzhe Xu", "url": "https://arxiv.org/a/wuzhe_xu", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:tianhao_zhang", "kind": "person", "label": "Tianhao Zhang", "url": "https://arxiv.org/a/tianhao_zhang", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2506.09781", "kind": "paper", "label": "On the Similarities of Embeddings in Contrastive Learning", "url": "https://arxiv.org/abs/2506.09781", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2025-06-11"}
{"type": "node", "id": "author:chungpa_lee", "kind": "person", "label": "Chungpa Lee", "url": "https://arxiv.org/a/chungpa_lee", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:sehee_lim", "kind": "person", "label": "Sehee Lim", "url": "https://arxiv.org/a/sehee_lim", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:kibok_lee", "kind": "person", "label": "Kibok Lee", "url": "https://arxiv.org/a/kibok_lee", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:jy_yong_sohn", "kind": "person", "label": "Jy-yong Sohn", "url": "https://arxiv.org/a/jy_yong_sohn", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1910.03193", "kind": "paper", "label": "DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators", "url": "https://arxiv.org/abs/1910.03193", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2019-10-08"}
{"type": "node", "id": "author:lu_lu", "kind": "person", "label": "Lu Lu", "url": "https://arxiv.org/a/lu_lu", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:pengzhan_jin", "kind": "person", "label": "Pengzhan Jin", "url": "https://arxiv.org/a/pengzhan_jin", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:george_em_karniadakis", "kind": "person", "label": "George Em Karniadakis", "url": "https://arxiv.org/a/george_em_karniadakis", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2504.10932", "kind": "paper", "label": "Multi-scale DeepOnet (Mscale-DeepOnet) for Mitigating Spectral Bias in Learning High Frequency Operators of Oscillatory Functions", "url": "https://arxiv.org/abs/2504.10932", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2025-04-15"}
{"type": "node", "id": "author:bo_wang", "kind": "person", "label": "Bo Wang", "url": "https://arxiv.org/a/bo_wang", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:lizuo_liu", "kind": "person", "label": "Lizuo Liu", "url": "https://arxiv.org/a/lizuo_liu", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:wei_cai", "kind": "person", "label": "Wei Cai", "url": "https://arxiv.org/a/wei_cai", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2212.04663", "kind": "paper", "label": "Transfer Learning Enhanced DeepONet for Long-Time Prediction of Evolution Equations", "url": "https://arxiv.org/abs/2212.04663", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2022-12-09"}
{"type": "node", "id": "author:li_wang", "kind": "person", "label": "Li Wang", "url": "https://arxiv.org/a/li_wang", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1905.07435", "kind": "paper", "label": "Alpha MAML: Adaptive Model-Agnostic Meta-Learning", "url": "https://arxiv.org/abs/1905.07435", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2019-05-17"}
{"type": "node", "id": "author:harkirat_singh_behl", "kind": "person", "label": "Harkirat Singh Behl", "url": "https://arxiv.org/a/harkirat_singh_behl", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:at_l_m_g_ne_baydin", "kind": "person", "label": "At\u0131l\u0131m G\u00fcne\u015f Baydin", "url": "https://arxiv.org/a/at_l_m_g_ne_baydin", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:philip_h_s_torr", "kind": "person", "label": "Philip H. S. Torr", "url": "https://arxiv.org/a/philip_h_s_torr", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2006.02361", "kind": "paper", "label": "Optimizing Neural Networks via Koopman Operator Theory", "url": "https://arxiv.org/abs/2006.02361", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2020-06-03"}
{"type": "node", "id": "author:akshunna_s_dogra", "kind": "person", "label": "Akshunna S. Dogra", "url": "https://arxiv.org/a/akshunna_s_dogra", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:william_t_redman", "kind": "person", "label": "William T Redman", "url": "https://arxiv.org/a/william_t_redman", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1804.03587", "kind": "paper", "label": "Symmetries on plabic graphs and associated polytopes", "url": "https://arxiv.org/abs/1804.03587", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2018-04-10"}
{"type": "node", "id": "author:xin_fang", "kind": "person", "label": "Xin Fang", "url": "https://arxiv.org/a/xin_fang", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:ghislain_fourier", "kind": "person", "label": "Ghislain Fourier", "url": "https://arxiv.org/a/ghislain_fourier", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1010.5964", "kind": "paper", "label": "Quadratic discrete Fourier transform and mutually unbiased bases", "url": "https://arxiv.org/abs/1010.5964", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2010-10-28"}
{"type": "node", "id": "author:maurice_robert_kibler", "kind": "person", "label": "Maurice Robert Kibler", "url": "https://arxiv.org/a/maurice_robert_kibler", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2509.25500", "kind": "paper", "label": "A High-Frequency Uncertainty Principle for the Fourier-Bessel Transform", "url": "https://arxiv.org/abs/2509.25500", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2025-09-29"}
{"type": "node", "id": "author:benjamin_jaye", "kind": "person", "label": "Benjamin Jaye", "url": "https://arxiv.org/a/benjamin_jaye", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:rahul_sethi", "kind": "person", "label": "Rahul Sethi", "url": "https://arxiv.org/a/rahul_sethi", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:manuel_calixto", "kind": "person", "label": "Manuel Calixto", "url": "https://arxiv.org/a/manuel_calixto", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:julio_guerrero", "kind": "person", "label": "Julio Guerrero", "url": "https://arxiv.org/a/julio_guerrero", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:juan_carlos_s_nchez_monreal", "kind": "person", "label": "Juan Carlos S\u00e1nchez-Monreal", "url": "https://arxiv.org/a/juan_carlos_s_nchez_monreal", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:0904.4716", "kind": "paper", "label": "Sampling Theorem and Discrete Fourier Transform on the Hyperboloid", "url": "https://arxiv.org/abs/0904.4716", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2009-04-29"}
{"type": "node", "id": "paper:1605.09340", "kind": "paper", "label": "Fourier multiplier theorems involving type and cotype", "url": "https://arxiv.org/abs/1605.09340", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2016-05-30"}
{"type": "node", "id": "author:jan_rozendaal", "kind": "person", "label": "Jan Rozendaal", "url": "https://arxiv.org/a/jan_rozendaal", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:mark_veraar", "kind": "person", "label": "Mark Veraar", "url": "https://arxiv.org/a/mark_veraar", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2202.04211", "kind": "paper", "label": "$L^{p}$-$L^{q}$ boundedness of Fourier multipliers on Fundamental domains of Lattices in $\\mathbb{R}^d$", "url": "https://arxiv.org/abs/2202.04211", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2022-02-09"}
{"type": "node", "id": "author:arne_hendrickx", "kind": "person", "label": "Arne Hendrickx", "url": "https://arxiv.org/a/arne_hendrickx", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2203.07923", "kind": "paper", "label": "$L^p-L^q$ local smoothing estimates for the wave equation via $k$-broad Fourier restriction", "url": "https://arxiv.org/abs/2203.07923", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2022-03-15"}
{"type": "node", "id": "author:david_beltran", "kind": "person", "label": "David Beltran", "url": "https://arxiv.org/a/david_beltran", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:olli_saari", "kind": "person", "label": "Olli Saari", "url": "https://arxiv.org/a/olli_saari", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1406.0636", "kind": "paper", "label": "On a Class of Fourier Integral Operators on Manifolds with Boundary", "url": "https://arxiv.org/abs/1406.0636", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2014-06-03"}
{"type": "node", "id": "author:ubertino_battisti", "kind": "person", "label": "Ubertino Battisti", "url": "https://arxiv.org/a/ubertino_battisti", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:sandro_coriasco", "kind": "person", "label": "Sandro Coriasco", "url": "https://arxiv.org/a/sandro_coriasco", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:elmar_schrohe", "kind": "person", "label": "Elmar Schrohe", "url": "https://arxiv.org/a/elmar_schrohe", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2307.05639", "kind": "paper", "label": "Learning Active Subspaces and Discovering Important Features with Gaussian Radial Basis Functions Neural Networks", "url": "https://arxiv.org/abs/2307.05639", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2023-07-11"}
{"type": "node", "id": "author:danny_d_agostino", "kind": "person", "label": "Danny D'Agostino", "url": "https://arxiv.org/a/danny_d_agostino", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:ilija_ilievski", "kind": "person", "label": "Ilija Ilievski", "url": "https://arxiv.org/a/ilija_ilievski", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:christine_annette_shoemaker", "kind": "person", "label": "Christine Annette Shoemaker", "url": "https://arxiv.org/a/christine_annette_shoemaker", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1901.06610", "kind": "paper", "label": "Hierarchical Attentional Hybrid Neural Networks for Document Classification", "url": "https://arxiv.org/abs/1901.06610", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2019-01-20"}
{"type": "node", "id": "author:jader_abreu", "kind": "person", "label": "Jader Abreu", "url": "https://arxiv.org/a/jader_abreu", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:luis_fred", "kind": "person", "label": "Luis Fred", "url": "https://arxiv.org/a/luis_fred", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:david_mac_do", "kind": "person", "label": "David Mac\u00eado", "url": "https://arxiv.org/a/david_mac_do", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:cleber_zanchettin", "kind": "person", "label": "Cleber Zanchettin", "url": "https://arxiv.org/a/cleber_zanchettin", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1506.01230", "kind": "paper", "label": "Stability of solutions to stochastic partial differential equations", "url": "https://arxiv.org/abs/1506.01230", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2015-06-03"}
{"type": "node", "id": "author:benjamin_gess", "kind": "person", "label": "Benjamin Gess", "url": "https://arxiv.org/a/benjamin_gess", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:jonas_m_t_lle", "kind": "person", "label": "Jonas M. T\u00f6lle", "url": "https://arxiv.org/a/jonas_m_t_lle", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1012.4657", "kind": "paper", "label": "An inverse problem of Calderon type with partial data", "url": "https://arxiv.org/abs/1012.4657", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2010-12-21"}
{"type": "node", "id": "author:jussi_behrndt", "kind": "person", "label": "Jussi Behrndt", "url": "https://arxiv.org/a/jussi_behrndt", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:jonathan_rohleder", "kind": "person", "label": "Jonathan Rohleder", "url": "https://arxiv.org/a/jonathan_rohleder", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1005.4095", "kind": "paper", "label": "Regularity analysis for stochastic partial differential equations with nonlinear multiplicative trace class noise", "url": "https://arxiv.org/abs/1005.4095", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2010-05-21"}
{"type": "node", "id": "author:arnulf_jentzen", "kind": "person", "label": "Arnulf Jentzen", "url": "https://arxiv.org/a/arnulf_jentzen", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:michael_roeckner", "kind": "person", "label": "Michael Roeckner", "url": "https://arxiv.org/a/michael_roeckner", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1210.5831", "kind": "paper", "label": "Stability of a critical nonlinear neutral delay differential equation", "url": "https://arxiv.org/abs/1210.5831", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2012-10-22"}
{"type": "node", "id": "author:st_phane_junca", "kind": "person", "label": "St\u00e9phane Junca", "url": "https://arxiv.org/a/st_phane_junca", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:bruno_lombard", "kind": "person", "label": "Bruno Lombard", "url": "https://arxiv.org/a/bruno_lombard", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1912.05497", "kind": "paper", "label": "Boundary value problems for elliptic partial differential equations", "url": "https://arxiv.org/abs/1912.05497", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2019-12-11"}
{"type": "node", "id": "author:mourad_choulli", "kind": "person", "label": "Mourad Choulli", "url": "https://arxiv.org/a/mourad_choulli", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2303.02304", "kind": "paper", "label": "Coupled Multiwavelet Neural Operator Learning for Coupled Partial Differential Equations", "url": "https://arxiv.org/abs/2303.02304", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2023-03-04"}
{"type": "node", "id": "author:xiongye_xiao", "kind": "person", "label": "Xiongye Xiao", "url": "https://arxiv.org/a/xiongye_xiao", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:defu_cao", "kind": "person", "label": "Defu Cao", "url": "https://arxiv.org/a/defu_cao", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:ruochen_yang", "kind": "person", "label": "Ruochen Yang", "url": "https://arxiv.org/a/ruochen_yang", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:gaurav_gupta", "kind": "person", "label": "Gaurav Gupta", "url": "https://arxiv.org/a/gaurav_gupta", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:gengshuo_liu", "kind": "person", "label": "Gengshuo Liu", "url": "https://arxiv.org/a/gengshuo_liu", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1204.6613", "kind": "paper", "label": "Maximum principles for boundary-degenerate second-order linear elliptic differential operators", "url": "https://arxiv.org/abs/1204.6613", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2012-04-30"}
{"type": "node", "id": "author:paul_m_n_feehan", "kind": "person", "label": "Paul M. N. Feehan", "url": "https://arxiv.org/a/paul_m_n_feehan", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:0801.3838", "kind": "paper", "label": "Pseudodifferential multi-product representation of the solution operator of a parabolic equation", "url": "https://arxiv.org/abs/0801.3838", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2008-01-24"}
{"type": "node", "id": "author:hiroshi_isozaki", "kind": "person", "label": "Hiroshi Isozaki", "url": "https://arxiv.org/a/hiroshi_isozaki", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:j_r_me_le_rousseau", "kind": "person", "label": "J\u00e9r\u00f4me Le Rousseau", "url": "https://arxiv.org/a/j_r_me_le_rousseau", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1210.6727", "kind": "paper", "label": "Schauder a priori estimates and regularity of solutions to boundary-degenerate elliptic linear second-order partial differential equations", "url": "https://arxiv.org/abs/1210.6727", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2012-10-25"}
{"type": "node", "id": "author:camelia_pop", "kind": "person", "label": "Camelia Pop", "url": "https://arxiv.org/a/camelia_pop", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1506.03252", "kind": "paper", "label": "Rough differential equations driven by signals in Besov spaces", "url": "https://arxiv.org/abs/1506.03252", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2015-06-10"}
{"type": "node", "id": "author:david_j_pr_mel", "kind": "person", "label": "David J. Pr\u00f6mel", "url": "https://arxiv.org/a/david_j_pr_mel", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:mathias_trabs", "kind": "person", "label": "Mathias Trabs", "url": "https://arxiv.org/a/mathias_trabs", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1805.06925", "kind": "paper", "label": "Applications of integral transforms composition method (ITCM) to wave-type singular differential equations and index shift transmutations", "url": "https://arxiv.org/abs/1805.06925", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2018-05-17"}
{"type": "node", "id": "author:ahmed_fitouhi", "kind": "person", "label": "Ahmed Fitouhi", "url": "https://arxiv.org/a/ahmed_fitouhi", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:in_ss_jebabli", "kind": "person", "label": "In\u00e8ss Jebabli", "url": "https://arxiv.org/a/in_ss_jebabli", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:elina_l_shishkina", "kind": "person", "label": "Elina L. Shishkina", "url": "https://arxiv.org/a/elina_l_shishkina", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:sergei_m_sitnik", "kind": "person", "label": "Sergei M. Sitnik", "url": "https://arxiv.org/a/sergei_m_sitnik", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1804.08515", "kind": "paper", "label": "Planarly branched rough paths and rough differential equations on homogeneous spaces", "url": "https://arxiv.org/abs/1804.08515", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2018-04-23"}
{"type": "node", "id": "author:charles_curry", "kind": "person", "label": "Charles Curry", "url": "https://arxiv.org/a/charles_curry", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:kurusch_ebrahimi_fard", "kind": "person", "label": "Kurusch Ebrahimi-Fard", "url": "https://arxiv.org/a/kurusch_ebrahimi_fard", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:dominique_manchon", "kind": "person", "label": "Dominique Manchon", "url": "https://arxiv.org/a/dominique_manchon", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:hans_z_munthe_kaas", "kind": "person", "label": "Hans Z. Munthe-Kaas", "url": "https://arxiv.org/a/hans_z_munthe_kaas", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2005.00865", "kind": "paper", "label": "Neural Differential Equations for Single Image Super-resolution", "url": "https://arxiv.org/abs/2005.00865", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2020-05-02"}
{"type": "node", "id": "author:teven_le_scao", "kind": "person", "label": "Teven Le Scao", "url": "https://arxiv.org/a/teven_le_scao", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2012.10726", "kind": "paper", "label": "Stability and oscillation of linear delay differential equations", "url": "https://arxiv.org/abs/2012.10726", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2020-12-19"}
{"type": "node", "id": "author:john_ioannis_stavroulakis", "kind": "person", "label": "John Ioannis Stavroulakis", "url": "https://arxiv.org/a/john_ioannis_stavroulakis", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:elena_braverman", "kind": "person", "label": "Elena Braverman", "url": "https://arxiv.org/a/elena_braverman", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1709.07098", "kind": "paper", "label": "Talagrand Concentration Inequalities for Stochastic Partial Differential Equations", "url": "https://arxiv.org/abs/1709.07098", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2017-09-20"}
{"type": "node", "id": "author:davar_khoshnevisan", "kind": "person", "label": "Davar Khoshnevisan", "url": "https://arxiv.org/a/davar_khoshnevisan", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:andrey_sarantsev", "kind": "person", "label": "Andrey Sarantsev", "url": "https://arxiv.org/a/andrey_sarantsev", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2309.17345", "kind": "paper", "label": "Physics-Informed Neural Network for the Transient Diffusivity Equation in Reservoir Engineering", "url": "https://arxiv.org/abs/2309.17345", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2023-09-29"}
{"type": "node", "id": "author:daniel_badawi", "kind": "person", "label": "Daniel Badawi", "url": "https://arxiv.org/a/daniel_badawi", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:eduardo_gildin", "kind": "person", "label": "Eduardo Gildin", "url": "https://arxiv.org/a/eduardo_gildin", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2107.00465", "kind": "paper", "label": "Physics-Informed Neural Networks for Minimising Worst-Case Violations in DC Optimal Power Flow", "url": "https://arxiv.org/abs/2107.00465", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2021-06-28"}
{"type": "node", "id": "author:rahul_nellikkath", "kind": "person", "label": "Rahul Nellikkath", "url": "https://arxiv.org/a/rahul_nellikkath", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:spyros_chatzivasileiadis", "kind": "person", "label": "Spyros Chatzivasileiadis", "url": "https://arxiv.org/a/spyros_chatzivasileiadis", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2009.04544", "kind": "paper", "label": "Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism", "url": "https://arxiv.org/abs/2009.04544", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2020-09-07"}
{"type": "node", "id": "author:levi_mcclenny", "kind": "person", "label": "Levi McClenny", "url": "https://arxiv.org/a/levi_mcclenny", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:ulisses_braga_neto", "kind": "person", "label": "Ulisses Braga-Neto", "url": "https://arxiv.org/a/ulisses_braga_neto", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2501.04013", "kind": "paper", "label": "Convergence of Physics-Informed Neural Networks for Fully Nonlinear PDE's", "url": "https://arxiv.org/abs/2501.04013", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2024-12-19"}
{"type": "node", "id": "author:avetik_arakelyan", "kind": "person", "label": "Avetik Arakelyan", "url": "https://arxiv.org/a/avetik_arakelyan", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:rafayel_barkhudaryan", "kind": "person", "label": "Rafayel Barkhudaryan", "url": "https://arxiv.org/a/rafayel_barkhudaryan", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2408.16969", "kind": "paper", "label": "Point Neuron Learning: A New Physics-Informed Neural Network Architecture", "url": "https://arxiv.org/abs/2408.16969", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2024-08-30"}
{"type": "node", "id": "author:hanwen_bi", "kind": "person", "label": "Hanwen Bi", "url": "https://arxiv.org/a/hanwen_bi", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:thushara_d_abhayapala", "kind": "person", "label": "Thushara D. Abhayapala", "url": "https://arxiv.org/a/thushara_d_abhayapala", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2604.23003", "kind": "paper", "label": "Collocation-based Robust Physics Informed Neural Networks for time-dependent simulations of pollution propagation under thermal inversion conditions on Spitsbergen", "url": "https://arxiv.org/abs/2604.23003", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2026-04-24"}
{"type": "node", "id": "author:leszek_siwik", "kind": "person", "label": "Leszek Siwik", "url": "https://arxiv.org/a/leszek_siwik", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:maciej_sikora", "kind": "person", "label": "Maciej Sikora", "url": "https://arxiv.org/a/maciej_sikora", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:natalia_leszczy_ska", "kind": "person", "label": "Natalia Leszczy\u0144ska", "url": "https://arxiv.org/a/natalia_leszczy_ska", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:tomasz_maciej_ciesielski", "kind": "person", "label": "Tomasz Maciej Ciesielski", "url": "https://arxiv.org/a/tomasz_maciej_ciesielski", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:eirik_valseth", "kind": "person", "label": "Eirik Valseth", "url": "https://arxiv.org/a/eirik_valseth", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2302.08332", "kind": "paper", "label": "Magnetohydrodynamics with Physics Informed Neural Operators", "url": "https://arxiv.org/abs/2302.08332", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2023-02-13"}
{"type": "node", "id": "author:shawn_g_rosofsky", "kind": "person", "label": "Shawn G. Rosofsky", "url": "https://arxiv.org/a/shawn_g_rosofsky", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:e_a_huerta", "kind": "person", "label": "E. A. Huerta", "url": "https://arxiv.org/a/e_a_huerta", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2509.13425", "kind": "paper", "label": "Unified Spatiotemporal Physics-Informed Learning (USPIL): A Framework for Modeling Complex Predator-Prey Dynamics", "url": "https://arxiv.org/abs/2509.13425", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2025-09-16"}
{"type": "node", "id": "author:julian_evan_chrisnanto", "kind": "person", "label": "Julian Evan Chrisnanto", "url": "https://arxiv.org/a/julian_evan_chrisnanto", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:salsabila_rahma_alia", "kind": "person", "label": "Salsabila Rahma Alia", "url": "https://arxiv.org/a/salsabila_rahma_alia", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:yulison_herry_chrisnanto", "kind": "person", "label": "Yulison Herry Chrisnanto", "url": "https://arxiv.org/a/yulison_herry_chrisnanto", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:ferry_faizal", "kind": "person", "label": "Ferry Faizal", "url": "https://arxiv.org/a/ferry_faizal", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2509.18131", "kind": "paper", "label": "Randomness and signal propagation in physics-informed neural networks (PINNs): A neural PDE perspective", "url": "https://arxiv.org/abs/2509.18131", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2025-09-12"}
{"type": "node", "id": "author:jean_michel_tucny", "kind": "person", "label": "Jean-Michel Tucny", "url": "https://arxiv.org/a/jean_michel_tucny", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:abhisek_ganguly", "kind": "person", "label": "Abhisek Ganguly", "url": "https://arxiv.org/a/abhisek_ganguly", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:santosh_ansumali", "kind": "person", "label": "Santosh Ansumali", "url": "https://arxiv.org/a/santosh_ansumali", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:sauro_succi", "kind": "person", "label": "Sauro Succi", "url": "https://arxiv.org/a/sauro_succi", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2512.22189", "kind": "paper", "label": "Physics-Informed Machine Learning for Transformer Condition Monitoring -- Part II: Physics-Informed Neural Networks and Uncertainty Quantification", "url": "https://arxiv.org/abs/2512.22189", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2025-12-20"}
{"type": "node", "id": "author:jose_i_aizpurua", "kind": "person", "label": "Jose I. Aizpurua", "url": "https://arxiv.org/a/jose_i_aizpurua", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:2604.20731", "kind": "paper", "label": "CO$_2$ sequestration hybrid solver using isogeometric alternating-directions and collocation-based robust variational physics informed neural networks (IGA-ADS-CRVPINN)", "url": "https://arxiv.org/abs/2604.20731", "source": "arxiv", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "published": "2026-04-22"}
{"type": "node", "id": "author:askold_vilkha", "kind": "person", "label": "Askold Vilkha", "url": "https://arxiv.org/a/askold_vilkha", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:tomasz_s_u_alec", "kind": "person", "label": "Tomasz S\u0142u\u017calec", "url": "https://arxiv.org/a/tomasz_s_u_alec", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:marcin_o", "kind": "person", "label": "Marcin \u0141o\u015b", "url": "https://arxiv.org/a/marcin_o", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "author:maciej_paszy_ski", "kind": "person", "label": "Maciej Paszy\u0144ski", "url": "https://arxiv.org/a/maciej_paszy_ski", "source": "arxiv-author", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "paper:1311.2485", "kind": "paper", "label": "Continuous-time quantum error correction", "url": "https://arxiv.org/abs/1311.2485", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2013-11-11"}
{"type": "node", "id": "author:ognyan_oreshkov", "kind": "person", "label": "Ognyan Oreshkov", "url": "https://arxiv.org/a/ognyan_oreshkov", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:2605.17156", "kind": "paper", "label": "Sparse Mamba Decoder for Quantum Error Correction: Efficient Defect-Centric Processing of Surface Code Syndromes", "url": "https://arxiv.org/abs/2605.17156", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2026-05-16"}
{"type": "node", "id": "author:samira_sayedsalehi", "kind": "person", "label": "Samira Sayedsalehi", "url": "https://arxiv.org/a/samira_sayedsalehi", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:nader_bagherzadeh", "kind": "person", "label": "Nader Bagherzadeh", "url": "https://arxiv.org/a/nader_bagherzadeh", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:maxim_shcherbakov", "kind": "person", "label": "Maxim Shcherbakov", "url": "https://arxiv.org/a/maxim_shcherbakov", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:jean_luc_gaudiot", "kind": "person", "label": "Jean-Luc Gaudiot", "url": "https://arxiv.org/a/jean_luc_gaudiot", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:1610.04013", "kind": "paper", "label": "Entanglement-Assisted Quantum Error-Correcting Codes", "url": "https://arxiv.org/abs/1610.04013", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2016-10-13"}
{"type": "node", "id": "author:todd_brun", "kind": "person", "label": "Todd Brun", "url": "https://arxiv.org/a/todd_brun", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:min_hsiu_hsieh", "kind": "person", "label": "Min-Hsiu Hsieh", "url": "https://arxiv.org/a/min_hsiu_hsieh", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:hsun_hsien_chang", "kind": "person", "label": "Hsun-Hsien Chang", "url": "https://arxiv.org/a/hsun_hsien_chang", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:a_m_steane", "kind": "person", "label": "A. M. Steane", "url": "https://arxiv.org/a/a_m_steane", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:0811.3734", "kind": "paper", "label": "Quantum error correction beyond qubits", "url": "https://arxiv.org/abs/0811.3734", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2008-11-24"}
{"type": "node", "id": "author:takao_aoki", "kind": "person", "label": "Takao Aoki", "url": "https://arxiv.org/a/takao_aoki", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:go_takahashi", "kind": "person", "label": "Go Takahashi", "url": "https://arxiv.org/a/go_takahashi", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:tadashi_kajiya", "kind": "person", "label": "Tadashi Kajiya", "url": "https://arxiv.org/a/tadashi_kajiya", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:jun_ichi_yoshikawa", "kind": "person", "label": "Jun-ichi Yoshikawa", "url": "https://arxiv.org/a/jun_ichi_yoshikawa", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:samuel_l_braunstein", "kind": "person", "label": "Samuel L. Braunstein", "url": "https://arxiv.org/a/samuel_l_braunstein", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:1910.03672", "kind": "paper", "label": "Quantum Error Correction", "url": "https://arxiv.org/abs/1910.03672", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2019-10-08"}
{"type": "node", "id": "author:todd_a_brun", "kind": "person", "label": "Todd A. Brun", "url": "https://arxiv.org/a/todd_a_brun", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:2311.00487", "kind": "paper", "label": "Echo-evolution data generation for quantum error mitigation via neural networks", "url": "https://arxiv.org/abs/2311.00487", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2023-11-01"}
{"type": "node", "id": "author:d_v_babukhin", "kind": "person", "label": "D. V. Babukhin", "url": "https://arxiv.org/a/d_v_babukhin", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:2504.19833", "kind": "paper", "label": "Quantum Error Correction in Quaternionic Hilbert Spaces", "url": "https://arxiv.org/abs/2504.19833", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2025-04-28"}
{"type": "node", "id": "author:valentine_nyirahafashimana", "kind": "person", "label": "Valentine Nyirahafashimana", "url": "https://arxiv.org/a/valentine_nyirahafashimana", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:nurisya_mohd_shah", "kind": "person", "label": "Nurisya Mohd Shah", "url": "https://arxiv.org/a/nurisya_mohd_shah", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:umair_abdul_halim", "kind": "person", "label": "Umair Abdul Halim", "url": "https://arxiv.org/a/umair_abdul_halim", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:mohamed_othman", "kind": "person", "label": "Mohamed Othman", "url": "https://arxiv.org/a/mohamed_othman", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:sharifah_kartini_said_husain", "kind": "person", "label": "Sharifah Kartini Said Husain", "url": "https://arxiv.org/a/sharifah_kartini_said_husain", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:1307.5893", "kind": "paper", "label": "Error suppression and error correction in adiabatic quantum computation I: techniques and challenges", "url": "https://arxiv.org/abs/1307.5893", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2013-07-22"}
{"type": "node", "id": "author:kevin_c_young", "kind": "person", "label": "Kevin C. Young", "url": "https://arxiv.org/a/kevin_c_young", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:mohan_sarovar", "kind": "person", "label": "Mohan Sarovar", "url": "https://arxiv.org/a/mohan_sarovar", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:robin_blume_kohout", "kind": "person", "label": "Robin Blume-Kohout", "url": "https://arxiv.org/a/robin_blume_kohout", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:1307.5892", "kind": "paper", "label": "Error suppression and error correction in adiabatic quantum computation II: non-equilibrium dynamics", "url": "https://arxiv.org/abs/1307.5892", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2013-07-22"}
{"type": "node", "id": "paper:1907.10552", "kind": "paper", "label": "A neural network oracle for quantum nonlocality problems in networks", "url": "https://arxiv.org/abs/1907.10552", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2019-07-24"}
{"type": "node", "id": "author:tam_s_kriv_chy", "kind": "person", "label": "Tam\u00e1s Kriv\u00e1chy", "url": "https://arxiv.org/a/tam_s_kriv_chy", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:yu_cai", "kind": "person", "label": "Yu Cai", "url": "https://arxiv.org/a/yu_cai", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:daniel_cavalcanti", "kind": "person", "label": "Daniel Cavalcanti", "url": "https://arxiv.org/a/daniel_cavalcanti", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:arash_tavakoli", "kind": "person", "label": "Arash Tavakoli", "url": "https://arxiv.org/a/arash_tavakoli", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:nicolas_gisin", "kind": "person", "label": "Nicolas Gisin", "url": "https://arxiv.org/a/nicolas_gisin", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:2304.07362", "kind": "paper", "label": "The END: An Equivariant Neural Decoder for Quantum Error Correction", "url": "https://arxiv.org/abs/2304.07362", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2023-04-14"}
{"type": "node", "id": "author:evgenii_egorov", "kind": "person", "label": "Evgenii Egorov", "url": "https://arxiv.org/a/evgenii_egorov", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:roberto_bondesan", "kind": "person", "label": "Roberto Bondesan", "url": "https://arxiv.org/a/roberto_bondesan", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:max_welling", "kind": "person", "label": "Max Welling", "url": "https://arxiv.org/a/max_welling", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:2601.07522", "kind": "paper", "label": "Thermodynamic Recycling of Algorithmic Failure Branches: Quantum-Computer Demonstration with Quantum Error Correction", "url": "https://arxiv.org/abs/2601.07522", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2026-01-12"}
{"type": "node", "id": "author:nobumasa_ishida", "kind": "person", "label": "Nobumasa Ishida", "url": "https://arxiv.org/a/nobumasa_ishida", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:yoshihiko_hasegawa", "kind": "person", "label": "Yoshihiko Hasegawa", "url": "https://arxiv.org/a/yoshihiko_hasegawa", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:1810.13348", "kind": "paper", "label": "Multimodal Machine Learning for Automated ICD Coding", "url": "https://arxiv.org/abs/1810.13348", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2018-10-31"}
{"type": "node", "id": "author:keyang_xu", "kind": "person", "label": "Keyang Xu", "url": "https://arxiv.org/a/keyang_xu", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:mike_lam", "kind": "person", "label": "Mike Lam", "url": "https://arxiv.org/a/mike_lam", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:jingzhi_pang", "kind": "person", "label": "Jingzhi Pang", "url": "https://arxiv.org/a/jingzhi_pang", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:xin_gao", "kind": "person", "label": "Xin Gao", "url": "https://arxiv.org/a/xin_gao", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:charlotte_band", "kind": "person", "label": "Charlotte Band", "url": "https://arxiv.org/a/charlotte_band", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:2512.07737", "kind": "paper", "label": "A scalable and real-time neural decoder for topological quantum codes", "url": "https://arxiv.org/abs/2512.07737", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2025-12-08"}
{"type": "node", "id": "author:andrew_w_senior", "kind": "person", "label": "Andrew W. Senior", "url": "https://arxiv.org/a/andrew_w_senior", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:thomas_edlich", "kind": "person", "label": "Thomas Edlich", "url": "https://arxiv.org/a/thomas_edlich", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:francisco_j_h_heras", "kind": "person", "label": "Francisco J. H. Heras", "url": "https://arxiv.org/a/francisco_j_h_heras", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:lei_m_zhang", "kind": "person", "label": "Lei M. Zhang", "url": "https://arxiv.org/a/lei_m_zhang", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:oscar_higgott", "kind": "person", "label": "Oscar Higgott", "url": "https://arxiv.org/a/oscar_higgott", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:1908.02829", "kind": "paper", "label": "Kitaev's quantum double model as an error correcting code", "url": "https://arxiv.org/abs/1908.02829", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2019-08-07"}
{"type": "node", "id": "author:shawn_x_cui", "kind": "person", "label": "Shawn X. Cui", "url": "https://arxiv.org/a/shawn_x_cui", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:dawei_ding", "kind": "person", "label": "Dawei Ding", "url": "https://arxiv.org/a/dawei_ding", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:xizhi_han", "kind": "person", "label": "Xizhi Han", "url": "https://arxiv.org/a/xizhi_han", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:geoffrey_penington", "kind": "person", "label": "Geoffrey Penington", "url": "https://arxiv.org/a/geoffrey_penington", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:daniel_ranard", "kind": "person", "label": "Daniel Ranard", "url": "https://arxiv.org/a/daniel_ranard", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:2304.11442", "kind": "paper", "label": "Stabilizer Formalism for Operator Algebra Quantum Error Correction", "url": "https://arxiv.org/abs/2304.11442", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2023-04-22"}
{"type": "node", "id": "author:guillaume_dauphinais", "kind": "person", "label": "Guillaume Dauphinais", "url": "https://arxiv.org/a/guillaume_dauphinais", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:david_w_kribs", "kind": "person", "label": "David W. Kribs", "url": "https://arxiv.org/a/david_w_kribs", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:michael_vasmer", "kind": "person", "label": "Michael Vasmer", "url": "https://arxiv.org/a/michael_vasmer", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:2203.09234", "kind": "paper", "label": "Autonomous Quantum Error Correction in a Four-Photon Kerr Parametric Oscillator", "url": "https://arxiv.org/abs/2203.09234", "source": "arxiv", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "published": "2022-03-17"}
{"type": "node", "id": "author:sangil_kwon", "kind": "person", "label": "Sangil Kwon", "url": "https://arxiv.org/a/sangil_kwon", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:shohei_watabe", "kind": "person", "label": "Shohei Watabe", "url": "https://arxiv.org/a/shohei_watabe", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:jaw_shen_tsai", "kind": "person", "label": "Jaw-Shen Tsai", "url": "https://arxiv.org/a/jaw_shen_tsai", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "author:a_j_scott", "kind": "person", "label": "A. J. Scott", "url": "https://arxiv.org/a/a_j_scott", "source": "arxiv-author", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "paper:2306.00978", "kind": "paper", "label": "AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration", "url": "https://arxiv.org/abs/2306.00978", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2023-06-01"}
{"type": "node", "id": "author:ji_lin", "kind": "person", "label": "Ji Lin", "url": "https://arxiv.org/a/ji_lin", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jiaming_tang", "kind": "person", "label": "Jiaming Tang", "url": "https://arxiv.org/a/jiaming_tang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:haotian_tang", "kind": "person", "label": "Haotian Tang", "url": "https://arxiv.org/a/haotian_tang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:shang_yang", "kind": "person", "label": "Shang Yang", "url": "https://arxiv.org/a/shang_yang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:wei_ming_chen", "kind": "person", "label": "Wei-Ming Chen", "url": "https://arxiv.org/a/wei_ming_chen", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2605.08692", "kind": "paper", "label": "AAAC: Activation-Aware Adaptive Codebooks for 4-bit LLM Weight Quantization", "url": "https://arxiv.org/abs/2605.08692", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2026-05-09"}
{"type": "node", "id": "author:beshr_islambouli", "kind": "person", "label": "Beshr IslamBouli", "url": "https://arxiv.org/a/beshr_islambouli", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:david_jin", "kind": "person", "label": "David Jin", "url": "https://arxiv.org/a/david_jin", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2506.10205", "kind": "paper", "label": "AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent", "url": "https://arxiv.org/abs/2506.10205", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2025-06-11"}
{"type": "node", "id": "author:jing_liu", "kind": "person", "label": "Jing Liu", "url": "https://arxiv.org/a/jing_liu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:toshiaki_koike_akino", "kind": "person", "label": "Toshiaki Koike-Akino", "url": "https://arxiv.org/a/toshiaki_koike_akino", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:ye_wang", "kind": "person", "label": "Ye Wang", "url": "https://arxiv.org/a/ye_wang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:hassan_mansour", "kind": "person", "label": "Hassan Mansour", "url": "https://arxiv.org/a/hassan_mansour", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:matthew_brand", "kind": "person", "label": "Matthew Brand", "url": "https://arxiv.org/a/matthew_brand", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2605.26339", "kind": "paper", "label": "QAM-W: Joint 2D Codebook Quantization for LLM Weights via Hadamard Rotation and Activation-Aware Scaling", "url": "https://arxiv.org/abs/2605.26339", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2026-05-25"}
{"type": "node", "id": "author:preetam_sharma", "kind": "person", "label": "Preetam Sharma", "url": "https://arxiv.org/a/preetam_sharma", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:kacper_dobek", "kind": "person", "label": "Kacper Dobek", "url": "https://arxiv.org/a/kacper_dobek", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2606.05868", "kind": "paper", "label": "YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition", "url": "https://arxiv.org/abs/2606.05868", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2026-06-04"}
{"type": "node", "id": "author:psbc_llm_team", "kind": "person", "label": "PSBC LLM Team", "url": "https://arxiv.org/a/psbc_llm_team", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:huawei_llm_team", "kind": "person", "label": "Huawei LLM Team", "url": "https://arxiv.org/a/huawei_llm_team", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:ruihan_long", "kind": "person", "label": "Ruihan Long", "url": "https://arxiv.org/a/ruihan_long", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:junjie_wu", "kind": "person", "label": "Junjie Wu", "url": "https://arxiv.org/a/junjie_wu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:tianan_zhang", "kind": "person", "label": "Tianan Zhang", "url": "https://arxiv.org/a/tianan_zhang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2505.14302", "kind": "paper", "label": "Scaling Law for Quantization-Aware Training", "url": "https://arxiv.org/abs/2505.14302", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2025-05-20"}
{"type": "node", "id": "author:mengzhao_chen", "kind": "person", "label": "Mengzhao Chen", "url": "https://arxiv.org/a/mengzhao_chen", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:chaoyi_zhang", "kind": "person", "label": "Chaoyi Zhang", "url": "https://arxiv.org/a/chaoyi_zhang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yutao_zeng", "kind": "person", "label": "Yutao Zeng", "url": "https://arxiv.org/a/yutao_zeng", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:zeyue_xue", "kind": "person", "label": "Zeyue Xue", "url": "https://arxiv.org/a/zeyue_xue", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2504.05352", "kind": "paper", "label": "Achieving binary weight and activation for LLMs using Post-Training Quantization", "url": "https://arxiv.org/abs/2504.05352", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2025-04-07"}
{"type": "node", "id": "author:siqing_song", "kind": "person", "label": "Siqing Song", "url": "https://arxiv.org/a/siqing_song", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:chuang_wang", "kind": "person", "label": "Chuang Wang", "url": "https://arxiv.org/a/chuang_wang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:ruiqi_wang", "kind": "person", "label": "Ruiqi Wang", "url": "https://arxiv.org/a/ruiqi_wang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yi_yang", "kind": "person", "label": "Yi Yang", "url": "https://arxiv.org/a/yi_yang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:xu_yao_zhang", "kind": "person", "label": "Xu-Yao Zhang", "url": "https://arxiv.org/a/xu_yao_zhang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2406.16299", "kind": "paper", "label": "Compensate Quantization Errors: Make Weights Hierarchical to Compensate Each Other", "url": "https://arxiv.org/abs/2406.16299", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2024-06-24"}
{"type": "node", "id": "author:yifei_gao", "kind": "person", "label": "Yifei Gao", "url": "https://arxiv.org/a/yifei_gao", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jie_ou", "kind": "person", "label": "Jie Ou", "url": "https://arxiv.org/a/jie_ou", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yuting_xiao", "kind": "person", "label": "Yuting Xiao", "url": "https://arxiv.org/a/yuting_xiao", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:zhiyuan_xiang", "kind": "person", "label": "Zhiyuan Xiang", "url": "https://arxiv.org/a/zhiyuan_xiang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2407.15508", "kind": "paper", "label": "Compensate Quantization Errors+: Quantized Models Are Inquisitive Learners", "url": "https://arxiv.org/abs/2407.15508", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2024-07-22"}
{"type": "node", "id": "author:jun_cheng", "kind": "person", "label": "Jun Cheng", "url": "https://arxiv.org/a/jun_cheng", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:mengchu_zhou", "kind": "person", "label": "Mengchu Zhou", "url": "https://arxiv.org/a/mengchu_zhou", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2405.04532", "kind": "paper", "label": "QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving", "url": "https://arxiv.org/abs/2405.04532", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2024-05-07"}
{"type": "node", "id": "author:yujun_lin", "kind": "person", "label": "Yujun Lin", "url": "https://arxiv.org/a/yujun_lin", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:zhekai_zhang", "kind": "person", "label": "Zhekai Zhang", "url": "https://arxiv.org/a/zhekai_zhang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:guangxuan_xiao", "kind": "person", "label": "Guangxuan Xiao", "url": "https://arxiv.org/a/guangxuan_xiao", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2601.22873", "kind": "paper", "label": "EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis", "url": "https://arxiv.org/abs/2601.22873", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2026-01-30"}
{"type": "node", "id": "author:li_zhou", "kind": "person", "label": "Li Zhou", "url": "https://arxiv.org/a/li_zhou", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:hao_jiang", "kind": "person", "label": "Hao Jiang", "url": "https://arxiv.org/a/hao_jiang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:junjie_li", "kind": "person", "label": "Junjie Li", "url": "https://arxiv.org/a/junjie_li", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:tianrui_wang", "kind": "person", "label": "Tianrui Wang", "url": "https://arxiv.org/a/tianrui_wang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:haizhou_li", "kind": "person", "label": "Haizhou Li", "url": "https://arxiv.org/a/haizhou_li", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2402.12065", "kind": "paper", "label": "WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More", "url": "https://arxiv.org/abs/2402.12065", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2024-02-19"}
{"type": "node", "id": "author:yuxuan_yue", "kind": "person", "label": "Yuxuan Yue", "url": "https://arxiv.org/a/yuxuan_yue", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:haojie_duanmu", "kind": "person", "label": "Haojie Duanmu", "url": "https://arxiv.org/a/haojie_duanmu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:sifan_zhou", "kind": "person", "label": "Sifan Zhou", "url": "https://arxiv.org/a/sifan_zhou", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jianlong_wu", "kind": "person", "label": "Jianlong Wu", "url": "https://arxiv.org/a/jianlong_wu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2603.19296", "kind": "paper", "label": "TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference On The Fly", "url": "https://arxiv.org/abs/2603.19296", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2026-03-11"}
{"type": "node", "id": "paper:2407.08044", "kind": "paper", "label": "RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization", "url": "https://arxiv.org/abs/2407.08044", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2024-07-10"}
{"type": "node", "id": "author:xijie_huang", "kind": "person", "label": "Xijie Huang", "url": "https://arxiv.org/a/xijie_huang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:zechun_liu", "kind": "person", "label": "Zechun Liu", "url": "https://arxiv.org/a/zechun_liu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:shih_yang_liu", "kind": "person", "label": "Shih-Yang Liu", "url": "https://arxiv.org/a/shih_yang_liu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:kwang_ting_cheng", "kind": "person", "label": "Kwang-Ting Cheng", "url": "https://arxiv.org/a/kwang_ting_cheng", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:1702.03044", "kind": "paper", "label": "Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights", "url": "https://arxiv.org/abs/1702.03044", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2017-02-10"}
{"type": "node", "id": "author:aojun_zhou", "kind": "person", "label": "Aojun Zhou", "url": "https://arxiv.org/a/aojun_zhou", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:anbang_yao", "kind": "person", "label": "Anbang Yao", "url": "https://arxiv.org/a/anbang_yao", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yiwen_guo", "kind": "person", "label": "Yiwen Guo", "url": "https://arxiv.org/a/yiwen_guo", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:lin_xu", "kind": "person", "label": "Lin Xu", "url": "https://arxiv.org/a/lin_xu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yurong_chen", "kind": "person", "label": "Yurong Chen", "url": "https://arxiv.org/a/yurong_chen", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2210.17323", "kind": "paper", "label": "GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers", "url": "https://arxiv.org/abs/2210.17323", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2022-10-31"}
{"type": "node", "id": "author:elias_frantar", "kind": "person", "label": "Elias Frantar", "url": "https://arxiv.org/a/elias_frantar", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:saleh_ashkboos", "kind": "person", "label": "Saleh Ashkboos", "url": "https://arxiv.org/a/saleh_ashkboos", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:torsten_hoefler", "kind": "person", "label": "Torsten Hoefler", "url": "https://arxiv.org/a/torsten_hoefler", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:dan_alistarh", "kind": "person", "label": "Dan Alistarh", "url": "https://arxiv.org/a/dan_alistarh", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2507.18553", "kind": "paper", "label": "The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm", "url": "https://arxiv.org/abs/2507.18553", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2025-07-24"}
{"type": "node", "id": "author:jiale_chen", "kind": "person", "label": "Jiale Chen", "url": "https://arxiv.org/a/jiale_chen", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yalda_shabanzadeh", "kind": "person", "label": "Yalda Shabanzadeh", "url": "https://arxiv.org/a/yalda_shabanzadeh", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:elvir_crn_evi", "kind": "person", "label": "Elvir Crn\u010devi\u0107", "url": "https://arxiv.org/a/elvir_crn_evi", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2406.08155", "kind": "paper", "label": "QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts", "url": "https://arxiv.org/abs/2406.08155", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2024-06-12"}
{"type": "node", "id": "author:pingzhi_li", "kind": "person", "label": "Pingzhi Li", "url": "https://arxiv.org/a/pingzhi_li", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:xiaolong_jin", "kind": "person", "label": "Xiaolong Jin", "url": "https://arxiv.org/a/xiaolong_jin", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:zhen_tan", "kind": "person", "label": "Zhen Tan", "url": "https://arxiv.org/a/zhen_tan", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yu_cheng", "kind": "person", "label": "Yu Cheng", "url": "https://arxiv.org/a/yu_cheng", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:tianlong_chen", "kind": "person", "label": "Tianlong Chen", "url": "https://arxiv.org/a/tianlong_chen", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2509.16989", "kind": "paper", "label": "PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models", "url": "https://arxiv.org/abs/2509.16989", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2025-09-21"}
{"type": "node", "id": "author:he_xiao", "kind": "person", "label": "He Xiao", "url": "https://arxiv.org/a/he_xiao", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:runming_yang", "kind": "person", "label": "Runming Yang", "url": "https://arxiv.org/a/runming_yang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:qingyao_yang", "kind": "person", "label": "Qingyao Yang", "url": "https://arxiv.org/a/qingyao_yang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:wendong_xu", "kind": "person", "label": "Wendong Xu", "url": "https://arxiv.org/a/wendong_xu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:zhen_li", "kind": "person", "label": "Zhen Li", "url": "https://arxiv.org/a/zhen_li", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2508.03332", "kind": "paper", "label": "Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models", "url": "https://arxiv.org/abs/2508.03332", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2025-08-05"}
{"type": "node", "id": "author:dirui_xie", "kind": "person", "label": "Dirui Xie", "url": "https://arxiv.org/a/dirui_xie", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:zunhai_su", "kind": "person", "label": "Zunhai Su", "url": "https://arxiv.org/a/zunhai_su", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2606.01412", "kind": "paper", "label": "GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation", "url": "https://arxiv.org/abs/2606.01412", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2026-05-31"}
{"type": "node", "id": "author:shihao_zhang", "kind": "person", "label": "Shihao Zhang", "url": "https://arxiv.org/a/shihao_zhang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:rayan_saab", "kind": "person", "label": "Rayan Saab", "url": "https://arxiv.org/a/rayan_saab", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2605.09430", "kind": "paper", "label": "FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation", "url": "https://arxiv.org/abs/2605.09430", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2026-05-10"}
{"type": "node", "id": "author:junkang_zhou", "kind": "person", "label": "Junkang Zhou", "url": "https://arxiv.org/a/junkang_zhou", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yefei_he", "kind": "person", "label": "Yefei He", "url": "https://arxiv.org/a/yefei_he", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:feng_chen", "kind": "person", "label": "Feng Chen", "url": "https://arxiv.org/a/feng_chen", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:weijie_wang", "kind": "person", "label": "Weijie Wang", "url": "https://arxiv.org/a/weijie_wang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:bohan_zhuang", "kind": "person", "label": "Bohan Zhuang", "url": "https://arxiv.org/a/bohan_zhuang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2505.02351", "kind": "paper", "label": "Opt-GPTQ: An Optimized GPTQ Combining Sparse Attention and Quantization Techniques", "url": "https://arxiv.org/abs/2505.02351", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2025-05-05"}
{"type": "node", "id": "author:jie_kong", "kind": "person", "label": "Jie Kong", "url": "https://arxiv.org/a/jie_kong", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:junxiang_zhang", "kind": "person", "label": "Junxiang Zhang", "url": "https://arxiv.org/a/junxiang_zhang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jiheng_xu", "kind": "person", "label": "Jiheng Xu", "url": "https://arxiv.org/a/jiheng_xu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yalong_li", "kind": "person", "label": "Yalong Li", "url": "https://arxiv.org/a/yalong_li", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:shouhua_zhang", "kind": "person", "label": "Shouhua Zhang", "url": "https://arxiv.org/a/shouhua_zhang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2502.21321", "kind": "paper", "label": "LLM Post-Training: A Deep Dive into Reasoning Large Language Models", "url": "https://arxiv.org/abs/2502.21321", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2025-02-28"}
{"type": "node", "id": "author:komal_kumar", "kind": "person", "label": "Komal Kumar", "url": "https://arxiv.org/a/komal_kumar", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:tajamul_ashraf", "kind": "person", "label": "Tajamul Ashraf", "url": "https://arxiv.org/a/tajamul_ashraf", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:omkar_thawakar", "kind": "person", "label": "Omkar Thawakar", "url": "https://arxiv.org/a/omkar_thawakar", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:rao_muhammad_anwer", "kind": "person", "label": "Rao Muhammad Anwer", "url": "https://arxiv.org/a/rao_muhammad_anwer", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:hisham_cholakkal", "kind": "person", "label": "Hisham Cholakkal", "url": "https://arxiv.org/a/hisham_cholakkal", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2509.12991", "kind": "paper", "label": "Bridging Performance Gaps for ECG Foundation Models: A Post-Training Strategy", "url": "https://arxiv.org/abs/2509.12991", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2025-09-16"}
{"type": "node", "id": "author:ya_zhou", "kind": "person", "label": "Ya Zhou", "url": "https://arxiv.org/a/ya_zhou", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yujie_yang", "kind": "person", "label": "Yujie Yang", "url": "https://arxiv.org/a/yujie_yang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:xiaohan_fan", "kind": "person", "label": "Xiaohan Fan", "url": "https://arxiv.org/a/xiaohan_fan", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:wei_zhao", "kind": "person", "label": "Wei Zhao", "url": "https://arxiv.org/a/wei_zhao", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2308.07662", "kind": "paper", "label": "Gradient-Based Post-Training Quantization: Challenging the Status Quo", "url": "https://arxiv.org/abs/2308.07662", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2023-08-15"}
{"type": "node", "id": "author:edouard_yvinec", "kind": "person", "label": "Edouard Yvinec", "url": "https://arxiv.org/a/edouard_yvinec", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:arnaud_dapogny", "kind": "person", "label": "Arnaud Dapogny", "url": "https://arxiv.org/a/arnaud_dapogny", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:kevin_bailly", "kind": "person", "label": "Kevin Bailly", "url": "https://arxiv.org/a/kevin_bailly", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2601.11663", "kind": "paper", "label": "Activation Sensitivity as a Unifying Principle for Post-Training Quantization", "url": "https://arxiv.org/abs/2601.11663", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2026-01-15"}
{"type": "node", "id": "author:bruce_changlong_xu", "kind": "person", "label": "Bruce Changlong Xu", "url": "https://arxiv.org/a/bruce_changlong_xu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:1911.07190", "kind": "paper", "label": "Loss Aware Post-training Quantization", "url": "https://arxiv.org/abs/1911.07190", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2019-11-17"}
{"type": "node", "id": "author:yury_nahshan", "kind": "person", "label": "Yury Nahshan", "url": "https://arxiv.org/a/yury_nahshan", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:brian_chmiel", "kind": "person", "label": "Brian Chmiel", "url": "https://arxiv.org/a/brian_chmiel", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:chaim_baskin", "kind": "person", "label": "Chaim Baskin", "url": "https://arxiv.org/a/chaim_baskin", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:evgenii_zheltonozhskii", "kind": "person", "label": "Evgenii Zheltonozhskii", "url": "https://arxiv.org/a/evgenii_zheltonozhskii", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:ron_banner", "kind": "person", "label": "Ron Banner", "url": "https://arxiv.org/a/ron_banner", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2605.11222", "kind": "paper", "label": "ADMM-Q: An Improved Hessian-based Weight Quantizer for Post-Training Quantization of Large Language Models", "url": "https://arxiv.org/abs/2605.11222", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2026-05-11"}
{"type": "node", "id": "author:ryan_lucas", "kind": "person", "label": "Ryan Lucas", "url": "https://arxiv.org/a/ryan_lucas", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:mehdi_makni", "kind": "person", "label": "Mehdi Makni", "url": "https://arxiv.org/a/mehdi_makni", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:xiang_meng", "kind": "person", "label": "Xiang Meng", "url": "https://arxiv.org/a/xiang_meng", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:adam_deng", "kind": "person", "label": "Adam Deng", "url": "https://arxiv.org/a/adam_deng", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:rahul_mazumder", "kind": "person", "label": "Rahul Mazumder", "url": "https://arxiv.org/a/rahul_mazumder", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2410.05265", "kind": "paper", "label": "PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization", "url": "https://arxiv.org/abs/2410.05265", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2024-10-07"}
{"type": "node", "id": "author:yi_liu", "kind": "person", "label": "Yi Liu", "url": "https://arxiv.org/a/yi_liu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jiahao_wang", "kind": "person", "label": "Jiahao Wang", "url": "https://arxiv.org/a/jiahao_wang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yi_bin", "kind": "person", "label": "Yi Bin", "url": "https://arxiv.org/a/yi_bin", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:wenqi_shao", "kind": "person", "label": "Wenqi Shao", "url": "https://arxiv.org/a/wenqi_shao", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2405.11357", "kind": "paper", "label": "Large Language Models Lack Understanding of Character Composition of Words", "url": "https://arxiv.org/abs/2405.11357", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2024-05-18"}
{"type": "node", "id": "author:andrew_shin", "kind": "person", "label": "Andrew Shin", "url": "https://arxiv.org/a/andrew_shin", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:kunitake_kaneko", "kind": "person", "label": "Kunitake Kaneko", "url": "https://arxiv.org/a/kunitake_kaneko", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2312.05434", "kind": "paper", "label": "Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models", "url": "https://arxiv.org/abs/2312.05434", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2023-12-09"}
{"type": "node", "id": "author:hongzhan_lin", "kind": "person", "label": "Hongzhan Lin", "url": "https://arxiv.org/a/hongzhan_lin", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:ziyang_luo", "kind": "person", "label": "Ziyang Luo", "url": "https://arxiv.org/a/ziyang_luo", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jing_ma", "kind": "person", "label": "Jing Ma", "url": "https://arxiv.org/a/jing_ma", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:long_chen", "kind": "person", "label": "Long Chen", "url": "https://arxiv.org/a/long_chen", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2508.04848", "kind": "paper", "label": "Large Language Models Reasoning Abilities Under Non-Ideal Conditions After RL-Fine-Tuning", "url": "https://arxiv.org/abs/2508.04848", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2025-08-06"}
{"type": "node", "id": "author:chang_tian", "kind": "person", "label": "Chang Tian", "url": "https://arxiv.org/a/chang_tian", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:matthew_b_blaschko", "kind": "person", "label": "Matthew B. Blaschko", "url": "https://arxiv.org/a/matthew_b_blaschko", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:mingzhe_xing", "kind": "person", "label": "Mingzhe Xing", "url": "https://arxiv.org/a/mingzhe_xing", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:xiuxing_li", "kind": "person", "label": "Xiuxing Li", "url": "https://arxiv.org/a/xiuxing_li", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yinliang_yue", "kind": "person", "label": "Yinliang Yue", "url": "https://arxiv.org/a/yinliang_yue", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2402.14679", "kind": "paper", "label": "Is Self-knowledge and Action Consistent or Not: Investigating Large Language Model's Personality", "url": "https://arxiv.org/abs/2402.14679", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2024-02-22"}
{"type": "node", "id": "author:yiming_ai", "kind": "person", "label": "Yiming Ai", "url": "https://arxiv.org/a/yiming_ai", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:zhiwei_he", "kind": "person", "label": "Zhiwei He", "url": "https://arxiv.org/a/zhiwei_he", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:ziyin_zhang", "kind": "person", "label": "Ziyin Zhang", "url": "https://arxiv.org/a/ziyin_zhang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:wenhong_zhu", "kind": "person", "label": "Wenhong Zhu", "url": "https://arxiv.org/a/wenhong_zhu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:hongkun_hao", "kind": "person", "label": "Hongkun Hao", "url": "https://arxiv.org/a/hongkun_hao", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2306.08568", "kind": "paper", "label": "WizardCoder: Empowering Code Large Language Models with Evol-Instruct", "url": "https://arxiv.org/abs/2306.08568", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2023-06-14"}
{"type": "node", "id": "paper:2407.12036", "kind": "paper", "label": "Exploring Advanced Large Language Models with LLMsuite", "url": "https://arxiv.org/abs/2407.12036", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2024-07-01"}
{"type": "node", "id": "author:giorgio_roffo", "kind": "person", "label": "Giorgio Roffo", "url": "https://arxiv.org/a/giorgio_roffo", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:1909.13144", "kind": "paper", "label": "Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks", "url": "https://arxiv.org/abs/1909.13144", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2019-09-28"}
{"type": "node", "id": "author:yuhang_li", "kind": "person", "label": "Yuhang Li", "url": "https://arxiv.org/a/yuhang_li", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:xin_dong", "kind": "person", "label": "Xin Dong", "url": "https://arxiv.org/a/xin_dong", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:1902.06822", "kind": "paper", "label": "Low-bit Quantization of Neural Networks for Efficient Inference", "url": "https://arxiv.org/abs/1902.06822", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2019-02-18"}
{"type": "node", "id": "author:yoni_choukroun", "kind": "person", "label": "Yoni Choukroun", "url": "https://arxiv.org/a/yoni_choukroun", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:eli_kravchik", "kind": "person", "label": "Eli Kravchik", "url": "https://arxiv.org/a/eli_kravchik", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:fan_yang", "kind": "person", "label": "Fan Yang", "url": "https://arxiv.org/a/fan_yang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:pavel_kisilev", "kind": "person", "label": "Pavel Kisilev", "url": "https://arxiv.org/a/pavel_kisilev", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2605.11396", "kind": "paper", "label": "MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization", "url": "https://arxiv.org/abs/2605.11396", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2026-05-12"}
{"type": "node", "id": "author:yupeng_su", "kind": "person", "label": "Yupeng Su", "url": "https://arxiv.org/a/yupeng_su", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:ruijie_zhang", "kind": "person", "label": "Ruijie Zhang", "url": "https://arxiv.org/a/ruijie_zhang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:ziyue_liu", "kind": "person", "label": "Ziyue Liu", "url": "https://arxiv.org/a/ziyue_liu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yequan_zhao", "kind": "person", "label": "Yequan Zhao", "url": "https://arxiv.org/a/yequan_zhao", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:zheng_zhang", "kind": "person", "label": "Zheng Zhang", "url": "https://arxiv.org/a/zheng_zhang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2505.05530", "kind": "paper", "label": "Low-bit Model Quantization for Deep Neural Networks: A Survey", "url": "https://arxiv.org/abs/2505.05530", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2025-05-08"}
{"type": "node", "id": "author:kai_liu", "kind": "person", "label": "Kai Liu", "url": "https://arxiv.org/a/kai_liu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:qian_zheng", "kind": "person", "label": "Qian Zheng", "url": "https://arxiv.org/a/qian_zheng", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:kaiwen_tao", "kind": "person", "label": "Kaiwen Tao", "url": "https://arxiv.org/a/kaiwen_tao", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:zhiteng_li", "kind": "person", "label": "Zhiteng Li", "url": "https://arxiv.org/a/zhiteng_li", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:haotong_qin", "kind": "person", "label": "Haotong Qin", "url": "https://arxiv.org/a/haotong_qin", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2009.08695", "kind": "paper", "label": "Searching for Low-Bit Weights in Quantized Neural Networks", "url": "https://arxiv.org/abs/2009.08695", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2020-09-18"}
{"type": "node", "id": "author:zhaohui_yang", "kind": "person", "label": "Zhaohui Yang", "url": "https://arxiv.org/a/zhaohui_yang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:yunhe_wang", "kind": "person", "label": "Yunhe Wang", "url": "https://arxiv.org/a/yunhe_wang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:kai_han", "kind": "person", "label": "Kai Han", "url": "https://arxiv.org/a/kai_han", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:chunjing_xu", "kind": "person", "label": "Chunjing Xu", "url": "https://arxiv.org/a/chunjing_xu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:chao_xu", "kind": "person", "label": "Chao Xu", "url": "https://arxiv.org/a/chao_xu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2210.15189", "kind": "paper", "label": "Partially Oblivious Neural Network Inference", "url": "https://arxiv.org/abs/2210.15189", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2022-10-27"}
{"type": "node", "id": "author:panagiotis_rizomiliotis", "kind": "person", "label": "Panagiotis Rizomiliotis", "url": "https://arxiv.org/a/panagiotis_rizomiliotis", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:christos_diou", "kind": "person", "label": "Christos Diou", "url": "https://arxiv.org/a/christos_diou", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:aikaterini_triakosia", "kind": "person", "label": "Aikaterini Triakosia", "url": "https://arxiv.org/a/aikaterini_triakosia", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:ilias_kyrannas", "kind": "person", "label": "Ilias Kyrannas", "url": "https://arxiv.org/a/ilias_kyrannas", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:konstantinos_tserpes", "kind": "person", "label": "Konstantinos Tserpes", "url": "https://arxiv.org/a/konstantinos_tserpes", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:1908.05033", "kind": "paper", "label": "Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks", "url": "https://arxiv.org/abs/1908.05033", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2019-08-14"}
{"type": "node", "id": "author:ruihao_gong", "kind": "person", "label": "Ruihao Gong", "url": "https://arxiv.org/a/ruihao_gong", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:xianglong_liu", "kind": "person", "label": "Xianglong Liu", "url": "https://arxiv.org/a/xianglong_liu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:shenghu_jiang", "kind": "person", "label": "Shenghu Jiang", "url": "https://arxiv.org/a/shenghu_jiang", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:tianxiang_li", "kind": "person", "label": "Tianxiang Li", "url": "https://arxiv.org/a/tianxiang_li", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:peng_hu", "kind": "person", "label": "Peng Hu", "url": "https://arxiv.org/a/peng_hu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:1708.01001", "kind": "paper", "label": "Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization", "url": "https://arxiv.org/abs/1708.01001", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2017-08-03"}
{"type": "node", "id": "author:yinpeng_dong", "kind": "person", "label": "Yinpeng Dong", "url": "https://arxiv.org/a/yinpeng_dong", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:renkun_ni", "kind": "person", "label": "Renkun Ni", "url": "https://arxiv.org/a/renkun_ni", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jianguo_li", "kind": "person", "label": "Jianguo Li", "url": "https://arxiv.org/a/jianguo_li", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jun_zhu", "kind": "person", "label": "Jun Zhu", "url": "https://arxiv.org/a/jun_zhu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2307.00331", "kind": "paper", "label": "Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision", "url": "https://arxiv.org/abs/2307.00331", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2023-07-01"}
{"type": "node", "id": "author:zhiqiang_shen", "kind": "person", "label": "Zhiqiang Shen", "url": "https://arxiv.org/a/zhiqiang_shen", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:pingcheng_dong", "kind": "person", "label": "Pingcheng Dong", "url": "https://arxiv.org/a/pingcheng_dong", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2606.29337", "kind": "paper", "label": "W4A4 Quantization for Inference on Wan2.2-I2V-A14B", "url": "https://arxiv.org/abs/2606.29337", "source": "arxiv", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "published": "2026-06-28"}
{"type": "node", "id": "author:yidong_chen", "kind": "person", "label": "Yidong Chen", "url": "https://arxiv.org/a/yidong_chen", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:chengyu_shi", "kind": "person", "label": "Chengyu Shi", "url": "https://arxiv.org/a/chengyu_shi", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "author:jiahao_liu", "kind": "person", "label": "Jiahao Liu", "url": "https://arxiv.org/a/jiahao_liu", "source": "arxiv-author", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "paper:2603.29727", "kind": "paper", "label": "Latent-Y: A Lab-Validated Autonomous Agent for De Novo Drug Design", "url": "https://arxiv.org/abs/2603.29727", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2026-03-31"}
{"type": "node", "id": "author:latent_labs_team", "kind": "person", "label": "Latent Labs Team", "url": "https://arxiv.org/a/latent_labs_team", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:sebastian_m_schmon", "kind": "person", "label": "Sebastian M. Schmon", "url": "https://arxiv.org/a/sebastian_m_schmon", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:daniella_pretorius", "kind": "person", "label": "Daniella Pretorius", "url": "https://arxiv.org/a/daniella_pretorius", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:simon_mathis", "kind": "person", "label": "Simon Mathis", "url": "https://arxiv.org/a/simon_mathis", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:rebecca_bartke_croughan", "kind": "person", "label": "Rebecca Bartke-Croughan", "url": "https://arxiv.org/a/rebecca_bartke_croughan", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2507.19375", "kind": "paper", "label": "Latent-X: An Atom-level Frontier Model for De Novo Protein Binder Design", "url": "https://arxiv.org/abs/2507.19375", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2025-07-25"}
{"type": "node", "id": "author:alex_bridgland", "kind": "person", "label": "Alex Bridgland", "url": "https://arxiv.org/a/alex_bridgland", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:jonathan_crabb", "kind": "person", "label": "Jonathan Crabb\u00e9", "url": "https://arxiv.org/a/jonathan_crabb", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:henry_kenlay", "kind": "person", "label": "Henry Kenlay", "url": "https://arxiv.org/a/henry_kenlay", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2512.20263", "kind": "paper", "label": "Drug-like antibodies with low immunogenicity in human panels designed with Latent-X2", "url": "https://arxiv.org/abs/2512.20263", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2025-12-23"}
{"type": "node", "id": "paper:2605.15725", "kind": "paper", "label": "DiLA: Disentangled Latent Action World Models", "url": "https://arxiv.org/abs/2605.15725", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2026-05-15"}
{"type": "node", "id": "author:tianqiu_zhang", "kind": "person", "label": "Tianqiu Zhang", "url": "https://arxiv.org/a/tianqiu_zhang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:muyang_lyu", "kind": "person", "label": "Muyang Lyu", "url": "https://arxiv.org/a/muyang_lyu", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yufan_zhang", "kind": "person", "label": "Yufan Zhang", "url": "https://arxiv.org/a/yufan_zhang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:fang_fang", "kind": "person", "label": "Fang Fang", "url": "https://arxiv.org/a/fang_fang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:si_wu", "kind": "person", "label": "Si Wu", "url": "https://arxiv.org/a/si_wu", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2607.04464", "kind": "paper", "label": "Operator-on-F complements value-equivalence: a planning-time diagnostic for latent world models", "url": "https://arxiv.org/abs/2607.04464", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2026-07-05"}
{"type": "node", "id": "author:donna_vakalis", "kind": "person", "label": "Donna Vakalis", "url": "https://arxiv.org/a/donna_vakalis", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2503.18938", "kind": "paper", "label": "AdaWorld: Learning Adaptable World Models with Latent Actions", "url": "https://arxiv.org/abs/2503.18938", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2025-03-24"}
{"type": "node", "id": "author:shenyuan_gao", "kind": "person", "label": "Shenyuan Gao", "url": "https://arxiv.org/a/shenyuan_gao", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:siyuan_zhou", "kind": "person", "label": "Siyuan Zhou", "url": "https://arxiv.org/a/siyuan_zhou", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yilun_du", "kind": "person", "label": "Yilun Du", "url": "https://arxiv.org/a/yilun_du", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:jun_zhang", "kind": "person", "label": "Jun Zhang", "url": "https://arxiv.org/a/jun_zhang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:chuang_gan", "kind": "person", "label": "Chuang Gan", "url": "https://arxiv.org/a/chuang_gan", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2605.31361", "kind": "paper", "label": "Dreaming Of Others: Latent Teammate Modeling In World Models For Multi-Agent Reinforcement Learning", "url": "https://arxiv.org/abs/2605.31361", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2026-05-29"}
{"type": "node", "id": "author:tomas_leroy_stone", "kind": "person", "label": "Tomas Leroy-Stone", "url": "https://arxiv.org/a/tomas_leroy_stone", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2606.09828", "kind": "paper", "label": "Latent Spatial Memory for Video World Models", "url": "https://arxiv.org/abs/2606.09828", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2026-06-08"}
{"type": "node", "id": "author:haoyu_zhao", "kind": "person", "label": "Haoyu Zhao", "url": "https://arxiv.org/a/haoyu_zhao", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yifan_yang", "kind": "person", "label": "Yifan Yang", "url": "https://arxiv.org/a/yifan_yang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:zeyu_zhang", "kind": "person", "label": "Zeyu Zhang", "url": "https://arxiv.org/a/zeyu_zhang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2606.13295", "kind": "paper", "label": "Simultaneous Latent Budget Trees for Stratified Classification", "url": "https://arxiv.org/abs/2606.13295", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2026-06-11"}
{"type": "node", "id": "author:simultaneous_latent_budget_trees_for_stratified_classification_cristian_buoncomp", "kind": "person", "label": "Simultaneous Latent Budget Trees for Stratified Classification Cristian Buoncompagni", "url": "https://arxiv.org/a/simultaneous_latent_budget_trees_for_stratified_classification_cristian_buoncomp", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:stefano_pellegrino", "kind": "person", "label": "Stefano Pellegrino", "url": "https://arxiv.org/a/stefano_pellegrino", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:giulia_vannucci", "kind": "person", "label": "Giulia Vannucci", "url": "https://arxiv.org/a/giulia_vannucci", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:raffaele_dubbioso", "kind": "person", "label": "Raffaele Dubbioso", "url": "https://arxiv.org/a/raffaele_dubbioso", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:roberta_siciliano", "kind": "person", "label": "Roberta Siciliano", "url": "https://arxiv.org/a/roberta_siciliano", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2602.10104", "kind": "paper", "label": "Olaf-World: Orienting Latent Actions for Video World Modeling", "url": "https://arxiv.org/abs/2602.10104", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2026-02-10"}
{"type": "node", "id": "author:yuxin_jiang", "kind": "person", "label": "Yuxin Jiang", "url": "https://arxiv.org/a/yuxin_jiang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yuchao_gu", "kind": "person", "label": "Yuchao Gu", "url": "https://arxiv.org/a/yuchao_gu", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:ivor_w_tsang", "kind": "person", "label": "Ivor W. Tsang", "url": "https://arxiv.org/a/ivor_w_tsang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:mike_zheng_shou", "kind": "person", "label": "Mike Zheng Shou", "url": "https://arxiv.org/a/mike_zheng_shou", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2506.00613", "kind": "paper", "label": "WorldGym: World Model as An Environment for Policy Evaluation", "url": "https://arxiv.org/abs/2506.00613", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2025-05-31"}
{"type": "node", "id": "author:julian_quevedo", "kind": "person", "label": "Julian Quevedo", "url": "https://arxiv.org/a/julian_quevedo", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:ansh_kumar_sharma", "kind": "person", "label": "Ansh Kumar Sharma", "url": "https://arxiv.org/a/ansh_kumar_sharma", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yixiang_sun", "kind": "person", "label": "Yixiang Sun", "url": "https://arxiv.org/a/yixiang_sun", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:varad_suryavanshi", "kind": "person", "label": "Varad Suryavanshi", "url": "https://arxiv.org/a/varad_suryavanshi", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:percy_liang", "kind": "person", "label": "Percy Liang", "url": "https://arxiv.org/a/percy_liang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2510.07092", "kind": "paper", "label": "Generative World Modelling for Humanoids: 1X World Model Challenge Technical Report", "url": "https://arxiv.org/abs/2510.07092", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2025-10-08"}
{"type": "node", "id": "author:riccardo_mereu", "kind": "person", "label": "Riccardo Mereu", "url": "https://arxiv.org/a/riccardo_mereu", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:aidan_scannell", "kind": "person", "label": "Aidan Scannell", "url": "https://arxiv.org/a/aidan_scannell", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yuxin_hou", "kind": "person", "label": "Yuxin Hou", "url": "https://arxiv.org/a/yuxin_hou", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yi_zhao", "kind": "person", "label": "Yi Zhao", "url": "https://arxiv.org/a/yi_zhao", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:aditya_jitta", "kind": "person", "label": "Aditya Jitta", "url": "https://arxiv.org/a/aditya_jitta", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2603.04715", "kind": "paper", "label": "Probabilistic Dreaming for World Models", "url": "https://arxiv.org/abs/2603.04715", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2026-03-05"}
{"type": "node", "id": "author:gavin_wong", "kind": "person", "label": "Gavin Wong", "url": "https://arxiv.org/a/gavin_wong", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2512.00005", "kind": "paper", "label": "DREAMer-VXS: A Latent World Model for Sample-Efficient AGV Exploration in Stochastic, Unobserved Environments", "url": "https://arxiv.org/abs/2512.00005", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2025-10-06"}
{"type": "node", "id": "author:agniprabha_chakraborty", "kind": "person", "label": "Agniprabha Chakraborty", "url": "https://arxiv.org/a/agniprabha_chakraborty", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2605.23993", "kind": "paper", "label": "Nano World Models: A Minimalist Implementation of Future Video Prediction", "url": "https://arxiv.org/abs/2605.23993", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2026-05-17"}
{"type": "node", "id": "author:siqiao_huang", "kind": "person", "label": "Siqiao Huang", "url": "https://arxiv.org/a/siqiao_huang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:partha_kaushik", "kind": "person", "label": "Partha Kaushik", "url": "https://arxiv.org/a/partha_kaushik", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:michael_chen", "kind": "person", "label": "Michael Chen", "url": "https://arxiv.org/a/michael_chen", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:hengkai_pan", "kind": "person", "label": "Hengkai Pan", "url": "https://arxiv.org/a/hengkai_pan", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:kaiwen_geng", "kind": "person", "label": "Kaiwen Geng", "url": "https://arxiv.org/a/kaiwen_geng", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2009.00804", "kind": "paper", "label": "Architectural Implications of Graph Neural Networks", "url": "https://arxiv.org/abs/2009.00804", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2020-09-02"}
{"type": "node", "id": "author:zhihui_zhang", "kind": "person", "label": "Zhihui Zhang", "url": "https://arxiv.org/a/zhihui_zhang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:jingwen_leng", "kind": "person", "label": "Jingwen Leng", "url": "https://arxiv.org/a/jingwen_leng", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:lingxiao_ma", "kind": "person", "label": "Lingxiao Ma", "url": "https://arxiv.org/a/lingxiao_ma", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:youshan_miao", "kind": "person", "label": "Youshan Miao", "url": "https://arxiv.org/a/youshan_miao", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:chao_li", "kind": "person", "label": "Chao Li", "url": "https://arxiv.org/a/chao_li", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2207.13219", "kind": "paper", "label": "Dalorex: A Data-Local Program Execution and Architecture for Memory-bound Applications", "url": "https://arxiv.org/abs/2207.13219", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2022-07-26"}
{"type": "node", "id": "author:marcelo_orenes_vera", "kind": "person", "label": "Marcelo Orenes-Vera", "url": "https://arxiv.org/a/marcelo_orenes_vera", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:esin_tureci", "kind": "person", "label": "Esin Tureci", "url": "https://arxiv.org/a/esin_tureci", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:david_wentzlaff", "kind": "person", "label": "David Wentzlaff", "url": "https://arxiv.org/a/david_wentzlaff", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:margaret_martonosi", "kind": "person", "label": "Margaret Martonosi", "url": "https://arxiv.org/a/margaret_martonosi", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2508.10489", "kind": "paper", "label": "Learning State-Space Models of Dynamic Systems from Arbitrary Data using Joint Embedding Predictive Architectures", "url": "https://arxiv.org/abs/2508.10489", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2025-08-14"}
{"type": "node", "id": "author:jonas_ulmen", "kind": "person", "label": "Jonas Ulmen", "url": "https://arxiv.org/a/jonas_ulmen", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:ganesh_sundaram", "kind": "person", "label": "Ganesh Sundaram", "url": "https://arxiv.org/a/ganesh_sundaram", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:daniel_g_rges", "kind": "person", "label": "Daniel G\u00f6rges", "url": "https://arxiv.org/a/daniel_g_rges", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2402.19171", "kind": "paper", "label": "Towards Assessing Spread in Sets of Software Architecture Designs", "url": "https://arxiv.org/abs/2402.19171", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2024-02-29"}
{"type": "node", "id": "author:vittorio_cortellessa", "kind": "person", "label": "Vittorio Cortellessa", "url": "https://arxiv.org/a/vittorio_cortellessa", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:j_andres_diaz_pace", "kind": "person", "label": "J. Andres Diaz-Pace", "url": "https://arxiv.org/a/j_andres_diaz_pace", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:daniele_di_pompeo", "kind": "person", "label": "Daniele Di Pompeo", "url": "https://arxiv.org/a/daniele_di_pompeo", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:michele_tucci", "kind": "person", "label": "Michele Tucci", "url": "https://arxiv.org/a/michele_tucci", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2412.20486", "kind": "paper", "label": "LSQCA: Resource-Efficient Load/Store Architecture for Limited-Scale Fault-Tolerant Quantum Computing", "url": "https://arxiv.org/abs/2412.20486", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2024-12-29"}
{"type": "node", "id": "author:takumi_kobori", "kind": "person", "label": "Takumi Kobori", "url": "https://arxiv.org/a/takumi_kobori", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yasunari_suzuki", "kind": "person", "label": "Yasunari Suzuki", "url": "https://arxiv.org/a/yasunari_suzuki", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yosuke_ueno", "kind": "person", "label": "Yosuke Ueno", "url": "https://arxiv.org/a/yosuke_ueno", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:teruo_tanimoto", "kind": "person", "label": "Teruo Tanimoto", "url": "https://arxiv.org/a/teruo_tanimoto", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:synge_todo", "kind": "person", "label": "Synge Todo", "url": "https://arxiv.org/a/synge_todo", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:1306.0089", "kind": "paper", "label": "A Novel Reconfigurable Architecture of a DSP Processor for Efficient Mapping of DSP Functions using Field Programmable DSP Arrays", "url": "https://arxiv.org/abs/1306.0089", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2013-06-01"}
{"type": "node", "id": "author:amitabha_sinha", "kind": "person", "label": "Amitabha Sinha", "url": "https://arxiv.org/a/amitabha_sinha", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:mitrava_sarkar", "kind": "person", "label": "Mitrava Sarkar", "url": "https://arxiv.org/a/mitrava_sarkar", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:soumojit_acharyya", "kind": "person", "label": "Soumojit Acharyya", "url": "https://arxiv.org/a/soumojit_acharyya", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:suranjan_chakraborty", "kind": "person", "label": "Suranjan Chakraborty", "url": "https://arxiv.org/a/suranjan_chakraborty", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2603.00049", "kind": "paper", "label": "BiJEPA: Bi-directional Joint Embedding Predictive Architecture for Symmetric Representation Learning", "url": "https://arxiv.org/abs/2603.00049", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2026-02-10"}
{"type": "node", "id": "author:yongchao_huang", "kind": "person", "label": "Yongchao Huang", "url": "https://arxiv.org/a/yongchao_huang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2505.09343", "kind": "paper", "label": "Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures", "url": "https://arxiv.org/abs/2505.09343", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2025-05-14"}
{"type": "node", "id": "author:chenggang_zhao", "kind": "person", "label": "Chenggang Zhao", "url": "https://arxiv.org/a/chenggang_zhao", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:chengqi_deng", "kind": "person", "label": "Chengqi Deng", "url": "https://arxiv.org/a/chengqi_deng", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:chong_ruan", "kind": "person", "label": "Chong Ruan", "url": "https://arxiv.org/a/chong_ruan", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:damai_dai", "kind": "person", "label": "Damai Dai", "url": "https://arxiv.org/a/damai_dai", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:huazuo_gao", "kind": "person", "label": "Huazuo Gao", "url": "https://arxiv.org/a/huazuo_gao", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2512.10942", "kind": "paper", "label": "VL-JEPA: Joint Embedding Predictive Architecture for Vision-language", "url": "https://arxiv.org/abs/2512.10942", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2025-12-11"}
{"type": "node", "id": "author:delong_chen", "kind": "person", "label": "Delong Chen", "url": "https://arxiv.org/a/delong_chen", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:mustafa_shukor", "kind": "person", "label": "Mustafa Shukor", "url": "https://arxiv.org/a/mustafa_shukor", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:theo_moutakanni", "kind": "person", "label": "Theo Moutakanni", "url": "https://arxiv.org/a/theo_moutakanni", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:willy_chung", "kind": "person", "label": "Willy Chung", "url": "https://arxiv.org/a/willy_chung", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:jade_yu", "kind": "person", "label": "Jade Yu", "url": "https://arxiv.org/a/jade_yu", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2211.10831", "kind": "paper", "label": "Joint Embedding Predictive Architectures Focus on Slow Features", "url": "https://arxiv.org/abs/2211.10831", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2022-11-20"}
{"type": "node", "id": "author:vlad_sobal", "kind": "person", "label": "Vlad Sobal", "url": "https://arxiv.org/a/vlad_sobal", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:jyothir_s", "kind": "person", "label": "Jyothir S", "url": "https://arxiv.org/a/jyothir_s", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:siddhartha_jalagam", "kind": "person", "label": "Siddhartha Jalagam", "url": "https://arxiv.org/a/siddhartha_jalagam", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:nicolas_carion", "kind": "person", "label": "Nicolas Carion", "url": "https://arxiv.org/a/nicolas_carion", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2410.03755", "kind": "paper", "label": "Denoising with a Joint-Embedding Predictive Architecture", "url": "https://arxiv.org/abs/2410.03755", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2024-10-02"}
{"type": "node", "id": "author:dengsheng_chen", "kind": "person", "label": "Dengsheng Chen", "url": "https://arxiv.org/a/dengsheng_chen", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:jie_hu", "kind": "person", "label": "Jie Hu", "url": "https://arxiv.org/a/jie_hu", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:xiaoming_wei", "kind": "person", "label": "Xiaoming Wei", "url": "https://arxiv.org/a/xiaoming_wei", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:enhua_wu", "kind": "person", "label": "Enhua Wu", "url": "https://arxiv.org/a/enhua_wu", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2301.07516", "kind": "paper", "label": "Quality Attributes Optimization of Software Architecture: Research Challenges and Directions", "url": "https://arxiv.org/abs/2301.07516", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2023-01-18"}
{"type": "node", "id": "paper:2407.10733", "kind": "paper", "label": "Joint-Embedding Predictive Architecture for Self-Supervised Learning of Mask Classification Architecture", "url": "https://arxiv.org/abs/2407.10733", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2024-07-15"}
{"type": "node", "id": "author:dong_hee_kim", "kind": "person", "label": "Dong-Hee Kim", "url": "https://arxiv.org/a/dong_hee_kim", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:sungduk_cho", "kind": "person", "label": "Sungduk Cho", "url": "https://arxiv.org/a/sungduk_cho", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:hyeonwoo_cho", "kind": "person", "label": "Hyeonwoo Cho", "url": "https://arxiv.org/a/hyeonwoo_cho", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:chanmin_park", "kind": "person", "label": "Chanmin Park", "url": "https://arxiv.org/a/chanmin_park", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:jinyoung_kim", "kind": "person", "label": "Jinyoung Kim", "url": "https://arxiv.org/a/jinyoung_kim", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2506.18194", "kind": "paper", "label": "Joint Embedding Predictive Architecture for self-supervised pretraining on polymer molecular graphs", "url": "https://arxiv.org/abs/2506.18194", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2025-06-22"}
{"type": "node", "id": "author:francesco_piccoli", "kind": "person", "label": "Francesco Piccoli", "url": "https://arxiv.org/a/francesco_piccoli", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:gabriel_vogel", "kind": "person", "label": "Gabriel Vogel", "url": "https://arxiv.org/a/gabriel_vogel", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:jana_m_weber", "kind": "person", "label": "Jana M. Weber", "url": "https://arxiv.org/a/jana_m_weber", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2404.16432", "kind": "paper", "label": "Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud", "url": "https://arxiv.org/abs/2404.16432", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2024-04-25"}
{"type": "node", "id": "author:ayumu_saito", "kind": "person", "label": "Ayumu Saito", "url": "https://arxiv.org/a/ayumu_saito", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:prachi_kudeshia", "kind": "person", "label": "Prachi Kudeshia", "url": "https://arxiv.org/a/prachi_kudeshia", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:jiju_poovvancheri", "kind": "person", "label": "Jiju Poovvancheri", "url": "https://arxiv.org/a/jiju_poovvancheri", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2403.05131", "kind": "paper", "label": "Sora as a World Model? A Complete Survey on Text-to-Video Generation", "url": "https://arxiv.org/abs/2403.05131", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2024-03-08"}
{"type": "node", "id": "author:fachrina_dewi_puspitasari", "kind": "person", "label": "Fachrina Dewi Puspitasari", "url": "https://arxiv.org/a/fachrina_dewi_puspitasari", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:chaoning_zhang", "kind": "person", "label": "Chaoning Zhang", "url": "https://arxiv.org/a/chaoning_zhang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:joseph_cho", "kind": "person", "label": "Joseph Cho", "url": "https://arxiv.org/a/joseph_cho", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:adnan_haider", "kind": "person", "label": "Adnan Haider", "url": "https://arxiv.org/a/adnan_haider", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:noor_ul_eman", "kind": "person", "label": "Noor Ul Eman", "url": "https://arxiv.org/a/noor_ul_eman", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2605.22882", "kind": "paper", "label": "GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation", "url": "https://arxiv.org/abs/2605.22882", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2026-05-20"}
{"type": "node", "id": "author:kaichen_zhou", "kind": "person", "label": "Kaichen Zhou", "url": "https://arxiv.org/a/kaichen_zhou", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yuzhen_chen", "kind": "person", "label": "Yuzhen Chen", "url": "https://arxiv.org/a/yuzhen_chen", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:fangneng_zhan", "kind": "person", "label": "Fangneng Zhan", "url": "https://arxiv.org/a/fangneng_zhan", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:hang_hua", "kind": "person", "label": "Hang Hua", "url": "https://arxiv.org/a/hang_hua", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:grace_chen", "kind": "person", "label": "Grace Chen", "url": "https://arxiv.org/a/grace_chen", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2605.24322", "kind": "paper", "label": "Causal Physics Steering in Video World Models via Concept Activation Vectors", "url": "https://arxiv.org/abs/2605.24322", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2026-05-23"}
{"type": "node", "id": "author:nahid_alam", "kind": "person", "label": "Nahid Alam", "url": "https://arxiv.org/a/nahid_alam", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2511.08585", "kind": "paper", "label": "Simulating the Visual World with Artificial Intelligence: A Roadmap", "url": "https://arxiv.org/abs/2511.08585", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2025-11-11"}
{"type": "node", "id": "author:jingtong_yue", "kind": "person", "label": "Jingtong Yue", "url": "https://arxiv.org/a/jingtong_yue", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:ziqi_huang", "kind": "person", "label": "Ziqi Huang", "url": "https://arxiv.org/a/ziqi_huang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:zhaoxi_chen", "kind": "person", "label": "Zhaoxi Chen", "url": "https://arxiv.org/a/zhaoxi_chen", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:xintao_wang", "kind": "person", "label": "Xintao Wang", "url": "https://arxiv.org/a/xintao_wang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:pengfei_wan", "kind": "person", "label": "Pengfei Wan", "url": "https://arxiv.org/a/pengfei_wan", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2410.12822", "kind": "paper", "label": "AVID: Adapting Video Diffusion Models to World Models", "url": "https://arxiv.org/abs/2410.12822", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2024-10-01"}
{"type": "node", "id": "author:marc_rigter", "kind": "person", "label": "Marc Rigter", "url": "https://arxiv.org/a/marc_rigter", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:tarun_gupta", "kind": "person", "label": "Tarun Gupta", "url": "https://arxiv.org/a/tarun_gupta", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:agrin_hilmkil", "kind": "person", "label": "Agrin Hilmkil", "url": "https://arxiv.org/a/agrin_hilmkil", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:chao_ma", "kind": "person", "label": "Chao Ma", "url": "https://arxiv.org/a/chao_ma", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2407.00367", "kind": "paper", "label": "SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix", "url": "https://arxiv.org/abs/2407.00367", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2024-06-29"}
{"type": "node", "id": "author:peng_dai", "kind": "person", "label": "Peng Dai", "url": "https://arxiv.org/a/peng_dai", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:feitong_tan", "kind": "person", "label": "Feitong Tan", "url": "https://arxiv.org/a/feitong_tan", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:qiangeng_xu", "kind": "person", "label": "Qiangeng Xu", "url": "https://arxiv.org/a/qiangeng_xu", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:david_futschik", "kind": "person", "label": "David Futschik", "url": "https://arxiv.org/a/david_futschik", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:ruofei_du", "kind": "person", "label": "Ruofei Du", "url": "https://arxiv.org/a/ruofei_du", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:1709.06342", "kind": "paper", "label": "Assessing Visual Quality of Omnidirectional Videos", "url": "https://arxiv.org/abs/1709.06342", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2017-09-19"}
{"type": "node", "id": "author:mai_xu", "kind": "person", "label": "Mai Xu", "url": "https://arxiv.org/a/mai_xu", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:chen_li", "kind": "person", "label": "Chen Li", "url": "https://arxiv.org/a/chen_li", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:zulin_wang", "kind": "person", "label": "Zulin Wang", "url": "https://arxiv.org/a/zulin_wang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:zhenzhong_chen", "kind": "person", "label": "Zhenzhong Chen", "url": "https://arxiv.org/a/zhenzhong_chen", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:zhenyu_guan", "kind": "person", "label": "Zhenyu Guan", "url": "https://arxiv.org/a/zhenyu_guan", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2401.09985", "kind": "paper", "label": "WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens", "url": "https://arxiv.org/abs/2401.09985", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2024-01-18"}
{"type": "node", "id": "author:xiaofeng_wang", "kind": "person", "label": "Xiaofeng Wang", "url": "https://arxiv.org/a/xiaofeng_wang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:zheng_zhu", "kind": "person", "label": "Zheng Zhu", "url": "https://arxiv.org/a/zheng_zhu", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:guan_huang", "kind": "person", "label": "Guan Huang", "url": "https://arxiv.org/a/guan_huang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:boyuan_wang", "kind": "person", "label": "Boyuan Wang", "url": "https://arxiv.org/a/boyuan_wang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:xinze_chen", "kind": "person", "label": "Xinze Chen", "url": "https://arxiv.org/a/xinze_chen", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2507.16869", "kind": "paper", "label": "Controllable Video Generation: A Survey", "url": "https://arxiv.org/abs/2507.16869", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2025-07-22"}
{"type": "node", "id": "author:yue_ma", "kind": "person", "label": "Yue Ma", "url": "https://arxiv.org/a/yue_ma", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:kunyu_feng", "kind": "person", "label": "Kunyu Feng", "url": "https://arxiv.org/a/kunyu_feng", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:zhongyuan_hu", "kind": "person", "label": "Zhongyuan Hu", "url": "https://arxiv.org/a/zhongyuan_hu", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:xinyu_wang", "kind": "person", "label": "Xinyu Wang", "url": "https://arxiv.org/a/xinyu_wang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yucheng_wang", "kind": "person", "label": "Yucheng Wang", "url": "https://arxiv.org/a/yucheng_wang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2305.14669", "kind": "paper", "label": "NegVSR: Augmenting Negatives for Generalized Noise Modeling in Real-World Video Super-Resolution", "url": "https://arxiv.org/abs/2305.14669", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2023-05-24"}
{"type": "node", "id": "author:yexing_song", "kind": "person", "label": "Yexing Song", "url": "https://arxiv.org/a/yexing_song", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:meilin_wang", "kind": "person", "label": "Meilin Wang", "url": "https://arxiv.org/a/meilin_wang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:zhijing_yang", "kind": "person", "label": "Zhijing Yang", "url": "https://arxiv.org/a/zhijing_yang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:xiaoyu_xian", "kind": "person", "label": "Xiaoyu Xian", "url": "https://arxiv.org/a/xiaoyu_xian", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yukai_shi", "kind": "person", "label": "Yukai Shi", "url": "https://arxiv.org/a/yukai_shi", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2508.08048", "kind": "paper", "label": "S^2VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix", "url": "https://arxiv.org/abs/2508.08048", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2025-08-11"}
{"type": "node", "id": "author:yihua_huang", "kind": "person", "label": "Yihua Huang", "url": "https://arxiv.org/a/yihua_huang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2605.27589", "kind": "paper", "label": "What-If World: A Causal Benchmark for General World Models in Embodied Scenarios", "url": "https://arxiv.org/abs/2605.27589", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2026-05-26"}
{"type": "node", "id": "author:kunlin_cai", "kind": "person", "label": "Kunlin Cai", "url": "https://arxiv.org/a/kunlin_cai", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:rui_song", "kind": "person", "label": "Rui Song", "url": "https://arxiv.org/a/rui_song", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:jinghuai_zhang", "kind": "person", "label": "Jinghuai Zhang", "url": "https://arxiv.org/a/jinghuai_zhang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:kaiyuan_zhang", "kind": "person", "label": "Kaiyuan Zhang", "url": "https://arxiv.org/a/kaiyuan_zhang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:pranav_bodapati", "kind": "person", "label": "Pranav Bodapati", "url": "https://arxiv.org/a/pranav_bodapati", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2406.09455", "kind": "paper", "label": "Pandora: Towards General World Model with Natural Language Actions and Video States", "url": "https://arxiv.org/abs/2406.09455", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2024-06-12"}
{"type": "node", "id": "author:jiannan_xiang", "kind": "person", "label": "Jiannan Xiang", "url": "https://arxiv.org/a/jiannan_xiang", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:guangyi_liu", "kind": "person", "label": "Guangyi Liu", "url": "https://arxiv.org/a/guangyi_liu", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yi_gu", "kind": "person", "label": "Yi Gu", "url": "https://arxiv.org/a/yi_gu", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:qiyue_gao", "kind": "person", "label": "Qiyue Gao", "url": "https://arxiv.org/a/qiyue_gao", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yuting_ning", "kind": "person", "label": "Yuting Ning", "url": "https://arxiv.org/a/yuting_ning", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2602.12375", "kind": "paper", "label": "Value Bonuses using Ensemble Errors for Exploration in Reinforcement Learning", "url": "https://arxiv.org/abs/2602.12375", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2026-02-12"}
{"type": "node", "id": "author:abdul_wahab", "kind": "person", "label": "Abdul Wahab", "url": "https://arxiv.org/a/abdul_wahab", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:raksha_kumaraswamy", "kind": "person", "label": "Raksha Kumaraswamy", "url": "https://arxiv.org/a/raksha_kumaraswamy", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:martha_white", "kind": "person", "label": "Martha White", "url": "https://arxiv.org/a/martha_white", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:1711.10137", "kind": "paper", "label": "One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay", "url": "https://arxiv.org/abs/1711.10137", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2017-11-28"}
{"type": "node", "id": "author:jake_bruce", "kind": "person", "label": "Jake Bruce", "url": "https://arxiv.org/a/jake_bruce", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:niko_suenderhauf", "kind": "person", "label": "Niko Suenderhauf", "url": "https://arxiv.org/a/niko_suenderhauf", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:piotr_mirowski", "kind": "person", "label": "Piotr Mirowski", "url": "https://arxiv.org/a/piotr_mirowski", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:raia_hadsell", "kind": "person", "label": "Raia Hadsell", "url": "https://arxiv.org/a/raia_hadsell", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:michael_milford", "kind": "person", "label": "Michael Milford", "url": "https://arxiv.org/a/michael_milford", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2507.02910", "kind": "paper", "label": "Causal-Paced Deep Reinforcement Learning", "url": "https://arxiv.org/abs/2507.02910", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2025-06-24"}
{"type": "node", "id": "author:geonwoo_cho", "kind": "person", "label": "Geonwoo Cho", "url": "https://arxiv.org/a/geonwoo_cho", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:jaegyun_im", "kind": "person", "label": "Jaegyun Im", "url": "https://arxiv.org/a/jaegyun_im", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:doyoon_kim", "kind": "person", "label": "Doyoon Kim", "url": "https://arxiv.org/a/doyoon_kim", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:sundong_kim", "kind": "person", "label": "Sundong Kim", "url": "https://arxiv.org/a/sundong_kim", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:1807.05037", "kind": "paper", "label": "Exploring Hierarchy-Aware Inverse Reinforcement Learning", "url": "https://arxiv.org/abs/1807.05037", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2018-07-13"}
{"type": "node", "id": "author:chris_cundy", "kind": "person", "label": "Chris Cundy", "url": "https://arxiv.org/a/chris_cundy", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:daniel_filan", "kind": "person", "label": "Daniel Filan", "url": "https://arxiv.org/a/daniel_filan", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2301.08028", "kind": "paper", "label": "A Tutorial on Meta-Reinforcement Learning", "url": "https://arxiv.org/abs/2301.08028", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2023-01-19"}
{"type": "node", "id": "author:jacob_beck", "kind": "person", "label": "Jacob Beck", "url": "https://arxiv.org/a/jacob_beck", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:risto_vuorio", "kind": "person", "label": "Risto Vuorio", "url": "https://arxiv.org/a/risto_vuorio", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:evan_zheran_liu", "kind": "person", "label": "Evan Zheran Liu", "url": "https://arxiv.org/a/evan_zheran_liu", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:zheng_xiong", "kind": "person", "label": "Zheng Xiong", "url": "https://arxiv.org/a/zheng_xiong", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:luisa_zintgraf", "kind": "person", "label": "Luisa Zintgraf", "url": "https://arxiv.org/a/luisa_zintgraf", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2406.04896", "kind": "paper", "label": "Stabilizing Extreme Q-learning by Maclaurin Expansion", "url": "https://arxiv.org/abs/2406.04896", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2024-06-07"}
{"type": "node", "id": "author:motoki_omura", "kind": "person", "label": "Motoki Omura", "url": "https://arxiv.org/a/motoki_omura", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:takayuki_osa", "kind": "person", "label": "Takayuki Osa", "url": "https://arxiv.org/a/takayuki_osa", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:yusuke_mukuta", "kind": "person", "label": "Yusuke Mukuta", "url": "https://arxiv.org/a/yusuke_mukuta", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:tatsuya_harada", "kind": "person", "label": "Tatsuya Harada", "url": "https://arxiv.org/a/tatsuya_harada", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:1809.09501", "kind": "paper", "label": "Anderson Acceleration for Reinforcement Learning", "url": "https://arxiv.org/abs/1809.09501", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2018-09-25"}
{"type": "node", "id": "author:matthieu_geist", "kind": "person", "label": "Matthieu Geist", "url": "https://arxiv.org/a/matthieu_geist", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:bruno_scherrer", "kind": "person", "label": "Bruno Scherrer", "url": "https://arxiv.org/a/bruno_scherrer", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:1705.00470", "kind": "paper", "label": "Learning Multimodal Transition Dynamics for Model-Based Reinforcement Learning", "url": "https://arxiv.org/abs/1705.00470", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2017-05-01"}
{"type": "node", "id": "paper:1904.09489", "kind": "paper", "label": "Compression and Localization in Reinforcement Learning for ATARI Games", "url": "https://arxiv.org/abs/1904.09489", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2019-04-20"}
{"type": "node", "id": "author:joel_ruben_antony_moniz", "kind": "person", "label": "Joel Ruben Antony Moniz", "url": "https://arxiv.org/a/joel_ruben_antony_moniz", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:barun_patra", "kind": "person", "label": "Barun Patra", "url": "https://arxiv.org/a/barun_patra", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:sarthak_garg", "kind": "person", "label": "Sarthak Garg", "url": "https://arxiv.org/a/sarthak_garg", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:1911.04947", "kind": "paper", "label": "Accelerating Training in Pommerman with Imitation and Reinforcement Learning", "url": "https://arxiv.org/abs/1911.04947", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2019-11-12"}
{"type": "node", "id": "author:hardik_meisheri", "kind": "person", "label": "Hardik Meisheri", "url": "https://arxiv.org/a/hardik_meisheri", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:omkar_shelke", "kind": "person", "label": "Omkar Shelke", "url": "https://arxiv.org/a/omkar_shelke", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:richa_verma", "kind": "person", "label": "Richa Verma", "url": "https://arxiv.org/a/richa_verma", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:harshad_khadilkar", "kind": "person", "label": "Harshad Khadilkar", "url": "https://arxiv.org/a/harshad_khadilkar", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:1909.11939", "kind": "paper", "label": "MERL: Multi-Head Reinforcement Learning", "url": "https://arxiv.org/abs/1909.11939", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2019-09-26"}
{"type": "node", "id": "author:yannis_flet_berliac", "kind": "person", "label": "Yannis Flet-Berliac", "url": "https://arxiv.org/a/yannis_flet_berliac", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2011.02511", "kind": "paper", "label": "Offline Reinforcement Learning from Human Feedback in Real-World Sequence-to-Sequence Tasks", "url": "https://arxiv.org/abs/2011.02511", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2020-11-04"}
{"type": "node", "id": "author:julia_kreutzer", "kind": "person", "label": "Julia Kreutzer", "url": "https://arxiv.org/a/julia_kreutzer", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:stefan_riezler", "kind": "person", "label": "Stefan Riezler", "url": "https://arxiv.org/a/stefan_riezler", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:carolin_lawrence", "kind": "person", "label": "Carolin Lawrence", "url": "https://arxiv.org/a/carolin_lawrence", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:1907.04543", "kind": "paper", "label": "An Optimistic Perspective on Offline Reinforcement Learning", "url": "https://arxiv.org/abs/1907.04543", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2019-07-10"}
{"type": "node", "id": "author:rishabh_agarwal", "kind": "person", "label": "Rishabh Agarwal", "url": "https://arxiv.org/a/rishabh_agarwal", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:dale_schuurmans", "kind": "person", "label": "Dale Schuurmans", "url": "https://arxiv.org/a/dale_schuurmans", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:mohammad_norouzi", "kind": "person", "label": "Mohammad Norouzi", "url": "https://arxiv.org/a/mohammad_norouzi", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:2112.01195", "kind": "paper", "label": "Maximum Entropy Model-based Reinforcement Learning", "url": "https://arxiv.org/abs/2112.01195", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2021-12-02"}
{"type": "node", "id": "author:oleg_svidchenko", "kind": "person", "label": "Oleg Svidchenko", "url": "https://arxiv.org/a/oleg_svidchenko", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:aleksei_shpilman", "kind": "person", "label": "Aleksei Shpilman", "url": "https://arxiv.org/a/aleksei_shpilman", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:1911.09560", "kind": "paper", "label": "Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means", "url": "https://arxiv.org/abs/1911.09560", "source": "arxiv", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "published": "2019-11-21"}
{"type": "node", "id": "author:andrea_agostinelli", "kind": "person", "label": "Andrea Agostinelli", "url": "https://arxiv.org/a/andrea_agostinelli", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:kai_arulkumaran", "kind": "person", "label": "Kai Arulkumaran", "url": "https://arxiv.org/a/kai_arulkumaran", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:marta_sarrico", "kind": "person", "label": "Marta Sarrico", "url": "https://arxiv.org/a/marta_sarrico", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:pierre_richemond", "kind": "person", "label": "Pierre Richemond", "url": "https://arxiv.org/a/pierre_richemond", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "author:anil_anthony_bharath", "kind": "person", "label": "Anil Anthony Bharath", "url": "https://arxiv.org/a/anil_anthony_bharath", "source": "arxiv-author", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "paper:1906.02243", "kind": "paper", "label": "Energy and Policy Considerations for Deep Learning in NLP", "url": "https://arxiv.org/abs/1906.02243", "source": "arxiv-anchor", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "anchor": true}
{"type": "node", "id": "paper:1907.10597", "kind": "paper", "label": "Green AI", "url": "https://arxiv.org/abs/1907.10597", "source": "arxiv-anchor", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "anchor": true}
{"type": "node", "id": "paper:2211.02001", "kind": "paper", "label": "Estimating the Carbon Footprint of BLOOM", "url": "https://arxiv.org/abs/2211.02001", "source": "arxiv-anchor", "axis": "energy", "layer": 0, "maps_to_surface": "energy", "anchor": true}
{"type": "node", "id": "paper:2208.07339", "kind": "paper", "label": "LLM.int8(): 8-bit Matrix Multiplication for Transformers", "url": "https://arxiv.org/abs/2208.07339", "source": "arxiv-anchor", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "anchor": true}
{"type": "node", "id": "paper:2305.14314", "kind": "paper", "label": "QLoRA: Efficient Finetuning of Quantized LLMs", "url": "https://arxiv.org/abs/2305.14314", "source": "arxiv-anchor", "axis": "quant", "layer": 0, "maps_to_surface": "energy", "anchor": true}
{"type": "node", "id": "paper:1901.09948", "kind": "paper", "label": "Towards spike-based machine intelligence with neuromorphic computing (Loihi era)", "url": "https://arxiv.org/abs/1901.09948", "source": "arxiv-anchor", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "anchor": true}
{"type": "node", "id": "paper:2109.12894", "kind": "paper", "label": "Training Spiking Neural Networks Using Lessons From Deep Learning (snnTorch)", "url": "https://arxiv.org/abs/2109.12894", "source": "arxiv-anchor", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic", "anchor": true}
{"type": "node", "id": "paper:2311.16863", "kind": "paper", "label": "Anti-UAV: A Large-Scale Benchmark for Vision-based UAV Tracking", "url": "https://arxiv.org/abs/2311.16863", "source": "arxiv-anchor", "axis": "defense", "layer": 0, "anchor": true}
{"type": "node", "id": "paper:1806.06771", "kind": "paper", "label": "Physics-Informed Neural Networks (original PINN, Raissi et al.)", "url": "https://arxiv.org/abs/1806.06771", "source": "arxiv-anchor", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "anchor": true}
{"type": "node", "id": "paper:2010.08895", "kind": "paper", "label": "Fourier Neural Operator for Parametric PDEs", "url": "https://arxiv.org/abs/2010.08895", "source": "arxiv-anchor", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn", "anchor": true}
{"type": "node", "id": "paper:2207.06431", "kind": "paper", "label": "Suppressing quantum errors by scaling a surface code logical qubit (Google)", "url": "https://arxiv.org/abs/2207.06431", "source": "arxiv-anchor", "axis": "qec", "layer": 0, "maps_to_surface": "qhall", "anchor": true}
{"type": "node", "id": "paper:2210.03629", "kind": "paper", "label": "ReAct: Synergizing Reasoning and Acting in Language Models", "url": "https://arxiv.org/abs/2210.03629", "source": "arxiv-anchor", "axis": "agents", "layer": 0, "anchor": true}
{"type": "node", "id": "paper:2308.08155", "kind": "paper", "label": "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation", "url": "https://arxiv.org/abs/2308.08155", "source": "arxiv-anchor", "axis": "agents", "layer": 0, "anchor": true}
{"type": "node", "id": "paper:2310.03714", "kind": "paper", "label": "DSPy: Compiling Declarative LM Calls into Self-Improving Pipelines", "url": "https://arxiv.org/abs/2310.03714", "source": "arxiv-anchor", "axis": "agents", "layer": 0, "anchor": true}
{"type": "node", "id": "paper:1803.10122", "kind": "paper", "label": "World Models (Ha & Schmidhuber)", "url": "https://arxiv.org/abs/1803.10122", "source": "arxiv-anchor", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "anchor": true}
{"type": "node", "id": "paper:2301.04104", "kind": "paper", "label": "Mastering Diverse Domains through World Models (DreamerV3)", "url": "https://arxiv.org/abs/2301.04104", "source": "arxiv-anchor", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "anchor": true}
{"type": "node", "id": "paper:2402.15391", "kind": "paper", "label": "Genie: Generative Interactive Environments", "url": "https://arxiv.org/abs/2402.15391", "source": "arxiv-anchor", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "anchor": true}
{"type": "node", "id": "paper:2301.08243", "kind": "paper", "label": "Self-Supervised Learning from Images with a JEPA (I-JEPA)", "url": "https://arxiv.org/abs/2301.08243", "source": "arxiv-anchor", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel", "anchor": true}
{"type": "node", "id": "paper:2210.02747", "kind": "paper", "label": "Flow Matching for Generative Modeling (Lipman et al.)", "url": "https://arxiv.org/abs/2210.02747", "source": "arxiv-anchor", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "anchor": true}
{"type": "node", "id": "paper:2303.08797", "kind": "paper", "label": "Stochastic Interpolants (Albergo & Vanden-Eijnden)", "url": "https://arxiv.org/abs/2303.08797", "source": "arxiv-anchor", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch", "anchor": true}
{"type": "node", "id": "lab:intel_ncl", "kind": "org", "label": "Intel Neuromorphic Computing Lab (NCL)", "url": "https://www.intel.com/content/www/us/en/research/neuromorphic-computing.html", "source": "curated-web", "axis": "neuro", "layer": 2, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "lab:lava_nc", "kind": "org", "label": "Lava (lava-nc) neuromorphic framework org", "url": "https://lava-nc.org", "source": "curated-web", "axis": "neuro", "layer": 2, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "lab:open_neuromorphic", "kind": "org", "label": "Open Neuromorphic community", "url": "https://open-neuromorphic.org", "source": "curated-web", "axis": "neuro", "layer": 2, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "lab:inrc", "kind": "org", "label": "Intel Neuromorphic Research Community (INRC)", "url": "https://intel-ncl.atlassian.net/wiki/spaces/INRC/overview", "source": "curated-web", "axis": "neuro", "layer": 2, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "lab:ibm_truenorth", "kind": "org", "label": "IBM Research neuromorphic (TrueNorth/NorthPole)", "url": "https://research.ibm.com/topics/neuromorphic-computing", "source": "curated-web", "axis": "neuro", "layer": 2, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "lab:sensetime_snn", "kind": "org", "label": "SpikingJelly / OpenBMB spiking group", "url": "https://github.com/fangwei123456/spikingjelly", "source": "curated-web", "axis": "neuro", "layer": 2, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "lab:ucsc_neuromorphic", "kind": "org", "label": "UC Santa Cruz snnTorch (Eshraghian lab)", "url": "https://github.com/jeshraghian/snntorch", "source": "curated-web", "axis": "neuro", "layer": 2, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "lab:human_brain_project", "kind": "org", "label": "Human Brain Project / EBRAINS neuromorphic (SpiNNaker, BrainScaleS)", "url": "https://www.ebrains.eu", "source": "curated-web", "axis": "neuro", "layer": 2, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "lab:spinnaker", "kind": "org", "label": "SpiNNaker (Manchester) neuromorphic hardware", "url": "https://apt.cs.manchester.ac.uk/projects/SpiNNaker/", "source": "curated-web", "axis": "neuro", "layer": 2, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "lab:mlco2", "kind": "org", "label": "ML CO2 Impact / CodeCarbon (MILA)", "url": "https://mlco2.github.io/impact/", "source": "curated-web", "axis": "energy", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "lab:codecarbon", "kind": "org", "label": "CodeCarbon project (MILA/Comet/BCG)", "url": "https://codecarbon.io", "source": "curated-web", "axis": "energy", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "lab:green_algorithms", "kind": "org", "label": "Green Algorithms (Cambridge)", "url": "https://www.green-algorithms.org", "source": "curated-web", "axis": "energy", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "lab:mlperf_power", "kind": "org", "label": "MLCommons MLPerf Power", "url": "https://mlcommons.org/benchmarks/inference-datacenter/", "source": "curated-web", "axis": "energy", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "lab:carbontracker_org", "kind": "org", "label": "Carbontracker (Aarhus University)", "url": "https://github.com/lfwa/carbontracker", "source": "curated-web", "axis": "energy", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "lab:hf_efficiency", "kind": "org", "label": "Hugging Face efficiency / Optimum", "url": "https://github.com/huggingface/optimum", "source": "curated-web", "axis": "quant", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "lab:mit_han_lab", "kind": "org", "label": "MIT HAN Lab (Song Han) - efficient ML / quantization", "url": "https://hanlab.mit.edu", "source": "curated-web", "axis": "quant", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "lab:neuralmagic", "kind": "org", "label": "Neural Magic (LLM Compressor / SparseML)", "url": "https://github.com/vllm-project/llm-compressor", "source": "curated-web", "axis": "quant", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "lab:ggml_org", "kind": "org", "label": "ggml / llama.cpp quantization org", "url": "https://github.com/ggml-org/llama.cpp", "source": "curated-web", "axis": "quant", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "lab:bitsandbytes_fdn", "kind": "org", "label": "bitsandbytes foundation", "url": "https://github.com/bitsandbytes-foundation/bitsandbytes", "source": "curated-web", "axis": "quant", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "lab:darpa", "kind": "org", "label": "DARPA (counter-UAS, sensor programs)", "url": "https://www.darpa.mil", "source": "curated-web", "axis": "defense", "layer": 2}
{"type": "node", "id": "lab:jco_cuas", "kind": "org", "label": "Joint Counter-small UAS Office (JCO)", "url": "https://www.army.mil/jcounteruas", "source": "curated-web", "axis": "defense", "layer": 2}
{"type": "node", "id": "lab:dhs_cuas", "kind": "org", "label": "DHS Counter-UAS program", "url": "https://www.dhs.gov/science-and-technology/counter-uas-technology", "source": "curated-web", "axis": "defense", "layer": 2}
{"type": "node", "id": "lab:nato_mda", "kind": "org", "label": "NATO Maritime domain awareness / CMRE", "url": "https://www.cmre.nato.int", "source": "curated-web", "axis": "defense", "layer": 2}
{"type": "node", "id": "lab:faa_uas", "kind": "org", "label": "FAA UAS detection & mitigation", "url": "https://www.faa.gov/uas", "source": "curated-web", "axis": "defense", "layer": 2}
{"type": "node", "id": "lab:nrl", "kind": "org", "label": "US Naval Research Laboratory", "url": "https://www.nrl.navy.mil", "source": "curated-web", "axis": "defense", "layer": 2}
{"type": "node", "id": "lab:afrl", "kind": "org", "label": "Air Force Research Laboratory", "url": "https://www.afrl.af.mil", "source": "curated-web", "axis": "defense", "layer": 2}
{"type": "node", "id": "lab:nvidia_modulus", "kind": "org", "label": "NVIDIA Modulus / PhysicsNeMo (PINN)", "url": "https://developer.nvidia.com/modulus", "source": "curated-web", "axis": "pinn", "layer": 2, "maps_to_surface": "pinn"}
{"type": "node", "id": "lab:brown_crunch", "kind": "org", "label": "Brown CRUNCH group (Karniadakis, PINN)", "url": "https://sites.brown.edu/crunch-group/", "source": "curated-web", "axis": "pinn", "layer": 2, "maps_to_surface": "pinn"}
{"type": "node", "id": "lab:caltech_ai4science", "kind": "org", "label": "Caltech AI4Science / neural operators (Anandkumar)", "url": "https://tensorlab.cms.caltech.edu/users/anima/", "source": "curated-web", "axis": "pinn", "layer": 2, "maps_to_surface": "pinn"}
{"type": "node", "id": "lab:neuraloperator_org", "kind": "org", "label": "neuraloperator library org", "url": "https://github.com/neuraloperator/neuraloperator", "source": "curated-web", "axis": "pinn", "layer": 2, "maps_to_surface": "pinn"}
{"type": "node", "id": "lab:lu_group_deepxde", "kind": "org", "label": "DeepXDE (Lu Lu group)", "url": "https://deepxde.readthedocs.io", "source": "curated-web", "axis": "pinn", "layer": 2, "maps_to_surface": "pinn"}
{"type": "node", "id": "lab:google_quantum_ai", "kind": "org", "label": "Google Quantum AI (surface code QEC)", "url": "https://quantumai.google", "source": "curated-web", "axis": "qec", "layer": 2, "maps_to_surface": "qhall"}
{"type": "node", "id": "lab:ibm_quantum", "kind": "org", "label": "IBM Quantum (QEC, qLDPC)", "url": "https://www.ibm.com/quantum", "source": "curated-web", "axis": "qec", "layer": 2, "maps_to_surface": "qhall"}
{"type": "node", "id": "lab:qec_zoo", "kind": "org", "label": "Error Correction Zoo", "url": "https://errorcorrectionzoo.org", "source": "curated-web", "axis": "qec", "layer": 2, "maps_to_surface": "qhall"}
{"type": "node", "id": "lab:qiskit_qec", "kind": "org", "label": "Qiskit QEC", "url": "https://github.com/qiskit-community/qiskit-qec", "source": "curated-web", "axis": "qec", "layer": 2, "maps_to_surface": "qhall"}
{"type": "node", "id": "lab:stim_org", "kind": "org", "label": "Stim (Craig Gidney / Google)", "url": "https://github.com/quantumlib/Stim", "source": "curated-web", "axis": "qec", "layer": 2, "maps_to_surface": "qhall"}
{"type": "node", "id": "lab:riverlane", "kind": "org", "label": "Riverlane (QEC decoders)", "url": "https://www.riverlane.com", "source": "curated-web", "axis": "qec", "layer": 2, "maps_to_surface": "qhall"}
{"type": "node", "id": "lab:langchain_ai", "kind": "org", "label": "LangChain / LangGraph (langchain-ai)", "url": "https://github.com/langchain-ai", "source": "curated-web", "axis": "agents", "layer": 2}
{"type": "node", "id": "lab:microsoft_autogen", "kind": "org", "label": "Microsoft AutoGen", "url": "https://github.com/microsoft/autogen", "source": "curated-web", "axis": "agents", "layer": 2}
{"type": "node", "id": "lab:crewai_inc", "kind": "org", "label": "CrewAI", "url": "https://www.crewai.com", "source": "curated-web", "axis": "agents", "layer": 2}
{"type": "node", "id": "lab:openai_agents", "kind": "org", "label": "OpenAI Agents SDK", "url": "https://github.com/openai/openai-agents-python", "source": "curated-web", "axis": "agents", "layer": 2}
{"type": "node", "id": "lab:hf_smolagents", "kind": "org", "label": "Hugging Face smolagents", "url": "https://github.com/huggingface/smolagents", "source": "curated-web", "axis": "agents", "layer": 2}
{"type": "node", "id": "lab:stanford_dspy", "kind": "org", "label": "Stanford DSPy (Omar Khattab)", "url": "https://github.com/stanfordnlp/dspy", "source": "curated-web", "axis": "agents", "layer": 2}
{"type": "node", "id": "lab:metagpt_org", "kind": "org", "label": "MetaGPT / DeepWisdom", "url": "https://github.com/geekan/MetaGPT", "source": "curated-web", "axis": "agents", "layer": 2}
{"type": "node", "id": "lab:meta_fair", "kind": "org", "label": "Meta FAIR (JEPA, world models, LeCun)", "url": "https://ai.meta.com/research/", "source": "curated-web", "axis": "worldmodel", "layer": 2, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "lab:deepmind_worldmodel", "kind": "org", "label": "Google DeepMind (Dreamer, Genie, SIMA)", "url": "https://deepmind.google/research/", "source": "curated-web", "axis": "worldmodel", "layer": 2, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "lab:wayve", "kind": "org", "label": "Wayve (GAIA driving world models)", "url": "https://wayve.ai", "source": "curated-web", "axis": "worldmodel", "layer": 2, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "lab:worldlabs", "kind": "org", "label": "World Labs (Fei-Fei Li, 3D world models)", "url": "https://www.worldlabs.ai", "source": "curated-web", "axis": "worldmodel", "layer": 2, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "lab:decart_ai", "kind": "org", "label": "Decart / Oasis interactive world model", "url": "https://www.decart.ai", "source": "curated-web", "axis": "worldmodel", "layer": 2, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "lab:mit_flowmatch", "kind": "org", "label": "MIT (Flow Matching, Lipman/Le collab)", "url": "https://github.com/facebookresearch/flow_matching", "source": "curated-web", "axis": "flowmatch", "layer": 2, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "lab:stability_ai", "kind": "org", "label": "Stability AI (rectified flow, SD3)", "url": "https://stability.ai", "source": "curated-web", "axis": "flowmatch", "layer": 2, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "lab:blackforest_labs", "kind": "org", "label": "Black Forest Labs (FLUX, flow matching)", "url": "https://blackforestlabs.ai", "source": "curated-web", "axis": "flowmatch", "layer": 2, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "lab:ut_austin_liu", "kind": "org", "label": "UT Austin (Qiang Liu, Rectified Flow)", "url": "https://github.com/gnobitab/RectifiedFlow", "source": "curated-web", "axis": "flowmatch", "layer": 2, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "person:song_han", "kind": "person", "label": "Song Han (MIT, efficient ML/quantization)", "url": "https://songhan.mit.edu", "source": "curated-web", "axis": "quant", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "person:tim_dettmers", "kind": "person", "label": "Tim Dettmers (bitsandbytes, QLoRA, 8-bit)", "url": "https://timdettmers.com", "source": "curated-web", "axis": "quant", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "person:elias_frantar", "kind": "person", "label": "Elias Frantar (GPTQ, SparseGPT)", "url": "https://arxiv.org/a/frantar_e_1", "source": "curated-web", "axis": "quant", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "person:ji_lin", "kind": "person", "label": "Ji Lin (AWQ)", "url": "https://arxiv.org/a/lin_j_1", "source": "curated-web", "axis": "quant", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "person:emma_strubell", "kind": "person", "label": "Emma Strubell (energy & policy of NLP)", "url": "https://strubell.github.io", "source": "curated-web", "axis": "energy", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "person:sasha_luccioni", "kind": "person", "label": "Sasha Luccioni (Hugging Face, ML carbon)", "url": "https://www.huggingface.co/sasha", "source": "curated-web", "axis": "energy", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "person:roy_schwartz", "kind": "person", "label": "Roy Schwartz (Green AI)", "url": "https://schwartz-lab-huji.github.io", "source": "curated-web", "axis": "energy", "layer": 2, "maps_to_surface": "energy"}
{"type": "node", "id": "person:jason_eshraghian", "kind": "person", "label": "Jason Eshraghian (snnTorch, UC Santa Cruz)", "url": "https://www.jasoneshraghian.com", "source": "curated-web", "axis": "neuro", "layer": 2, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "person:mike_davies", "kind": "person", "label": "Mike Davies (Intel Loihi lead)", "url": "https://www.intel.com/content/www/us/en/research/neuromorphic-computing.html", "source": "curated-web", "axis": "neuro", "layer": 2, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "person:wei_fang", "kind": "person", "label": "Wei Fang (SpikingJelly)", "url": "https://github.com/fangwei123456", "source": "curated-web", "axis": "neuro", "layer": 2, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "person:george_karniadakis", "kind": "person", "label": "George Em Karniadakis (PINN, Brown)", "url": "https://sites.brown.edu/crunch-group/", "source": "curated-web", "axis": "pinn", "layer": 2, "maps_to_surface": "pinn"}
{"type": "node", "id": "person:maziar_raissi", "kind": "person", "label": "Maziar Raissi (PINN originator)", "url": "https://sites.google.com/view/maziarraissi/", "source": "curated-web", "axis": "pinn", "layer": 2, "maps_to_surface": "pinn"}
{"type": "node", "id": "person:zongyi_li", "kind": "person", "label": "Zongyi Li (Fourier Neural Operator)", "url": "https://zongyi-li.github.io", "source": "curated-web", "axis": "pinn", "layer": 2, "maps_to_surface": "pinn"}
{"type": "node", "id": "person:anima_anandkumar", "kind": "person", "label": "Anima Anandkumar (neural operators, Caltech/NVIDIA)", "url": "https://tensorlab.cms.caltech.edu/users/anima/", "source": "curated-web", "axis": "pinn", "layer": 2, "maps_to_surface": "pinn"}
{"type": "node", "id": "person:lu_lu", "kind": "person", "label": "Lu Lu (DeepXDE, DeepONet)", "url": "https://lu.seas.upenn.edu", "source": "curated-web", "axis": "pinn", "layer": 2, "maps_to_surface": "pinn"}
{"type": "node", "id": "person:craig_gidney", "kind": "person", "label": "Craig Gidney (Stim, Google QEC)", "url": "https://algassert.com", "source": "curated-web", "axis": "qec", "layer": 2, "maps_to_surface": "qhall"}
{"type": "node", "id": "person:harupy_higgott", "kind": "person", "label": "Oscar Higgott (PyMatching, MWPM decoder)", "url": "https://github.com/oscarhiggott/PyMatching", "source": "curated-web", "axis": "qec", "layer": 2, "maps_to_surface": "qhall"}
{"type": "node", "id": "person:yann_lecun", "kind": "person", "label": "Yann LeCun (JEPA, world models, Meta)", "url": "https://yann.lecun.com", "source": "curated-web", "axis": "worldmodel", "layer": 2, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "person:danijar_hafner", "kind": "person", "label": "Danijar Hafner (Dreamer, DeepMind)", "url": "https://danijar.com", "source": "curated-web", "axis": "worldmodel", "layer": 2, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "person:david_ha", "kind": "person", "label": "David Ha (World Models)", "url": "https://otoro.net", "source": "curated-web", "axis": "worldmodel", "layer": 2, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "person:yaron_lipman", "kind": "person", "label": "Yaron Lipman (Flow Matching, Meta/Weizmann)", "url": "https://lipman.net.technion.ac.il/", "source": "curated-web", "axis": "flowmatch", "layer": 2, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "person:qiang_liu", "kind": "person", "label": "Qiang Liu (Rectified Flow, UT Austin)", "url": "https://www.cs.utexas.edu/~lqiang/", "source": "curated-web", "axis": "flowmatch", "layer": 2, "maps_to_surface": "flowmatch"}
{"type": "node", "id": "person:harrison_chase", "kind": "person", "label": "Harrison Chase (LangChain founder)", "url": "https://github.com/hwchase17", "source": "curated-web", "axis": "agents", "layer": 2}
{"type": "node", "id": "person:omar_khattab", "kind": "person", "label": "Omar Khattab (DSPy)", "url": "https://omarkhattab.com", "source": "curated-web", "axis": "agents", "layer": 2}
{"type": "node", "id": "person:chi_wang", "kind": "person", "label": "Chi Wang (AutoGen)", "url": "https://github.com/sonichi", "source": "curated-web", "axis": "agents", "layer": 2}
{"type": "node", "id": "dataset:mlperf_inference", "kind": "dataset", "label": "MLPerf Inference benchmark (incl. Power)", "url": "https://mlcommons.org/benchmarks/inference-datacenter/", "source": "curated-web", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "dataset:dawnbench", "kind": "dataset", "label": "DAWNBench (Stanford, cost/time-to-accuracy)", "url": "https://dawn.cs.stanford.edu/benchmark/", "source": "curated-web", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "dataset:ml_emissions_calc", "kind": "dataset", "label": "ML CO2 Impact Calculator", "url": "https://mlco2.github.io/impact/", "source": "curated-web", "axis": "energy", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "dataset:mmlu_quant", "kind": "dataset", "label": "MMLU (quant eval standard)", "url": "https://github.com/hendrycks/test", "source": "curated-web", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "dataset:lm_eval_harness", "kind": "dataset", "label": "EleutherAI lm-evaluation-harness", "url": "https://github.com/EleutherAI/lm-evaluation-harness", "source": "curated-web", "axis": "quant", "layer": 0, "maps_to_surface": "energy"}
{"type": "node", "id": "dataset:nmnist", "kind": "dataset", "label": "N-MNIST neuromorphic dataset", "url": "https://www.garrickorchard.com/datasets/n-mnist", "source": "curated-web", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "dataset:dvs_gesture", "kind": "dataset", "label": "DVS128 Gesture dataset (IBM)", "url": "https://research.ibm.com/interactive/dvsgesture/", "source": "curated-web", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "dataset:shd_ssc", "kind": "dataset", "label": "Spiking Heidelberg Digits (SHD/SSC)", "url": "https://zenkelab.org/resources/spiking-heidelberg-datasets-shd/", "source": "curated-web", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "dataset:intel_ndns", "kind": "dataset", "label": "Intel N-DNS Challenge (neuromorphic denoising)", "url": "https://github.com/IntelLabs/IntelNeuromorphicDNSChallenge", "source": "curated-web", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "dataset:prophesee_gen", "kind": "dataset", "label": "Prophesee event-camera automotive datasets", "url": "https://www.prophesee.ai/2020/01/24/prophesee-gen1-automotive-detection-dataset/", "source": "curated-web", "axis": "neuro", "layer": 0, "maps_to_surface": "neuromorphic"}
{"type": "node", "id": "dataset:drone_vs_bird", "kind": "dataset", "label": "Drone-vs-Bird Detection Challenge", "url": "https://wosdetc2023.wordpress.com", "source": "curated-web", "axis": "defense", "layer": 0}
{"type": "node", "id": "dataset:anti_uav", "kind": "dataset", "label": "Anti-UAV challenge dataset", "url": "https://anti-uav.github.io", "source": "curated-web", "axis": "defense", "layer": 0}
{"type": "node", "id": "dataset:seaships", "kind": "dataset", "label": "SeaShips maritime detection dataset", "url": "https://github.com/jiaming-wang/SeaShips", "source": "curated-web", "axis": "defense", "layer": 0}
{"type": "node", "id": "dataset:nuscenes", "kind": "dataset", "label": "nuScenes multi-sensor autonomous dataset", "url": "https://www.nuscenes.org", "source": "curated-web", "axis": "fusion", "layer": 0}
{"type": "node", "id": "dataset:kitti", "kind": "dataset", "label": "KITTI vision benchmark (LiDAR/camera)", "url": "https://www.cvlibs.net/datasets/kitti/", "source": "curated-web", "axis": "fusion", "layer": 0}
{"type": "node", "id": "dataset:waymo_open", "kind": "dataset", "label": "Waymo Open Dataset (multi-sensor)", "url": "https://waymo.com/open/", "source": "curated-web", "axis": "fusion", "layer": 0}
{"type": "node", "id": "dataset:pdebench", "kind": "dataset", "label": "PDEBench (PINN/operator benchmark)", "url": "https://github.com/pdebench/PDEBench", "source": "curated-web", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "dataset:pdearena", "kind": "dataset", "label": "PDEArena", "url": "https://github.com/pdearena/pdearena", "source": "curated-web", "axis": "pinn", "layer": 0, "maps_to_surface": "pinn"}
{"type": "node", "id": "dataset:google_qec_data", "kind": "dataset", "label": "Google Quantum AI QEC experiment data", "url": "https://zenodo.org/records/6804040", "source": "curated-web", "axis": "qec", "layer": 0, "maps_to_surface": "qhall"}
{"type": "node", "id": "dataset:gsm8k", "kind": "dataset", "label": "GSM8K (agent reasoning benchmark)", "url": "https://github.com/openai/grade-school-math", "source": "curated-web", "axis": "agents", "layer": 0}
{"type": "node", "id": "dataset:gaia_bench", "kind": "dataset", "label": "GAIA benchmark (agent assistants)", "url": "https://huggingface.co/datasets/gaia-benchmark/GAIA", "source": "curated-web", "axis": "agents", "layer": 0}
{"type": "node", "id": "dataset:swe_bench", "kind": "dataset", "label": "SWE-bench (agentic coding)", "url": "https://www.swebench.com", "source": "curated-web", "axis": "agents", "layer": 0}
{"type": "node", "id": "dataset:webarena", "kind": "dataset", "label": "WebArena (web agents)", "url": "https://webarena.dev", "source": "curated-web", "axis": "agents", "layer": 0}
{"type": "node", "id": "dataset:atari100k", "kind": "dataset", "label": "Atari 100k (world-model RL benchmark)", "url": "https://github.com/openai/atari-py", "source": "curated-web", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "dataset:dmc_suite", "kind": "dataset", "label": "DeepMind Control Suite", "url": "https://github.com/google-deepmind/dm_control", "source": "curated-web", "axis": "worldmodel", "layer": 0, "maps_to_surface": "worldmodel"}
{"type": "node", "id": "dataset:imagenet_flow", "kind": "dataset", "label": "ImageNet (generative FID benchmark)", "url": "https://www.image-net.org", "source": "curated-web", "axis": "flowmatch", "layer": 0, "maps_to_surface": "flowmatch"}
{"type": "edge", "src": "axis:energy", "dst": "surface:energy", "rel": "maps_to_surface"}
{"type": "edge", "src": "axis:quant", "dst": "surface:energy", "rel": "maps_to_surface"}
{"type": "edge", "src": "axis:neuro", "dst": "surface:neuromorphic", "rel": "maps_to_surface"}
{"type": "edge", "src": "axis:pinn", "dst": "surface:pinn", "rel": "maps_to_surface"}
{"type": "edge", "src": "axis:qec", "dst": "surface:qhall", "rel": "maps_to_surface"}
{"type": "edge", "src": "axis:worldmodel", "dst": "surface:worldmodel", "rel": "maps_to_surface"}
{"type": "edge", "src": "axis:flowmatch", "dst": "surface:flowmatch", "rel": "maps_to_surface"}
{"type": "edge", "src": "repo:microsoft/autogen", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:microsoft/ai-agents-for-beginners", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:JayZeeDesign/research-agents-3.0", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:victordibia/autogen-ui", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AgentOps-AI/agentops", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:karthikvenkatesan-eaton/Autogen_GraphRAG_Ollama", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jaemil/agentsflow", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Upsonic/Tiger", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:victordibia/designing-multiagent-systems", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Andyinater/AutoGen_EnhancedAgents", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:microsoft/spec-to-agents", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:rnadigital/agentcloud", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ksm26/AI-Agentic-Design-Patterns-with-AutoGen", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:microsoft/magentic-ui", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Repello-AI/Agent-Wiz", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:adamwlarson/ai-book-writer", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:JayZeeDesign/vision-agent-with-llava", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:SageMindAI/autogen-agi", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Azure-Samples/dream-team", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ag2ai/fastagency", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:crewAIInc/crewAI", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:crewAIInc/crewAI-examples", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:crewAIInc/crewAI-tools", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:strnad/CrewAI-Studio", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:majacinka/crewai-experiments", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:crewAIInc/awesome-crewai", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AbubakrChan/crewai-UI-business-product-launch", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:alexfazio/viral-clips-crew", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Eng-Elias/CrewAI-Visualizer", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:NanGePlus/CrewAITest", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bhancockio/crewai-updated-tutorial-hierarchical", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:liangdabiao/easy_investment_Agent_crewai", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:alexfazio/crewAI-quickstart", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bhancockio/automate-youtube-with-crewai", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:kid0317/crewai_mas_demo", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:definitive-io/crewai-groq", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:alejandro-ao/crewai-crash-course", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:tonykipkemboi/crewai-gmail-automation", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bhancockio/nextjs-crewai-basic-tutorial", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bhancockio/crewai-rag-deep-dive", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:tom-doerr/dspy_nodes", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:OmidZamani/dspy-skills", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:neoxelox/dspy-inspector", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:iliazlobin/dspy-research", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:DerwenAI/strwythura", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:o6-webwork/dspy-mlflow", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:aelaguiz/langdspy", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:vardhanam/qdrant_dspy", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:avnlp/dspy-opt", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jesk2/dspy-coded", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:thememium/dspy-auto-gepa", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ajkumar-13/Dspy-practice", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ruvnet/onnx-agent", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:nafew-azim/AUTODSPy", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:kmad/dspy-extraction-skill", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bhushang19/dspy-rlm-long-docs-demo", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:xanmendelsohn/LLM-Programs-DSPy", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:iamtushar04/dspy_pipeline", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jaydayal-ai/news-dspy-pipeline", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:purohit08/RAG-DSPy-Pipeline", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:langchain-ai/langchain", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:datawhalechina/llm-universe", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:langchain4j/langchain4j", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:tmc/langchaingo", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:daveebbelaar/langchain-experiments", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:chatchat-space/Langchain-Chatchat", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:kyrolabs/awesome-langchain", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:codebasics/langchain", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:patterns-ai-core/langchainrb", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:brainlid/langchain", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:kaushikb11/awesome-llm-agents", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:davidmigloz/langchain_dart", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:onlyphantom/llm-python", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:zilliztech/GPTCache", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:quarkiverse/quarkus-langchain4j", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:huangjia2019/langchain-in-action", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bragai/bRAG-langchain", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:intel/ipex-llm", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:alphasecio/langchain-examples", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:X-D-Lab/LangChain-ChatGLM-Webui", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:langchain-ai/langgraph", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:google-gemini/gemini-fullstack-langgraph-quickstart", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:langgraph4j/langgraph4j", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:langchain-ai/langgraphjs", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mayooear/ai-pdf-chatbot-langchain", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:langchain-ai/langgraph-example", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:harishneel1/langgraph", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:emarco177/langgraph-course", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:vonzosten/awesome-LangGraph", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:krishnaik06/Agentic-LanggraphCrash-course", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:langchain-ai/new-langgraph-project", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:langchain-ai/langgraph-supervisor-py", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:wassim249/fastapi-langgraph-agent-production-ready-template", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:langchain-ai/langgraph-swarm-py", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:braincrew-lab/langgraph-mcp-agents", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:BrandPeng/Langchain1.0-Langgraph1.0-Learning", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:langchain-ai/react-agent", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:LangChain-OpenTutorial/LangChain-OpenTutorial", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:langchain-ai/langgraph-101", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:campusx-official/langgraph-tutorials", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:FoundationAgents/MetaGPT", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:datawhalechina/hugging-multi-agent", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:geekan/MetaGPT-docs", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:NanGePlus/MetaGPTTest", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:qianyouliang/MetaGPT-Learn", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:FoundationAgents/MetaGPT-Ext", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Ori-Replication/MetaGPT_webui", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:FSoft-AI4Code/AgileCoder", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Lin-A1/novel-agent", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:andrepimenta/metagpt-app", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:kemeny/PongGame", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:startino/aitino", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:scmpevatrons/ai-chatverse", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:FoundationAgents/MetaGPT-App", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:vivy-yi/awesome-agent-orchestration", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:alitrack/QuickStart-MetaGPT", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:time1527/TeaChat", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:cerberuswilliam/MetaGPT", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:minhnn-tiny/MetaGPT_examples", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:evanshlom/MetaGPT-app", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:microsoft/agent-framework", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Ingenimax/agent-sdk-go", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:polyuiislab/infiAgent", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:e2b-dev/awesome-ai-sdks", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:aws/bedrock-agentcore-sdk-python", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:raga-ai-hub/RagaAI-Catalyst", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:symbolica-ai/agentica-python-sdk", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:PaddlePaddle/ERNIE-SDK", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:openserv-labs/sdk", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:cacheplane/angular-agent-framework", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:NapthaAI/naptha-sdk", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:symbolica-ai/agentica-typescript-sdk", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:sslava/ai-sdk-agents", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:sentient-engineering/sentient", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:atomicstrata/atomicmemory", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:hybroai/a2a-adapter", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:maker-community/ElectronBot.DotNet", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:chrispangg/deepagentsdk", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:coleam00/evolution-of-ai-agents", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:huggingface/agents-course", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ALucek/smolagents-guide", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:sinanuozdemir/oreilly-huggingface-tour", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mstrYoda/llm-agents-example", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:aniemerg/smolcc", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Snowflake-Labs/sfguide-build-agentic-workflows-with-huggingface-smolagents-in-snowflake", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:chiarapaglioni/GAIA-agents", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:antunsz/smolagents-crew", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:rizome-dev/go-smolagents", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:VladKha/drone-agent", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:botextractai/ai-huggingface-smolagents", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:kazemihabib/Huggingface-Agents-Course-Marimo-Edition", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:albertovalverde/huggingface-smolagents", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:yusuf-eren/smolagents.js", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:TheColonyCC/smolagents-colony", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Sakeeb91/text2sql-agent", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:SqwareInfotechLearn/SmolAgents-Huggingface", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:anjijava16/huggingface_smolagents_utils", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:virtualramblas/gromacs_smolagent", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:gm-gus/test-smolagents", "dst": "axis:agents", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:semanticarchitectures/interceptorDroneSim", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ParagonTechnologies/cuas-drone-detection", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Soussi-Aymen/drone-detection-frontend", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mohamesb/AI-Powered-Drone-Detection-System", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:GerardGz/autonomous-drone-landing-risk-detection", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Soussi-Aymen/drone-detection-backend", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:cognis-digital/uaslog", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mr-fool/volumetric-drone-detection", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Suliman8/SkyShield", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:JiyounRoth/Drone_RF_Detection_FPGA", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Sayeh-1337/meshkah", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:doguilmak/Drone-Detection-YOLOv11x", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:monemati/PX4-ROS2-Gazebo-YOLOv8", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:wish44165/YOLOv12-BoT-SORT-ReID", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:MrZilinXiao/DroneObjectDetection", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:alebal123bal/khadas_yolov8n_multithread", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:2178568050/AntiUAV_Improved_Based_on-YOLOv11", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:aiesst/UAV_PyTorch_YOLOv3", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:larics/synthetic-UAV", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:takzen/yolo-military-drone-detection", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:anasbadawy/YOLOv3-Object-Detection", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jashswayam/Automating-Tree-Counting-through-UAVs-and-YOLOv5-Object-Detection", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:dmdobrea/shieldUAV", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:anhuipl2010/SOD-YOLO", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Xjh-UCAS/YoloOW", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:MartinMohammed/object-tracking-yolo-v8-mil", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:lawlawCodes/MCA-YOLO", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:solawen/anti-uav-yolov11-det", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:v1taaa/YOLOv8-UAV-detection", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:iremustek/uav-object-detection-yolov5x", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:GuccIceCream/yolov8", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:wi5nuu/SENTINEL-X-X-Domain-Threat-Fusion-Platform", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:a-for-aarushi/PS-09---AI-tools-for-Maritime-Domain-Awareness-", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Alexdim620/Deep-Learning---Increasing-Maritime-Domain-Awareness-Using-Spatio-temporal-Sequencial-Data", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Iberasa3/Carcosa", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:aousabdo/watchstander", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AndrewKritikos/ais_anomaly_detection", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jeeva20-AquaSentinel/Jeeva-R--Sea-Guard-AI", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:JunshengFu/tracking-with-Extended-Kalman-Filter", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ZHOUYI1023/awesome-radar-perception", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:amyworrall/QuickRadar", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:BLE-Research-Group/MetaRadar", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Research-and-Project/mmWave_radar_tracking", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:radarlabs/react-native-radar", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ThasianX/SpotifyRadar", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:JunshengFu/tracking-with-Unscented-Kalman-Filter", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:radarlabs/radar-sdk-ios", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:radarlabs/radar-sdk-android", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:XiangyuDing/Radar-Detecting-and-Tracking", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:duckduckgo/tracker-radar-detector", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:duckduckgo/tracker-radar-wiki", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:elsbrock/hetzner-radar", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:LJacksonPan/RaTrack", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:radarlabs/radar-sdk-js", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:dhananjaymenon/SpeedRadar-OpenCV-", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:thkruz/keeptrack.space", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:drpwchen/paper-radar", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:radarlabs/flutter-radar", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:micropython-IMU/micropython-fusion", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Fusion-Goettingen/ExtendedObjectTracking", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bernwang/latte", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:aleksandrkim61/EagerMOT", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:TUMFTM/FusionTracking", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:thp/psmoveapi", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:UditBhaskar19/OBJECT_TRACKING_MULTI_SENSOR_FUSION", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ptiwari0664/SensorFusionNanoDegree", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:walkerbrown/sfnd-3d-object-tracking", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:palaghias/SensorFusion", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:yrlu/orientation_tracking-unscented_kalman_filter", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:max-kazak/SensorFusion", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:salmoshu/IndoorFusionNav", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Ram-Godavarthi/Sensor_Fusion_3D_Object_Tracking_Lidar-Camera", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Autoferry/sensor_fusion_dataset", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AbdullahGM1/l2i_fusion_detection", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:srnand/Object-Tracking-and-State-Prediction-with-Unscented-and-Extended-Kalman-Filters", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mzahana/smart_track", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Southparketeer/SLAM-Large-Dense-Scene-Real-Time-3D-Reconstruction", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:studian/SFND_P4_3D_Object_Tracking", "dst": "axis:defense", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:sufirehman/carbon-aware-ml-scheduler", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ksm26/Carbon-Aware-Computing-for-GenAI-Developers", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:boringlee24/sc23-clover", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:atharvchaudhari2907-code/CarbonQuest", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:UdayKurla/Carbon-Aware-Optimistic-Machine-Learning-Framework-CAOMLF-", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:nirtutac123/Carbon-Aware-Comparison-of-Machine-Learning-Models", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:yellelieder/carbon-aware-prediction-api", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ahmadrezadehghan/Carbon-Aware-Machine-Learning-for-Energy-Efficient-Quantum-Data-Centers", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Mayur-zope07/Carbon-Aware-Lifestyle-Optimizer", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:THESARTHAKGOEL/eco-ops", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:vernekaradarsh/CarbonAware_CropPrediction_using_DevOps", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:USD-AI-ResearchLab/ai-care", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:marknash22/Carbon-Aware-Scheduling-in-Cloud-Data-Centres-Using-Machine-Learning-project-for-my-masters-degree", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ramanaa-dev/ecotrack-ai-carbon-footprint-platform", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Meena-0726/Green-AI-Sustainability-Framework", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Harshada2012/Carbon_Footprint_Optimization", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:HRNBEnninful/Feasibility-Aware-ML-Energy-Materials", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Farhan-Fadillah/household_carbon_predictor", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Farhanfadillah99/household_carbon_predictor", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:avi1822/carbon_calculator", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:climatechange-ai-tutorials/tracking-ml-emissions", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:pramanik-souvik/multimodal-facebook-hateful-meme-detection", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AryaStark13/CMU-BNY-Datathon", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Pm023/CarbonIQ", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:izzulroslan/GreenModel-AI-Carbon-Emission-Tracker", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:RohitSah13/Eco-Ops-Green-Computing-Analytics-", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:yjwong1999/Twin-TD3", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:BIT-MCS/DRL-EC3", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:BIT-MCS/DRL-eFresh", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ahmadfaisal9900/Multi-Agent-Deep-Reinforcement-Learning-for-Energy-Efficient-RIS-Assisted-CoMP-NOMA-Networks", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:youxch/Inverse-design-of-patch-antennas", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:BIT-MCS/DRL-DisasterVC", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:BIT-MCS/e-Divert", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Geraldine-Winston/Energy-Efficient-Building-Design-Recommendations-using-deep-reinforcement-learning.", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:dhivyadharsi/Actor-Critic-Deep-Reinforcement-Learning-for-UAV-Assisted-MEC", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:BIT-MCS/Edics", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:GodeWithWind/GNN4SCMU", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ULudo/DRL-Building-Energy-Ctr", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mehrshaad/DeepRL-Offloading-MEC", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:solgaardlab/photonicbackprop", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:BIT-MCS/jPPO-ConvNTM", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:BIT-MCS/DRL-CEWS", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:NM001007/IST-DFRL-Base-Station-Sleep-Control", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:danielflood/fpga-eeg", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:dataclergy/Forecasting-Hourly-Energy-Consumption-with-Python", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Ishaniiitb/Memristor_based_Custom_Deep_Spiking_Neural_Network", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AI4Green/AI4Green", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:soham2002/GreenRoots", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Rishabhmannu/amazon-greencart-hackathon", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:NaiveNinjas/greenforce", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mwakidenis/Green-AI", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Pampaj7/GreenAI", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Deepsayan-Das/Green-Lens", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ErnestMunyoki/Green-Path", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:fredsta98/GreenChain", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:tholewis/green-software-engineer", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Tharshananth/BankEase-AI", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mahoutukaisali/GreenOps-Tracker", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:GDGC-MET/AiForGreenerPlanet-VibeCoding", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:RosalieJA/Academic_Project_GreenAI_Sustainable_Ressources_4_GreenComputing", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:hameembaba/Project---Creating-a-website-on-title-Green-Scape-Mapping-the-air-quality-for-sustainable-living", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jsnbyxyjsj/Green-Chain-PLI-Hackathon-2.0", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:saurabh-singh-rajput/Green-AI-Resources", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:KOSASIH/ecopulse-platform", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:greenfit-ai/greenfit-ai", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:anashanishaaban/GreenSync", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Aayush-Ankit/ml-inference-benchmarks", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jchuahtacc/ml-gpu-power", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:kathanpanchal/ml-inference-benchmarks", "dst": "axis:energy", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jy0205/Pyramid-Flow", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:yuvraj108c/ComfyUI-FLOAT", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:BioinfoMachineLearning/FlowDock", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:deepbrainai-research/float", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:m1balcerak/EnergyMatching", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:smsharma/minified-generative-models", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:LukasMosser/DeepFlow", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:amorehead/awesome-generative-flows", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:sp-uhh/streamfm", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:alexjli/proteinzen", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:MurrellGroup/Flowfusion.jl", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:aleksandrinvictor/flow-matching", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:MizuhoAOKI/jax_generative_models", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mrjoness/Flow-Back", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:pedrocurvo/follow-the-mean", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:BLEACH366/P2DFlow", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:willisma/diffuse_nnx", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:g4vrel/CFM", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:tesfaldet/genpt", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AI4Science-WestlakeU/FourierFlow", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:gnobitab/RectifiedFlow", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:feizc/FluxMusic", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:VAST-AI-Research/TripoSG", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:TongTong313/rectified-flow", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:gnobitab/InstaFlow", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:magic-research/piecewise-rectified-flow", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:lqiang67/rectified-flow", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:lucidrains/rectified-flow-pytorch", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:cloneofsimo/minRF", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:LituRout/RF-Inversion", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ohayonguy/PMRF", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:GradientSpaces/Rectified-Point-Flow", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:X-LANCE/VoiceFlow-TTS", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:HolmesShuan/FireFlow-Fast-Inversion-of-Rectified-Flow-for-Image-Semantic-Editing", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jacklishufan/OmniFlows", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:EternalEvan/FlowIE", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:wangjiangshan0725/RF-Solver-Edit", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:feifeiobama/RectifID", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:UNITES-Lab/FlowTS", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Pur1zumu/RIFT-SVC", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:malbergo/stochastic-interpolants", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:dongzhuoyao/awesome-flow-matching", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:interpolants/forecasting", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:nmboffi/jax-interpolants", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:martinschiodt/Turbulence_Stochastic_Interpolants", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:KAIST-Visual-AI-Group/BezierFlow", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:nmucke/StochasticInterpolants.jl", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:pnkraemer/mini-stochastic-interpolants", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:multitaskstochasticinterpolant/Code-Multitask-Stochastic-Interpolants", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Erik-Wikingsson/DAISI", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:CompVis/Art-fm", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:WladGrm/si-adistill", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:plurigrid/StochFlow", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:janisaiad/probgraph", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:joaovaleriano/stochastic-interpolants", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:atreya-s/ReturnDistribution_StochasticInterpolants", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:clarkmiyamoto/stochastic-interpolants", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:clarkmiyamoto/interpolants", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Blaise143/stochastic-interpolant-diffusion", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:workerjl/glass_stochastic_interpolant", "dst": "axis:flowmatch", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:zhujun98/sensor-fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ethz-asl/ethzasl_msf", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mithi/fusion-ukf", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:simondlevy/SensorFusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:sharathsrini/Kalman-Filter-for-Sensor-Fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:maddevsio/mad-location-manager", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:paulyehtw/Lidar-and-Radar-sensor-fusion-with-Extended-Kalman-Filter", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:technitute/AKFSF-Simulation-CPP", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mbrossar/FUSION2018", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mithi/fusion-ekf", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:flappyimi/Radar-Basic-Algorithm", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Jeff-Zhouxiaolong/demo_for_kalmanFilter", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:awerries/kalman-localization", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:diegoavillegasg/IMU-GNSS-Lidar-sensor-fusion-using-Extended-Kalman-Filter-for-State-Estimation", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:williamhyin/SFND_Unscented_Kalman_Filter", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:yrlu/orientation_tracking-unscented_kalman_filter", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mithi/fusion-ekf-python", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:soarbear/imu_ekf", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:EliaTarasov/ESKF", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bkarwoski/EKF_fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:EPVelasco/lidar-camera-fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mit-han-lab/bevfusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:CDonosoK/ros2_camera_lidar_fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:LiuFG/Camera-Lidar-Fusion-ROS", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:joshmcculloch/lidar-camera-fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ADLab-AutoDrive/BEVFusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:pangsu0613/CLOCs", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:godloveliang/SFND_3D_Object_Tracking", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ICEORY/DeepStream", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:haomo-ai/SuperFusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jie0110/image-pointcloud-fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ISEE-Technology/lidar-with-velocity", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AutoLidarPerception/kitti_lidar_camera", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:OrangeSodahub/CRLFnet", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:HuangCongQing/multi-sensor-fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:GCaptainNemo/Fusion-Lidar-Camera-ROS", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:zcbmlijygrdwa/camera_lidar_fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:TimKie/YOLO-LiDAR-Fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:APRIL-ZJU/Gaussian-LIC", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:wangxiyang2022/DeepFusionMOT", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:HKUST-Aerial-Robotics/VINS-Fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:2013fangwentao/Multi_Sensor_Fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ethz-asl/ethzasl_sensor_fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:zhh2005757/FAST-LIO-Multi-Sensor-Fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:sjtuyinjie/Ultra-Fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AlexGeControl/Sensor-Fusion-for-Localization-Courseware", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:yichen928/SparseFusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:autonomousvision/transfuser", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jypjypjypjyp/lvio_fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:aleksandrkim61/EagerMOT", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:TurtleZhong/LVIO-SAM", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:TUMFTM/FusionTracking", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:UditBhaskar19/OBJECT_TRACKING_MULTI_SENSOR_FUSION", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ICEORY/PMF", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:GREAT-WHU/DBA-Fusion", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:kekeliu-whu/MSF_LOAM", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:zouyajing/multi_sensor_loclization_and_mapping", "dst": "axis:fusion", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:chakravarthi589/Event-based-Vision_Resources", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:cedric-scheerlinck/dvs_image_reconstruction", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:idsc-frazzoli/retina", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:VLOGroup/dvs-panotracking", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Event-AHU/Event_Camera_in_Top_Conference", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:VLOGroup/dvs-reconstruction", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:better-flow/pydvs", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:prgumd/EVDodgeNet", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:wangxiao5791509/VisEvent_SOT_Benchmark", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:tub-rip/dvs_mcemvs", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:vision-agh/gcnn-dvs-fpga", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:tub-rip/dvs_global_flow_skeleton", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:iliis/dvs_reconstruction", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:TristanWH/DVS4PD", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:xueleichen/snn-dvs-carla", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mapleee/dvs-sonification", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Neuromorphicism/neuromorphic-bird-classifier-desktop-app-dvs-stream-cli-and-gui", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:cargonriv/dvs", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:tub-rip/dvs_mosaic_skeleton", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:NAIL-HNU/CalibrMultiDvs", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Kanaderu/lava-docker", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:open-neuromorphic/awesome-neuromorphic-hw", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:prophesee-ai/openeb", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:open-neuromorphic/fpga-snntorch", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:qiaokaki/AedatTools", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:alandiamond/spinnaker-neuromorphic-classifier", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:synsense/rockpool", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jeshraghian/ESSCIRC23-os-neuromorphic-tutorial", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:synsense/sinabs", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:colinshane/LIF_Neuromorphic", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:combra-lab/snn-eeg", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:markplagge/NeMo", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Thonner/NeuromorphicProcessor", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:lachlanchen/OpenHI", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:hisrg/Neural-Network-Compression-and-Accelerator-on-Hardware", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AdamDHines/LENS", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:KI-ASIC-TUM/time-coded-SFT", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:sandialabs/NeuroFEM", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:cepdnaclk/e16-4yp-neuromorphic-architecture", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ferdinandolivier/Dynex-Wallet-App", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:solversa/Master-Thesis-Brain-Machine-Interface", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:nengo/nengo-ocl", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:nengo/nengo-mpi", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:atakehiro/Neural_Simulator-Colab", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:simondlevy/NengoCPP", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ctn-archive/gosmann-frontiers2017", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:NickleDave/aver", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jvitku/nengo_java", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mtrberzi/nengo-gpu-surrogate-backend", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:kpc-simone/modelling_tutorial", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:OmarGAlcantara/MIL-Simulation-Nengo-ROS-XPlane", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jeshraghian/snntorch", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jjd1123/snntorch-implement4spike-deeplab", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Laz4rz/spikingNeuralNetworks", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AndreaLolli2912/Spiking-ResNet", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Sergeevks/SpikingNetTutorial", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:shilpakancharla/snn-networking", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:chardiwall/DPSNN", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Brain-inspired-Neural-Networks-Lab/LGN_snnTorch_classification", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:reyhane-1997/snntorch_leaky", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jmadden173/tt05-delta-modulation", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Saad-data/ANN-to-SNN-Conversion-with-snnTorch", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Twenkid/SNN", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:franzhd/snntorch_network", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Triponymous/brAIn", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:muddycode-tech/SPIKING_MNIST_SNN", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:spikora/SpikingTSF", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Biswajitnahak2003/snn-glacier-segmentation", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:KrishnaSagar-108/SNNtorch.js-SpikeNet.js", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:KP-AROB/AROB-SNNTorch", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:SpikingIntelligenceSystem/snn-mnist-classifier-project", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:fangwei123456/spikingjelly", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:conda-forge/spikingjelly-feedstock", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Barchid/spikingjelly-lightning", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:IamSandipanBhowmick/SNN_DSpike", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:TheBrainLab/Awesome-Spiking-Neural-Networks", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:TheBrainLab/Spikingformer", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Yanqi-Chen/spikingjellyCppExt", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:IamSandipanBhowmick/SNN-Segmentation-Via-SpikingJelly", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:CodeAlanqian/SNN-MNIST", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:lcedapro/SpikingJelly", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:coderonion/awesome-snn", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:DPR00/SpikingNeuralNetworks", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:TheBrainLab/SGLFormer", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:gv1x2/ANN2SNN-SpikingJelly-", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AllenYolk/dendritic-spiking-neuron", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:daydreamal/SpikingJelly_study", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ali-rasteh/spikingjelly-develop", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:DingJianhao/spikingjelly_lite", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Barchid/liaf-lightning", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:twetto/sje_extensions", "dst": "axis:neuro", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:lululxvi/deepxde", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Wulx2050/DeepXDE-and-PINN", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:imcs-compsim/pinns_for_comp_mech", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:aid4nscud/PINNResearch", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:stfc-sciml/DeepXDE-ZCS", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:yiwang89/lululxvi-deepxde", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:circularsquare/dxde-covid", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:PhysicsTeacher13/Deepxde", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:conda-forge/deepxde-feedstock", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:pescap/FastDeepXDE", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:KozakHou/Python-Tensorflow-DeepXDE", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:javierfa98/PINNs-Examples", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:shadzzz90/Heat-Equation-using-Deep-Galerkin-Method-and-DeepXDE", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:athtareq/PFE_LicenceMIASI", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:praksharma/DeepXDE-frontend", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:zongzi13545329/PINNS", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:xuelanghanbao/AI4XDE", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:tonymlebaron/DeepXDE_Training", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:zjuliu/AIgibson", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:StoneDaweiKing/Example_on_deepXde", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:neo-fetch/nvidia-modulus-airfoil-optimisation", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:adytiaa/physAI_CFDsim", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:TejasARathod/PhyCV-PhysicsNemo-Triton-Yolov9", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Mattjesc/PTQ-MeshGraphNet-NVIDIA-Modulus", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Shrestha-Bipin/PINN_Projects", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:saitejasrivilli/maxwell-pinn", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:li-Pingan/fourier-neural-operator", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:neuraloperator/Geo-FNO", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:SciML/FluxNeuralOperators.jl", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:alasdairtran/fourierflow", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:erik-norlin/Fourier-Neural-Operator", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:SciML/NeuralOperators.jl", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:lonestar686/AdaptiveFourierNeuralOperator", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:gegewen/ufno", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:slimgroup/dfno", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:abelsr/Fourier-Neural-Operator", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Hrrsmjd/fourier_neural_operator", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bilzinet/pifno", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ADharaUTEXAS123007/FNO", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:camlab-ethz/DSE-for-NeuralOperators", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:matlab-deep-learning/fourier-neural-operator", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Duke-MG-Lab/Allen-Cahn-FNO", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:slimgroup/FNO4CO2", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:astanziola/fourier-neural-operator-flax", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:lu-group/fourier-mionet-gcs", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:CUBELeonwang/FNO-3DUM", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:prateekbhustali/Physics-Informed-Neural-Networks", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:idrl-lab/PINNpapers", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jayroxis/PINNs", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mathLab/PINA", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:SciML/NeuralPDE.jl", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:PML-UCF/pinn", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:rezaakb/pinns-torch", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:EhsanGh94/PINN", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:wang-fujin/PINN4SOH", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:gmisy/Physics-Informed-Neural-Networks-for-Power-Systems", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:benmoseley/harmonic-oscillator-pinn", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:nanditadoloi/PINN", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Raocp/PINN-elastodynamics", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Raocp/PINN-laminar-flow", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:nguyenkhoa0209/pinns_tutorial", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:FilippoMB/Physics-Informed-Neural-Networks-tutorial", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Photon-AI-Research/NeuralSolvers", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:a1k12/characterizing-pinns-failure-modes", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:pierremtb/PINNs-TF2.0", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:okada39/pinn_wave", "dst": "axis:pinn", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:oliverweissl/NeuralDecoderToric3D", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Olfj/QEC_GNN-RNN", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:thatemocoder/qec-neural-decoder", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:GrahamYan/QEC-neural-decoder-benchmark", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:sghowell/nano-qec", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:thisac/qecco", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:roguetrainer/bnn-for-qec-decoder", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:afogelis/ml-qec-decoder", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Sumitchongder/adaptive-qec-decoder", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:adityakhannaadk/Spiking-Neural-Decoders", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:PrismaticFlame/qec_decoder_transformer", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:EnriqueHA/qec_toric", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ibengtsson/qec_nn_w_mwpm", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:m2papierz/gnns-qec-decoding", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bledden/pathfinder", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:watermarkhu/qsurface", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:nanleij/The-toric-code", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:cduck/VLQ", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:multimodalas/fusion-qec-sim", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:rasidi3112/Quantum-error-correction-threshold-simulator", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:emreyalcin26/SurfaceCodes", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:seandiscovery/quantum_topology", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:cobycloud/quantum-error-correction", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:qfizik/Surface-Code", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:hpoqh/Surface_Code", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:aknapen/Pinball", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Alexisdevpro/surfaces_codes_stim", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:btq-ag/QLDPC", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:PriyaRana19/quantum-error-correction-surface-code", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:shipradsingh/surface-codes-quantum-error-correction", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Linghua-Zhu/surface-code", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:glanzz/qec-surface-code", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:conition/surface_code", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:natashamp/Quantum-Error-Correction-Decoder", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ftahas/Quantum-Computing", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:overshiki/stim-hs", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:NTrevisani/Quantum_Stimulator", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:DeDuckProject/stim-mcp", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:HABER7789/QuantumFaultSim", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Pyhroff/qec-lab", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AriaWu34/qec-surface-code-simulation", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:yaleqc/qtcodes", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:cbmi-group/FFM-Multi-Decoder-Network", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bcriger/py-qcode", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:MikeVasmer/Sweep-Decoder-Boundaries", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ethanlake/message-passing-decoders", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:relicx99991231/MatrixCode", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:adam-the-hacker/TIPE-Quantum-Resilience", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:OgatiesInstitute/Iron-Skeleton", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:lostree99/hyperbolic_decoding", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ericrenone/KITAEV", "dst": "axis:qec", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mit-han-lab/llm-awq", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Kubenew/TurboQuant-v3", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:liyuan24/nanoquantization", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ziyoudeshizi-hub/temporal-code", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:archanareddy3640/AWQ-LLM-Quantization", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ziyoudeshizi-hub/aemp", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:QuangHPV/mlsys-awq", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ziyoudeshizi-hub/aatq", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Epsom700/RotorQuant", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:isgaoyan/BoundaryQAT", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:leeroopedia/workflow-mit-han-lab-llm-awq-awq-model-quantization", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:vk032503/test-time-quantization-llm-inference", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AlessandroVaraldi/approx-activations-lstm", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Ange10jk/AWQ-reproduction", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:vimarsh244/llm-awq", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jun-hyun-kim/ExtraAWQ", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:panjd123/llm-awq-reproduction", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ananya-mh/MoE-Quantization-Study", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:RiyaJ6/Solar10.7BInferenceOptimizer", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Hayder-H8/AWQ-3bits-on-small-LLMs", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bitsandbytes-foundation/bitsandbytes", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:facebookresearch/bitsandbytes", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jllllll/bitsandbytes-windows-webui", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:comfyanonymous/ComfyUI_bitsandbytes_NF4", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:taprosoft/llm_finetuning", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:broncotc/bitsandbytes-rocm", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:cyan2k/molmo-7b-bnb-4bit", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:DeXtmL/bitsandbytes-win-prebuilt", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mohitmishra786/BitsAndBytes", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:james-things/bitsandbytes-prebuilt-all_arch", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:conda-forge/bitsandbytes-feedstock", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bits-and-bytes-association/bitsandbytesassociation.ca", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:heiko-hotz/sm-bnb-transformers", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:aredden/torch-bnb-fp4", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:DaoyuanLi2816/can-i-finetune-this", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ZoffixUser4092/bitsandbytes", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:squeakus/bitsandbytes", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:dvgodoy/FineTuningLLMs", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:subhash307/SpringBoot-BitsAndBytes", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bitsandbytes-foundation/bitsandbytes-intel", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:vllm-project/vllm", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:NVIDIA/TensorRT-LLM", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:openlake-project/openlake", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:NVIDIA/Star-Attention", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:quic/efficient-transformers", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:VectorInstitute/vector-inference", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mit-han-lab/Quest", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:intel/neural-speed", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AlibabaResearch/flash-llm", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:usyd-fsalab/fp6_llm", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:nobodywho-ooo/nobodywho", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mit-han-lab/duo-attention", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:z-lab/paroquant", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:LeanModels/DFloat11", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:wangcx18/llm-vscode-inference-server", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:NLPOptimize/flash-tokenizer", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:inferflow/inferflow", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:skylight-org/sparse-attention-hub", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:opengear-project/GEAR", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:xLLM-AI/xllm-service", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:qwopqwop200/GPTQ-for-LLaMa", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AutoGPTQ/AutoGPTQ", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:IST-DASLab/gptq", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ModelCloud/GPTQModel", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Lightning-AI/lit-llama", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:intel/neural-compressor", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:IST-DASLab/gptq-gguf-toolkit", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:wejoncy/QLLM", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:taishan1994/LLM-Quantization", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:K024/chatglm-q", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:abhinand5/gptq_for_langchain", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:davisyoshida/jax-gptq", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:xhedit/quantkit", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:inferless/dolphin-2.5-mixtral-8x7b-gptq", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:IST-DASLab/MatGPTQ", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:seonglae/llama2gptq", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:inferless/mixtral-8x7b-v0.1", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:EasonGZY/AutoAPTQ", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bayjarvis/llm", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:IST-DASLab/GPTQ-Babai", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:horseee/LLM-Pruner", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:tianyic/only_train_once_personal_footprint", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:openvinotoolkit/nncf", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:MAC-AutoML/MindPipe", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:CASIA-LMC-Lab/FLAP", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:microsoft/only_train_once", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:SamsungSAILMontreal/ream", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:MAC-AutoML/Awesome-Efficient-Large-Models", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bupt-ai-club/llm-compression-papers", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:daniel-eai/LoRP-Locality-Aware-Redundancy-Pruning", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:yaya-sy/lillama", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:MyPrototypeWhat/context-chef", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:gaosh/ToMoE", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:upunaprosk/Awesome-LLM-Compression-Safety", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:cbacary/MoDeGPT", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:transcendencelabs/gateframe-context-manager", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:moxin-org/CC-MoE", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:railus2/Semantic-Pruning-Pipeline-for-LLM-Compression", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:psunlpgroup/Compression-Effects", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:RWKV/rwkv.cpp", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:intel/ipex-llm-tutorial", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Mininglamp-AI/cider", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:bassrehab/triton-kernels", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:xigh/herbert-rs", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:dasdristanta13/LLM-Lora-PEFT_accumulate", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jiaoch/Triton-INT8", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:NguyenThaiVu/llm_int8_quant", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jinho-choi123/LLM.int8-quantization-experiment", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Ne-minus/nlp-llm_int8-proj", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ankitgmishra/int8", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Aswathy-K/llm-quantization-benchmark", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:CuongNgyn2005/LLM_GEMMA3-1B-INT8", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:2404589803/LowMemoryLLM", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:shyamsridhar123/Quantization", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:moneyally/yua-t16", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:fei121/qwen3-8b-quant", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:saadtariq001s/custom-INT8-quantizer", "dst": "axis:quant", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:danijar/dreamerv3", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:danijar/dreamerv2", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:nicklashansen/dreamer4", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ucd-dare/CarDreamer", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:JeffWang987/DriveDreamer", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:f1yfisher/DriveDreamer2", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:vincent-thevenin/DreamerV2-Pytorch", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:JeffWang987/WorldDreamer", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:PKU-Alignment/SafeDreamer", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:OSU-NLP-Group/WebDreamer", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:changchencc/TransDreamer", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:GigaAI-research/DriveDreamer", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:esteveste/dreamerV2-pytorch", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:youngzhou1999/DriveDreamer-Policy", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:burchim/DreamerV3-PyTorch", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:machines-in-motion/dreamer-v4", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:naivoder/dreamerv3", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Cimy-wang/FusDreamer", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:ParamThakkar123/torchwm", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:chenghands-on/Dreamer_assemble", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AlmondGod/tinyworlds", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:SkyworkAI/Matrix-Game", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:insait-institute/GenieRedux", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Huster-YZY/GenieDrive", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:showlab/Olaf-World", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:imsight-knowhow/genie3-survey", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Pseudo-Lab/hello-world-models", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:nomitchell/pytorch-genie-world-model", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:danimelatru/Mini-Genie", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:plugyawn/opengenie", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AmanSwar/genie", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jin-seop-shin/Genie_world_model", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Nhatlinh9898/Genie-Forge-World-Model-AI", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:rotem154154/efficient_genie", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Nonepf/birds-in-world-models", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:milasd/nanogenie", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:BABI1023/Study-genie", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:754liam/Genie-Opt", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:edisonzhu2006/lucid", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:mattqlf/ephemeral-submission", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:facebookresearch/jepa", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:gaasher/I-JEPA", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:facebookresearch/ijepa", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AbdelStark/awesome-jepa", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Ayumu-J-S/Point-JEPA", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:kaland313/CNN-JEPA", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:waterdisappear/SAR-JEPA", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:HaoranZhuExplorer/adljepa", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jonwiggins/H-JEPA", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:LudovicTuncay/Audio-JEPA", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:theAdamColton/ijepa-enhanced", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:filipbasara0/simple-ijepa", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jackswl/bim-jepa", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:kweimann/ECG-JEPA", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:aidelab-iitbombay/RadJEPA", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:helloelora/jepa-point-cloud", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:marypilataki/amt-jepa", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:VU-AIML/SAT-JEPA-DIFF", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:driano1221/LeJEPA-TimeSeries", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:aimagelab/JARVIS", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:tkipf/c-swm", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:danijar/daydreamer", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:learning-at-home/hivemind", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Snowflake-Labs/agent-world-model", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:UMass-Embodied-AGI/TesserAct", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:eloialonso/diamond", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:leggedrobotics/robotic_world_model", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:TencentARC/AnimeSR", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Little-Podi/AdaWorld", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:codingforentrepreneurs/The-Hello-World-of-Machine-Learning", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:AIAnytime/Machine-Learning-Models-Implementation", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:jlin816/dynalang", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:itsmuriuki/FIFA-2018-World-cup-predictions", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:dariopavllo/textured-3d-gan", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:thuml/RLVR-World", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:Tencent-Hunyuan/Hy-Embodied-0.5-VLA", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:facebookresearch/denoised_mdp", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:karthikncode/text-world-player", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:maris205/airsim_agent", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "repo:imgeorgiev/PWM", "dst": "axis:worldmodel", "rel": "repo_in_axis"}
{"type": "edge", "src": "paper:2402.11651", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2402.11651", "dst": "author:renxi_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.11651", "dst": "author:haonan_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.11651", "dst": "author:xudong_han", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.11651", "dst": "author:yixuan_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.11651", "dst": "author:timothy_baldwin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.10464", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2304.10464", "dst": "author:yiduo_guo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.10464", "dst": "author:yaobo_liang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.10464", "dst": "author:chenfei_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.10464", "dst": "author:wenshan_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.10464", "dst": "author:dongyan_zhao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.27825", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.27825", "dst": "author:kai_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.27825", "dst": "author:yan_pang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.27825", "dst": "author:tianhao_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.19065", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2404.19065", "dst": "author:gabriel_sarch", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.19065", "dst": "author:sahil_somani", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.19065", "dst": "author:raghav_kapoor", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.19065", "dst": "author:michael_j_tarr", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.19065", "dst": "author:katerina_fragkiadaki", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.24775", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2606.24775", "dst": "author:wei_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.24775", "dst": "author:xuanhe_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.24775", "dst": "author:shaokun_han", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.24775", "dst": "author:hongming_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.24775", "dst": "author:guoliang_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:1503.07220", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1503.07220", "dst": "author:ekhlas_sonu", "rel": "authored_by"}
{"type": "edge", "src": "paper:1503.07220", "dst": "author:yingke_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:1503.07220", "dst": "author:prashant_doshi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.00764", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2408.00764", "dst": "author:mengkang_hu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.00764", "dst": "author:pu_zhao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.00764", "dst": "author:can_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.00764", "dst": "author:qingfeng_sun", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.00764", "dst": "author:jianguang_lou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2310.15127", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2310.15127", "dst": "author:gabriel_sarch", "rel": "authored_by"}
{"type": "edge", "src": "paper:2310.15127", "dst": "author:yue_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2310.15127", "dst": "author:michael_j_tarr", "rel": "authored_by"}
{"type": "edge", "src": "paper:2310.15127", "dst": "author:katerina_fragkiadaki", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.02645", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2409.02645", "dst": "author:jannik_peters", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.02645", "dst": "author:constantin_waubert_de_puiseau", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.02645", "dst": "author:hasan_tercan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.02645", "dst": "author:arya_gopikrishnan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.02645", "dst": "author:gustavo_adolpho_lucas_de_carvalho", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.07353", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2306.07353", "dst": "author:damien_pellier", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.07353", "dst": "author:alexandre_albore", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.07353", "dst": "author:humbert_fiorino", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.07353", "dst": "author:rafael_bailon_ruiz", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.24957", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.24957", "dst": "author:amap_ai_agent_team", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.24957", "dst": "author:yulan_hu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.24957", "dst": "author:xiangwen_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.24957", "dst": "author:sheng_ouyang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.24957", "dst": "author:hao_yi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.21676", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2503.21676", "dst": "author:nicolas_zucchet", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.21676", "dst": "author:j_rg_bornschein", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.21676", "dst": "author:stephanie_chan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.21676", "dst": "author:andrew_lampinen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.21676", "dst": "author:razvan_pascanu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.01774", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2011.01774", "dst": "author:scott_e_friedman", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.01774", "dst": "author:robert_p_goldman", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.01774", "dst": "author:richard_g_freedman", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.01774", "dst": "author:ugur_kuter", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.01774", "dst": "author:christopher_geib", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.04428", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2603.04428", "dst": "author:yakov_pyotr_shkolnikov", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.13930", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.13930", "dst": "author:samuel_rothfarb", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.13930", "dst": "author:megan_c_davis", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.13930", "dst": "author:ivana_matanovic", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.13930", "dst": "author:baikun_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.13930", "dst": "author:edward_f_holby", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.01023", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2404.01023", "dst": "author:zeeshan_rasheed", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.01023", "dst": "author:muhammad_waseem", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.01023", "dst": "author:kari_syst", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.01023", "dst": "author:pekka_abrahamsson", "rel": "authored_by"}
{"type": "edge", "src": "paper:2309.02427", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2309.02427", "dst": "author:theodore_r_sumers", "rel": "authored_by"}
{"type": "edge", "src": "paper:2309.02427", "dst": "author:shunyu_yao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2309.02427", "dst": "author:karthik_narasimhan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2309.02427", "dst": "author:thomas_l_griffiths", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.10793", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2312.10793", "dst": "author:renxi_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.10793", "dst": "author:haonan_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.10793", "dst": "author:minghao_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.10793", "dst": "author:yuxia_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.10793", "dst": "author:xudong_han", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.12244", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2304.12244", "dst": "author:can_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.12244", "dst": "author:qingfeng_sun", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.12244", "dst": "author:kai_zheng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.12244", "dst": "author:xiubo_geng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.12244", "dst": "author:pu_zhao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.16158", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2401.16158", "dst": "author:junyang_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.16158", "dst": "author:haiyang_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.16158", "dst": "author:jiabo_ye", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.16158", "dst": "author:ming_yan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.16158", "dst": "author:weizhou_shen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.04578", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2402.04578", "dst": "author:jiaqi_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.04578", "dst": "author:yuxian_jiang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.04578", "dst": "author:jiachen_lu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.04578", "dst": "author:li_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2310.00034", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2310.00034", "dst": "author:yuzhang_shang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2310.00034", "dst": "author:zhihang_yuan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2310.00034", "dst": "author:qiang_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2310.00034", "dst": "author:zhen_dong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.06196", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.06196", "dst": "author:charlie_masters", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.06196", "dst": "author:marta_grze_kiewicz", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.06196", "dst": "author:stefano_v_albrecht", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.19565", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2504.19565", "dst": "author:meng_xiao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.19565", "dst": "author:xunxin_cai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.19565", "dst": "author:qingqing_long", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.19565", "dst": "author:chengrui_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.19565", "dst": "author:yuanchun_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2309.07870", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2309.07870", "dst": "author:wangchunshu_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2309.07870", "dst": "author:yuchen_eleanor_jiang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2309.07870", "dst": "author:long_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2309.07870", "dst": "author:jialong_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2309.07870", "dst": "author:tiannan_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2308.16149", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2308.16149", "dst": "author:neha_sengupta", "rel": "authored_by"}
{"type": "edge", "src": "paper:2308.16149", "dst": "author:sunil_kumar_sahu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2308.16149", "dst": "author:bokang_jia", "rel": "authored_by"}
{"type": "edge", "src": "paper:2308.16149", "dst": "author:satheesh_katipomu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2308.16149", "dst": "author:haonan_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.19266", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2405.19266", "dst": "author:dingkang_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.19266", "dst": "author:jinjie_wei", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.19266", "dst": "author:dongling_xiao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.19266", "dst": "author:shunli_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.19266", "dst": "author:tong_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2203.08975", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2203.08975", "dst": "author:changxi_zhu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2203.08975", "dst": "author:mehdi_dastani", "rel": "authored_by"}
{"type": "edge", "src": "paper:2203.08975", "dst": "author:shihan_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:1311.5108", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1311.5108", "dst": "author:jean_baptiste_soyez", "rel": "authored_by"}
{"type": "edge", "src": "paper:1311.5108", "dst": "author:gildas_morvan", "rel": "authored_by"}
{"type": "edge", "src": "paper:1311.5108", "dst": "author:daniel_dupont", "rel": "authored_by"}
{"type": "edge", "src": "paper:1311.5108", "dst": "author:rochdi_merzouki", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.08322", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2508.08322", "dst": "author:muhammad_haseeb", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.06333", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2412.06333", "dst": "author:f_bredell", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.06333", "dst": "author:h_a_engelbrecht", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.06333", "dst": "author:j_c_schoeman", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.20138", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2412.20138", "dst": "author:yijia_xiao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.20138", "dst": "author:edward_sun", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.20138", "dst": "author:di_luo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.20138", "dst": "author:wei_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.07324", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2401.07324", "dst": "author:weizhou_shen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.07324", "dst": "author:chenliang_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.07324", "dst": "author:hongzhan_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.07324", "dst": "author:ming_yan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.07324", "dst": "author:xiaojun_quan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.15656", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2506.15656", "dst": "author:wenhao_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.15656", "dst": "author:selvakumar_manickam", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.15656", "dst": "author:yung_wey_chong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.15656", "dst": "author:shankar_karuppayah", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.13343", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2510.13343", "dst": "author:shota_takayama", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.13343", "dst": "author:katsuhide_fujita", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.12532", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2410.12532", "dst": "author:dingkang_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.12532", "dst": "author:jinjie_wei", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.12532", "dst": "author:mingcheng_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.12532", "dst": "author:jiyao_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.12532", "dst": "author:lihao_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.03350", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2604.03350", "dst": "author:paul_saves", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.03350", "dst": "author:matthieu_mastio", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.03350", "dst": "author:nicolas_verstaevel", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.03350", "dst": "author:benoit_gaudou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.03128", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2602.03128", "dst": "author:abdelghny_orogat", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.03128", "dst": "author:ana_rostam", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.03128", "dst": "author:essam_mansour", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.07165", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2502.07165", "dst": "author:peipei_wei", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.07165", "dst": "author:dimitris_dimitriadis", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.07165", "dst": "author:yan_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.07165", "dst": "author:mingwei_shen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.03278", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.03278", "dst": "author:michael_theologitis", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.03278", "dst": "author:dan_suciu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.03053", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2506.03053", "dst": "author:sinem_erisken", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.03053", "dst": "author:timothy_gothard", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.03053", "dst": "author:martin_leitgab", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.03053", "dst": "author:ram_potham", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.08156", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2601.08156", "dst": "author:arin_gopalan_yadav", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.08156", "dst": "author:varad_dherange", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.08156", "dst": "author:kumar_shivam", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.20023", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2606.20023", "dst": "author:kaiyue_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.20023", "dst": "author:yuyan_bu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.20023", "dst": "author:jingwei_yi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.20023", "dst": "author:yuchi_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.20023", "dst": "author:biyu_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.16021", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2504.16021", "dst": "author:dinithi_dissanayake", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.16021", "dst": "author:suranga_nanayakkara", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.07551", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2405.07551", "dst": "author:shuo_yin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.07551", "dst": "author:weihao_you", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.07551", "dst": "author:zhilong_ji", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.07551", "dst": "author:guoqiang_zhong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.07551", "dst": "author:jinfeng_bai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2111.01762", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2111.01762", "dst": "author:francisco_estrada", "rel": "authored_by"}
{"type": "edge", "src": "paper:2111.01762", "dst": "author:oscar_calder_n_bustamante", "rel": "authored_by"}
{"type": "edge", "src": "paper:2111.01762", "dst": "author:wouter_botzen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2111.01762", "dst": "author:juli_n_a_velasco", "rel": "authored_by"}
{"type": "edge", "src": "paper:2111.01762", "dst": "author:richard_s_j_tol", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.11163", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2402.11163", "dst": "author:jinhao_jiang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.11163", "dst": "author:kun_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.11163", "dst": "author:wayne_xin_zhao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.11163", "dst": "author:yang_song", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.11163", "dst": "author:chen_zhu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.30247", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2606.30247", "dst": "author:jiaqi_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.30247", "dst": "author:fanghui_song", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.01907", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2409.01907", "dst": "author:taiyu_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.01907", "dst": "author:xuesong_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.01907", "dst": "author:robbe_cools", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.01907", "dst": "author:adalberto_l_simeone", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.26306", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2509.26306", "dst": "author:hehai_lin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.26306", "dst": "author:shilei_cao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.26306", "dst": "author:sudong_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.26306", "dst": "author:haotian_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.26306", "dst": "author:minzhi_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.21309", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.21309", "dst": "author:guopeng_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.21309", "dst": "author:ruiqi_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.21309", "dst": "author:haisheng_tan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.03786", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2505.03786", "dst": "author:md_fahim_anjum", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.13278", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.13278", "dst": "author:jiaru_zou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.13278", "dst": "author:ling_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.13278", "dst": "author:yunzhe_qi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.13278", "dst": "author:sirui_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.13278", "dst": "author:mengting_ai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.20515", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2606.20515", "dst": "author:yalun_dai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.20515", "dst": "author:hao_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.20515", "dst": "author:shulin_tian", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.20515", "dst": "author:runmao_yao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.20515", "dst": "author:yuhao_dong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.10758", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2601.10758", "dst": "author:fengchao_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.10758", "dst": "author:tingmin_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.10758", "dst": "author:van_nguyen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.10758", "dst": "author:carsten_rudolph", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.09809", "dst": "axis:agents", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2502.09809", "dst": "author:jizhou_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.09809", "dst": "author:samuel_lee_cong", "rel": "authored_by"}
{"type": "edge", "src": "paper:1812.10968", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1812.10968", "dst": "author:bilel_benjdira", "rel": "authored_by"}
{"type": "edge", "src": "paper:1812.10968", "dst": "author:taha_khursheed", "rel": "authored_by"}
{"type": "edge", "src": "paper:1812.10968", "dst": "author:anis_koubaa", "rel": "authored_by"}
{"type": "edge", "src": "paper:1812.10968", "dst": "author:adel_ammar", "rel": "authored_by"}
{"type": "edge", "src": "paper:1812.10968", "dst": "author:kais_ouni", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.00995", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2510.00995", "dst": "author:jacob_moore", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.00995", "dst": "author:phil_tokumaru", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.00995", "dst": "author:ian_reid", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.00995", "dst": "author:brandon_sutherland", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.00995", "dst": "author:joseph_ritchie", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.06073", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1911.06073", "dst": "author:george_plastiras", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.06073", "dst": "author:christos_kyrkou", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.06073", "dst": "author:theocharis_theocharides", "rel": "authored_by"}
{"type": "edge", "src": "paper:2202.09661", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2202.09661", "dst": "author:rayan_bahrami", "rel": "authored_by"}
{"type": "edge", "src": "paper:2202.09661", "dst": "author:hamidreza_jafarnejadsani", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.04234", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2009.04234", "dst": "author:alfonso_alc_ntara", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.04234", "dst": "author:jes_s_capit_n", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.04234", "dst": "author:rita_cunha", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.04234", "dst": "author:an_bal_ollero", "rel": "authored_by"}
{"type": "edge", "src": "paper:2001.06066", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2001.06066", "dst": "author:fatih_g_k_e", "rel": "authored_by"}
{"type": "edge", "src": "paper:1006.1956", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1006.1956", "dst": "author:animesh_kr_trivedi", "rel": "authored_by"}
{"type": "edge", "src": "paper:1006.1956", "dst": "author:rajan_arora", "rel": "authored_by"}
{"type": "edge", "src": "paper:1006.1956", "dst": "author:rishi_kapoor", "rel": "authored_by"}
{"type": "edge", "src": "paper:1006.1956", "dst": "author:sudip_sanyal", "rel": "authored_by"}
{"type": "edge", "src": "paper:1006.1956", "dst": "author:sugata_sanyal", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.10492", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2009.10492", "dst": "author:alexander_kern", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.10492", "dst": "author:markus_bobbe", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.10492", "dst": "author:yogesh_khedar", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.10492", "dst": "author:ulf_bestmann", "rel": "authored_by"}
{"type": "edge", "src": "paper:1805.03358", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1805.03358", "dst": "author:ziji_shi", "rel": "authored_by"}
{"type": "edge", "src": "paper:1805.03358", "dst": "author:wee_keong_ng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.06503", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2401.06503", "dst": "author:chandler_timm_c_doloriel", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.06503", "dst": "author:rhandley_d_cajote", "rel": "authored_by"}
{"type": "edge", "src": "paper:2206.01411", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2206.01411", "dst": "author:claudio_zito", "rel": "authored_by"}
{"type": "edge", "src": "paper:2206.01411", "dst": "author:eliseo_ferrante", "rel": "authored_by"}
{"type": "edge", "src": "paper:0804.3894", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:0804.3894", "dst": "author:widyawardana_adiprawita", "rel": "authored_by"}
{"type": "edge", "src": "paper:0804.3894", "dst": "author:adang_suwandi_ahmad", "rel": "authored_by"}
{"type": "edge", "src": "paper:0804.3894", "dst": "author:jaka_semibiring", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.00435", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1807.00435", "dst": "author:gaurav_choudhary", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.00435", "dst": "author:vishal_sharma", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.00435", "dst": "author:ilsun_you", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.00435", "dst": "author:kangbin_yim", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.00435", "dst": "author:ing_ray_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.14543", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2302.14543", "dst": "author:himanshu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.14543", "dst": "author:jinraj_v_pushpangathan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.14543", "dst": "author:harikumar_kandath", "rel": "authored_by"}
{"type": "edge", "src": "paper:2112.11219", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2112.11219", "dst": "author:yasir_ali_farrukh", "rel": "authored_by"}
{"type": "edge", "src": "paper:2112.11219", "dst": "author:irfan_khan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.11113", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2306.11113", "dst": "author:deep_pandey", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.11113", "dst": "author:qi_yu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2105.04026", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2105.04026", "dst": "author:julius_berner", "rel": "authored_by"}
{"type": "edge", "src": "paper:2105.04026", "dst": "author:philipp_grohs", "rel": "authored_by"}
{"type": "edge", "src": "paper:2105.04026", "dst": "author:gitta_kutyniok", "rel": "authored_by"}
{"type": "edge", "src": "paper:2105.04026", "dst": "author:philipp_petersen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.04723", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2406.04723", "dst": "author:ignacio_roldan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.04723", "dst": "author:andras_palffy", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.04723", "dst": "author:julian_f_p_kooij", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.04723", "dst": "author:dariu_m_gavrila", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.04723", "dst": "author:francesco_fioranelli", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.10473", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2302.10473", "dst": "author:kun_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.10473", "dst": "author:zi_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.10473", "dst": "author:zhang_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.10473", "dst": "author:ang_su", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.10473", "dst": "author:xichao_teng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2301.00942", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2301.00942", "dst": "author:deep_ray", "rel": "authored_by"}
{"type": "edge", "src": "paper:2301.00942", "dst": "author:orazio_pinti", "rel": "authored_by"}
{"type": "edge", "src": "paper:2301.00942", "dst": "author:assad_a_oberai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2212.00966", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2212.00966", "dst": "author:rahul_kale", "rel": "authored_by"}
{"type": "edge", "src": "paper:2212.00966", "dst": "author:zhi_lu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2212.00966", "dst": "author:kar_wai_fok", "rel": "authored_by"}
{"type": "edge", "src": "paper:2212.00966", "dst": "author:vrizlynn_l_l_thing", "rel": "authored_by"}
{"type": "edge", "src": "paper:1706.05726", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1706.05726", "dst": "author:cemal_aker", "rel": "authored_by"}
{"type": "edge", "src": "paper:1706.05726", "dst": "author:sinan_kalkan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.13018", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.13018", "dst": "author:tomoya_tanaka", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.13018", "dst": "author:tomonori_ikeda", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.13018", "dst": "author:ryo_yonemoto", "rel": "authored_by"}
{"type": "edge", "src": "paper:2210.11745", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2210.11745", "dst": "author:junaid_akram", "rel": "authored_by"}
{"type": "edge", "src": "paper:2210.11745", "dst": "author:awais_akram", "rel": "authored_by"}
{"type": "edge", "src": "paper:2210.11745", "dst": "author:rutvij_h_jhaveri", "rel": "authored_by"}
{"type": "edge", "src": "paper:2210.11745", "dst": "author:mamoun_alazab", "rel": "authored_by"}
{"type": "edge", "src": "paper:2210.11745", "dst": "author:haoran_chi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2112.15454", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2112.15454", "dst": "author:song_kyoo_kim", "rel": "authored_by"}
{"type": "edge", "src": "paper:1711.00146", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1711.00146", "dst": "author:miquel_mart", "rel": "authored_by"}
{"type": "edge", "src": "paper:1711.00146", "dst": "author:atsuto_maki", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.20003", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2511.20003", "dst": "author:simin_zhu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.20003", "dst": "author:satish_ravindran", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.20003", "dst": "author:alexander_yarovoy", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.20003", "dst": "author:francesco_fioranelli", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.29261", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2603.29261", "dst": "author:lakshya_garg", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.29261", "dst": "author:sai_yaswanth", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.29261", "dst": "author:deep_narayan_mishra", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.29261", "dst": "author:karthik_kumaran", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.29261", "dst": "author:anupriya_sharma", "rel": "authored_by"}
{"type": "edge", "src": "paper:1903.03040", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1903.03040", "dst": "author:kjetil_o_lye", "rel": "authored_by"}
{"type": "edge", "src": "paper:1903.03040", "dst": "author:siddhartha_mishra", "rel": "authored_by"}
{"type": "edge", "src": "paper:1903.03040", "dst": "author:deep_ray", "rel": "authored_by"}
{"type": "edge", "src": "paper:2012.06469", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2012.06469", "dst": "author:indra_deep_mastan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2012.06469", "dst": "author:shanmuganathan_raman", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.00853", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2503.00853", "dst": "author:rui_yi_yong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.00853", "dst": "author:samuel_picosson", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.00853", "dst": "author:arnold_wiliem", "rel": "authored_by"}
{"type": "edge", "src": "paper:2004.03722", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2004.03722", "dst": "author:lucas_may_petry", "rel": "authored_by"}
{"type": "edge", "src": "paper:2004.03722", "dst": "author:amilcar_soares", "rel": "authored_by"}
{"type": "edge", "src": "paper:2004.03722", "dst": "author:vania_bogorny", "rel": "authored_by"}
{"type": "edge", "src": "paper:2004.03722", "dst": "author:bruno_brandoli", "rel": "authored_by"}
{"type": "edge", "src": "paper:2004.03722", "dst": "author:stan_matwin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.08294", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2406.08294", "dst": "author:yasod_ginige", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.08294", "dst": "author:ransika_gunasekara", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.08294", "dst": "author:darsha_hewavitharana", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.08294", "dst": "author:manjula_ariyarathne", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.08294", "dst": "author:ranga_rodrigo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.14764", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2311.14764", "dst": "author:martin_tran", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.14764", "dst": "author:jordan_shipard", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.14764", "dst": "author:hermawan_mulyono", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.14764", "dst": "author:arnold_wiliem", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.14764", "dst": "author:clinton_fookes", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.01274", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2507.01274", "dst": "author:vishakha_lall", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.01274", "dst": "author:yisi_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.00124", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2602.00124", "dst": "author:divya_acharya", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.00124", "dst": "author:pierre_bernab_e", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.00124", "dst": "author:antoine_chevrot", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.00124", "dst": "author:helge_spieker", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.00124", "dst": "author:arnaud_gotlieb", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.05778", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2403.05778", "dst": "author:mohamed_abuella", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.05778", "dst": "author:m_amine_atoui", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.05778", "dst": "author:slawomir_nowaczyk", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.05778", "dst": "author:simon_johansson", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.05778", "dst": "author:ethan_faghan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.07153", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2507.07153", "dst": "author:antonella_barisic_kulas", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.07153", "dst": "author:frano_petric", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.07153", "dst": "author:stjepan_bogdan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.11449", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2510.11449", "dst": "author:geoffery_agorku", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.11449", "dst": "author:sarah_hernandez", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.11449", "dst": "author:hayley_hames", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.11449", "dst": "author:cade_wagner", "rel": "authored_by"}
{"type": "edge", "src": "paper:2102.05869", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2102.05869", "dst": "author:bogdan_iancu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2102.05869", "dst": "author:valentin_soloviev", "rel": "authored_by"}
{"type": "edge", "src": "paper:2102.05869", "dst": "author:luca_zelioli", "rel": "authored_by"}
{"type": "edge", "src": "paper:2102.05869", "dst": "author:johan_lilius", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.13894", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2306.13894", "dst": "author:kenta_okamoto", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.13894", "dst": "author:akihisa_nagata", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.13894", "dst": "author:kyoma_arai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.13894", "dst": "author:yusei_nagao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.13894", "dst": "author:tatsuki_nishimura", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.12767", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2306.12767", "dst": "author:marijana_peti", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.12767", "dst": "author:ana_milas", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.12767", "dst": "author:natko_kra_evac", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.12767", "dst": "author:marko_kri_man_i", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.12767", "dst": "author:ivan_lon_ar", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.14203", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2511.14203", "dst": "author:yunhe_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.14762", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2311.14762", "dst": "author:benjamin_kiefer", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.14762", "dst": "author:lojze_ust", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.14762", "dst": "author:matej_kristan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.14762", "dst": "author:janez_per", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.14762", "dst": "author:matija_ter_ek", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.05270", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2312.05270", "dst": "author:emre_g_lsoylu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.05270", "dst": "author:paul_koch", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.05270", "dst": "author:mert_y_ld_z", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.05270", "dst": "author:manfred_constapel", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.05270", "dst": "author:andr_peter_kelm", "rel": "authored_by"}
{"type": "edge", "src": "paper:1609.04846", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1609.04846", "dst": "author:sebasti_n_basterrech", "rel": "authored_by"}
{"type": "edge", "src": "paper:1609.04846", "dst": "author:gerardo_rubino", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.01654", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2502.01654", "dst": "author:iat_hang_fong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.01654", "dst": "author:tengyue_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.01654", "dst": "author:simon_fong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.01654", "dst": "author:raymond_k_wong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.01654", "dst": "author:antonio_j_tall_n_ballesteros", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.06789", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1807.06789", "dst": "author:christos_kyrkou", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.06789", "dst": "author:george_plastiras", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.06789", "dst": "author:stylianos_venieris", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.06789", "dst": "author:theocharis_theocharides", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.06789", "dst": "author:christos_savvas_bouganis", "rel": "authored_by"}
{"type": "edge", "src": "paper:1803.02421", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1803.02421", "dst": "author:fady_medhat", "rel": "authored_by"}
{"type": "edge", "src": "paper:1803.02421", "dst": "author:david_chesmore", "rel": "authored_by"}
{"type": "edge", "src": "paper:1803.02421", "dst": "author:john_robinson", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.03561", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2311.03561", "dst": "author:cheng_yen_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.03561", "dst": "author:hsiang_wei_huang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.03561", "dst": "author:zhongyu_jiang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.03561", "dst": "author:heng_cheng_kuo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.03561", "dst": "author:jie_mei", "rel": "authored_by"}
{"type": "edge", "src": "paper:2002.04849", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2002.04849", "dst": "author:federico_mason", "rel": "authored_by"}
{"type": "edge", "src": "paper:2002.04849", "dst": "author:federico_chiariotti", "rel": "authored_by"}
{"type": "edge", "src": "paper:2002.04849", "dst": "author:martina_capuzzo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2002.04849", "dst": "author:davide_magrin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2002.04849", "dst": "author:andrea_zanella", "rel": "authored_by"}
{"type": "edge", "src": "paper:2008.02834", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2008.02834", "dst": "author:st_phane_vujasinovi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2008.02834", "dst": "author:stefan_becker", "rel": "authored_by"}
{"type": "edge", "src": "paper:2008.02834", "dst": "author:timo_breuer", "rel": "authored_by"}
{"type": "edge", "src": "paper:2008.02834", "dst": "author:sebastian_bullinger", "rel": "authored_by"}
{"type": "edge", "src": "paper:2008.02834", "dst": "author:norbert_scherer_negenborn", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.14753", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2306.14753", "dst": "author:sergey_oladyshkin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.14753", "dst": "author:timothy_praditia", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.14753", "dst": "author:ilja_kr_ker", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.14753", "dst": "author:farid_mohammadi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.14753", "dst": "author:wolfgang_nowak", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.14608", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.14608", "dst": "author:cole_dickerson", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.14608", "dst": "author:sean_kearney", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.14608", "dst": "author:sultan_manjur", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.14608", "dst": "author:ismail_guvenc", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.14608", "dst": "author:sevgi_gurbuz", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.27493", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2603.27493", "dst": "author:pengzhi_zhong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.27493", "dst": "author:jiwei_mo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.27493", "dst": "author:dan_zeng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.27493", "dst": "author:feixiang_he", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.27493", "dst": "author:shuiwang_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2107.00962", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2107.00962", "dst": "author:antonella_barisic", "rel": "authored_by"}
{"type": "edge", "src": "paper:2107.00962", "dst": "author:frano_petric", "rel": "authored_by"}
{"type": "edge", "src": "paper:2107.00962", "dst": "author:stjepan_bogdan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2110.02772", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2110.02772", "dst": "author:girik_malik", "rel": "authored_by"}
{"type": "edge", "src": "paper:2110.02772", "dst": "author:drew_linsley", "rel": "authored_by"}
{"type": "edge", "src": "paper:2110.02772", "dst": "author:thomas_serre", "rel": "authored_by"}
{"type": "edge", "src": "paper:2110.02772", "dst": "author:ennio_mingolla", "rel": "authored_by"}
{"type": "edge", "src": "paper:1408.3438", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1408.3438", "dst": "author:victoria_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:1408.3438", "dst": "author:john_v_tucker", "rel": "authored_by"}
{"type": "edge", "src": "paper:1912.03600", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1912.03600", "dst": "author:peng_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:1912.03600", "dst": "author:xing_xi", "rel": "authored_by"}
{"type": "edge", "src": "paper:1912.03600", "dst": "author:tony_q_s_quek", "rel": "authored_by"}
{"type": "edge", "src": "paper:1912.03600", "dst": "author:jingxuan_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:1912.03600", "dst": "author:xianbin_cao", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.02477", "dst": "axis:defense", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1807.02477", "dst": "author:igor_grabec", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.02477", "dst": "author:eva_vegl", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.02477", "dst": "author:mihael_sok", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.04338", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2306.04338", "dst": "author:cedric_de_boom", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.04338", "dst": "author:michael_reusens", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.16189", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2006.16189", "dst": "author:ian_walsh", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.16189", "dst": "author:dmytro_fishman", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.16189", "dst": "author:dario_garcia_gasulla", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.16189", "dst": "author:tiina_titma", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.16189", "dst": "author:gianluca_pollastri", "rel": "authored_by"}
{"type": "edge", "src": "paper:2201.12150", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2201.12150", "dst": "author:felix_mohr", "rel": "authored_by"}
{"type": "edge", "src": "paper:2201.12150", "dst": "author:jan_n_van_rijn", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.08893", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2302.08893", "dst": "author:davide_cacciarelli", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.08893", "dst": "author:murat_kulahci", "rel": "authored_by"}
{"type": "edge", "src": "paper:2303.15563", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2303.15563", "dst": "author:alejandro_guerra_manzanares", "rel": "authored_by"}
{"type": "edge", "src": "paper:2303.15563", "dst": "author:l_julian_lechuga_lopez", "rel": "authored_by"}
{"type": "edge", "src": "paper:2303.15563", "dst": "author:michail_maniatakos", "rel": "authored_by"}
{"type": "edge", "src": "paper:2303.15563", "dst": "author:farah_e_shamout", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.02381", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2304.02381", "dst": "author:maximilian_p_niroomand", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.02381", "dst": "author:david_j_wales", "rel": "authored_by"}
{"type": "edge", "src": "paper:1905.04749", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1905.04749", "dst": "author:junaed_younus_khan", "rel": "authored_by"}
{"type": "edge", "src": "paper:1905.04749", "dst": "author:md_tawkat_islam_khondaker", "rel": "authored_by"}
{"type": "edge", "src": "paper:1905.04749", "dst": "author:sadia_afroz", "rel": "authored_by"}
{"type": "edge", "src": "paper:1905.04749", "dst": "author:gias_uddin", "rel": "authored_by"}
{"type": "edge", "src": "paper:1905.04749", "dst": "author:anindya_iqbal", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.11092", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2602.11092", "dst": "author:cassandre_notton", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.11092", "dst": "author:benjamin_stott", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.11092", "dst": "author:philippe_schoeb", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.11092", "dst": "author:anthony_walsh", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.11092", "dst": "author:gr_goire_leboucher", "rel": "authored_by"}
{"type": "edge", "src": "paper:1705.05172", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1705.05172", "dst": "author:thomas_m_moerland", "rel": "authored_by"}
{"type": "edge", "src": "paper:1705.05172", "dst": "author:joost_broekens", "rel": "authored_by"}
{"type": "edge", "src": "paper:1705.05172", "dst": "author:catholijn_m_jonker", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.08759", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2509.08759", "dst": "author:mominul_rubel", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.08759", "dst": "author:adam_meyers", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.08759", "dst": "author:gabriel_nicolosi", "rel": "authored_by"}
{"type": "edge", "src": "paper:1906.01101", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1906.01101", "dst": "author:diego_granziol", "rel": "authored_by"}
{"type": "edge", "src": "paper:1906.01101", "dst": "author:binxin_ru", "rel": "authored_by"}
{"type": "edge", "src": "paper:1906.01101", "dst": "author:stefan_zohren", "rel": "authored_by"}
{"type": "edge", "src": "paper:1906.01101", "dst": "author:xiaowen_doing", "rel": "authored_by"}
{"type": "edge", "src": "paper:1906.01101", "dst": "author:michael_osborne", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.12511", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2404.12511", "dst": "author:olga_cherednichenko", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.12511", "dst": "author:dmytro_chernyshov", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.12511", "dst": "author:dmytro_sytnikov", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.12511", "dst": "author:polina_sytnikova", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.01393", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2402.01393", "dst": "author:carmen_martin_turrero", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.01393", "dst": "author:maxence_bouvier", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.01393", "dst": "author:manuel_breitenstein", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.01393", "dst": "author:pietro_zanuttigh", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.01393", "dst": "author:vincent_parret", "rel": "authored_by"}
{"type": "edge", "src": "paper:2204.12833", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2204.12833", "dst": "author:shin_ya_yamaguchi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2204.12833", "dst": "author:sekitoshi_kanai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2204.12833", "dst": "author:atsutoshi_kumagai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2204.12833", "dst": "author:daiki_chijiwa", "rel": "authored_by"}
{"type": "edge", "src": "paper:2204.12833", "dst": "author:hisashi_kashima", "rel": "authored_by"}
{"type": "edge", "src": "paper:1905.10345", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1905.10345", "dst": "author:iddo_drori", "rel": "authored_by"}
{"type": "edge", "src": "paper:1905.10345", "dst": "author:yamuna_krishnamurthy", "rel": "authored_by"}
{"type": "edge", "src": "paper:1905.10345", "dst": "author:raoni_lourenco", "rel": "authored_by"}
{"type": "edge", "src": "paper:1905.10345", "dst": "author:remi_rampin", "rel": "authored_by"}
{"type": "edge", "src": "paper:1905.10345", "dst": "author:kyunghyun_cho", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.11113", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2105.04026", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1910.09700", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1910.09700", "dst": "author:alexandre_lacoste", "rel": "authored_by"}
{"type": "edge", "src": "paper:1910.09700", "dst": "author:alexandra_luccioni", "rel": "authored_by"}
{"type": "edge", "src": "paper:1910.09700", "dst": "author:victor_schmidt", "rel": "authored_by"}
{"type": "edge", "src": "paper:1910.09700", "dst": "author:thomas_dandres", "rel": "authored_by"}
{"type": "edge", "src": "paper:2301.00942", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2103.00286", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2103.00286", "dst": "author:a_ziaee", "rel": "authored_by"}
{"type": "edge", "src": "paper:2103.00286", "dst": "author:r_dehbozorgi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2103.00286", "dst": "author:m_d_ller", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.12562", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2403.12562", "dst": "author:raghavendra_selvan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.12562", "dst": "author:bob_pepin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.12562", "dst": "author:christian_igel", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.12562", "dst": "author:gabrielle_samuel", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.12562", "dst": "author:erik_b_dam", "rel": "authored_by"}
{"type": "edge", "src": "paper:2007.03051", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2007.03051", "dst": "author:lasse_f_wolff_anthony", "rel": "authored_by"}
{"type": "edge", "src": "paper:2007.03051", "dst": "author:benjamin_kanding", "rel": "authored_by"}
{"type": "edge", "src": "paper:2007.03051", "dst": "author:raghavendra_selvan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.29261", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1711.00146", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1903.03040", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2109.13918", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2109.13918", "dst": "author:arpita_adhikari", "rel": "authored_by"}
{"type": "edge", "src": "paper:2109.13918", "dst": "author:joydip_sengupta", "rel": "authored_by"}
{"type": "edge", "src": "paper:2012.06469", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.23753", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.23753", "dst": "author:deep_shankar_pandey", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.23753", "dst": "author:hyomin_choi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.23753", "dst": "author:qi_yu", "rel": "authored_by"}
{"type": "edge", "src": "paper:1903.04717", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1903.04717", "dst": "author:scott_e_coull", "rel": "authored_by"}
{"type": "edge", "src": "paper:1903.04717", "dst": "author:christopher_gardner", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.04143", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2302.04143", "dst": "author:haoyue_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.04143", "dst": "author:jennifer_s_polson", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.04143", "dst": "author:eric_j_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.04143", "dst": "author:kambiz_nael", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.04143", "dst": "author:william_speier", "rel": "authored_by"}
{"type": "edge", "src": "paper:2109.05472", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2109.05472", "dst": "author:radosvet_desislavov", "rel": "authored_by"}
{"type": "edge", "src": "paper:2109.05472", "dst": "author:fernando_mart_nez_plumed", "rel": "authored_by"}
{"type": "edge", "src": "paper:2109.05472", "dst": "author:jos_hern_ndez_orallo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2107.02926", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2107.02926", "dst": "author:dhruv_v_patel", "rel": "authored_by"}
{"type": "edge", "src": "paper:2107.02926", "dst": "author:deep_ray", "rel": "authored_by"}
{"type": "edge", "src": "paper:2107.02926", "dst": "author:assad_a_oberai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.03712", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2011.03712", "dst": "author:indra_deep_mastan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.03712", "dst": "author:shanmuganathan_raman", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.03084", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2412.03084", "dst": "author:ajinkya_deshpande", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.03084", "dst": "author:deep_gupta", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.03084", "dst": "author:ankit_bhurane", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.03084", "dst": "author:nisha_meshram", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.03084", "dst": "author:sneha_singh", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.28944", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2603.28944", "dst": "author:aoi_naito", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.28944", "dst": "author:hirokazu_shirado", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.02842", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2501.02842", "dst": "author:qingyao_ai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.02842", "dst": "author:jingtao_zhan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.02842", "dst": "author:yiqun_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.16513", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2601.16513", "dst": "author:melissa_wilfley", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.16513", "dst": "author:mengting_ai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.16513", "dst": "author:madelyn_rose_sanfilippo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.19996", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2509.19996", "dst": "author:emilio_cruciani", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.19996", "dst": "author:roberto_verdecchia", "rel": "authored_by"}
{"type": "edge", "src": "paper:2205.01128", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2205.01128", "dst": "author:paul_smolensky", "rel": "authored_by"}
{"type": "edge", "src": "paper:2205.01128", "dst": "author:r_thomas_mccoy", "rel": "authored_by"}
{"type": "edge", "src": "paper:2205.01128", "dst": "author:roland_fernandez", "rel": "authored_by"}
{"type": "edge", "src": "paper:2205.01128", "dst": "author:matthew_goldrick", "rel": "authored_by"}
{"type": "edge", "src": "paper:2205.01128", "dst": "author:jianfeng_gao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.14776", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2501.14776", "dst": "author:niccol_marini", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.14776", "dst": "author:leonardo_pampaloni", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.14776", "dst": "author:filippo_di_martino", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.14776", "dst": "author:roberto_verdecchia", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.14776", "dst": "author:enrico_vicario", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.20902", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.20902", "dst": "author:siqi_mu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.20902", "dst": "author:shuo_wen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.20902", "dst": "author:yang_lu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.20902", "dst": "author:ruihong_jiang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.20902", "dst": "author:bo_ai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2308.12400", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2308.12400", "dst": "author:gerardo_adesso", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.10237", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2407.10237", "dst": "author:christian_clemm", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.10237", "dst": "author:lutz_stobbe", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.10237", "dst": "author:kishan_wimalawarne", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.10237", "dst": "author:jan_druschke", "rel": "authored_by"}
{"type": "edge", "src": "paper:2112.01298", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2112.01298", "dst": "author:luciano_cavalcante_siebert", "rel": "authored_by"}
{"type": "edge", "src": "paper:2112.01298", "dst": "author:maria_luce_lupetti", "rel": "authored_by"}
{"type": "edge", "src": "paper:2112.01298", "dst": "author:evgeni_aizenberg", "rel": "authored_by"}
{"type": "edge", "src": "paper:2112.01298", "dst": "author:niek_beckers", "rel": "authored_by"}
{"type": "edge", "src": "paper:2112.01298", "dst": "author:arkady_zgonnikov", "rel": "authored_by"}
{"type": "edge", "src": "paper:2607.04282", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2607.04282", "dst": "author:michael_iannelli", "rel": "authored_by"}
{"type": "edge", "src": "paper:2607.04282", "dst": "author:alan_ai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.00025", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2408.00025", "dst": "author:supriya_manna", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.00025", "dst": "author:niladri_sett", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.15284", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2401.15284", "dst": "author:zhicheng_lin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.16770", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2504.16770", "dst": "author:chaeyeon_lim", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.08817", "dst": "axis:energy", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2504.08817", "dst": "author:takahiro_misawa", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.08817", "dst": "author:ai_koizumi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.08817", "dst": "author:ryo_tamura", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.08817", "dst": "author:kazuyoshi_yoshimi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.15897", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2606.15897", "dst": "author:kacper_wyrwal", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.15897", "dst": "author:i_smail_i_lkan_ceylan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.15897", "dst": "author:alexander_tong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.03672", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2307.03672", "dst": "author:alexander_tong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.03672", "dst": "author:nikolay_malkin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.03672", "dst": "author:kilian_fatras", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.03672", "dst": "author:lazar_atanackovic", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.03672", "dst": "author:yanlei_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2305.17161", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2305.17161", "dst": "author:maximilian_dax", "rel": "authored_by"}
{"type": "edge", "src": "paper:2305.17161", "dst": "author:jonas_wildberger", "rel": "authored_by"}
{"type": "edge", "src": "paper:2305.17161", "dst": "author:simon_buchholz", "rel": "authored_by"}
{"type": "edge", "src": "paper:2305.17161", "dst": "author:stephen_r_green", "rel": "authored_by"}
{"type": "edge", "src": "paper:2305.17161", "dst": "author:jakob_h_macke", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.17872", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2504.17872", "dst": "author:max_muchen_sun", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.17872", "dst": "author:allison_pinosky", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.17872", "dst": "author:todd_murphey", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.16239", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.16239", "dst": "author:shuchan_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.17119", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2502.17119", "dst": "author:zhong_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.17119", "dst": "author:qi_huang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.17119", "dst": "author:lincen_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.17119", "dst": "author:jiayang_shi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.17119", "dst": "author:zhao_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:1903.01434", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1903.01434", "dst": "author:manoj_kumar", "rel": "authored_by"}
{"type": "edge", "src": "paper:1903.01434", "dst": "author:mohammad_babaeizadeh", "rel": "authored_by"}
{"type": "edge", "src": "paper:1903.01434", "dst": "author:dumitru_erhan", "rel": "authored_by"}
{"type": "edge", "src": "paper:1903.01434", "dst": "author:chelsea_finn", "rel": "authored_by"}
{"type": "edge", "src": "paper:1903.01434", "dst": "author:sergey_levine", "rel": "authored_by"}
{"type": "edge", "src": "paper:2110.02266", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2110.02266", "dst": "author:dea_daniella_wangsawijaya", "rel": "authored_by"}
{"type": "edge", "src": "paper:2110.02266", "dst": "author:claudia_nicolai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2110.02266", "dst": "author:bharathram_ganapathisubramani", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.06112", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.06112", "dst": "author:yifang_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.06112", "dst": "author:jiahao_cui", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.06112", "dst": "author:feipeng_cai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.06112", "dst": "author:zhihao_zhu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.06112", "dst": "author:hanlin_shang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.00482", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2302.00482", "dst": "author:alexander_tong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.00482", "dst": "author:kilian_fatras", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.00482", "dst": "author:nikolay_malkin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.00482", "dst": "author:guillaume_huguet", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.00482", "dst": "author:yanlei_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.08063", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.08063", "dst": "author:zhen_fang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.08063", "dst": "author:wenxuan_huang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.08063", "dst": "author:yu_zeng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.08063", "dst": "author:yiming_zhao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.08063", "dst": "author:shuang_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:1403.4969", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1403.4969", "dst": "author:martin_treiber", "rel": "authored_by"}
{"type": "edge", "src": "paper:1902.07351", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1902.07351", "dst": "author:baofang_song", "rel": "authored_by"}
{"type": "edge", "src": "paper:1902.07351", "dst": "author:carlos_plana", "rel": "authored_by"}
{"type": "edge", "src": "paper:1902.07351", "dst": "author:jose_m_lopez", "rel": "authored_by"}
{"type": "edge", "src": "paper:1902.07351", "dst": "author:marc_avila", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.06952", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2506.06952", "dst": "author:ying_shen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.06952", "dst": "author:zhiyang_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.06952", "dst": "author:jiuhai_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.06952", "dst": "author:shizhe_diao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.06952", "dst": "author:jiaxin_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.03540", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1908.03540", "dst": "author:pedro_m_milani", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.03540", "dst": "author:ian_e_gunady", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.03540", "dst": "author:david_s_ching", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.03540", "dst": "author:andrew_j_banko", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.03540", "dst": "author:christopher_j_elkins", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.05282", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2506.05282", "dst": "author:tao_sun", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.05282", "dst": "author:liyuan_zhu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.05282", "dst": "author:shengyu_huang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.05282", "dst": "author:shuran_song", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.05282", "dst": "author:iro_armeni", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.19835", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2511.19835", "dst": "author:xuewen_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.19835", "dst": "author:zhikai_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.19835", "dst": "author:jing_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.19835", "dst": "author:mengjuan_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.19835", "dst": "author:qingyi_gu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2207.02679", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2207.02679", "dst": "author:junnosuke_okajima", "rel": "authored_by"}
{"type": "edge", "src": "paper:2207.02679", "dst": "author:masaki_ito", "rel": "authored_by"}
{"type": "edge", "src": "paper:2207.02679", "dst": "author:yuka_iga", "rel": "authored_by"}
{"type": "edge", "src": "paper:1205.3624", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1205.3624", "dst": "author:manuel_garcia_villalba", "rel": "authored_by"}
{"type": "edge", "src": "paper:1205.3624", "dst": "author:aman_g_kidanemariam", "rel": "authored_by"}
{"type": "edge", "src": "paper:1205.3624", "dst": "author:markus_uhlmann", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.24757", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.24757", "dst": "author:sota_kumazawa", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.24757", "dst": "author:yasuhiro_yoshida", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.24757", "dst": "author:tomohiro_nimura", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.24757", "dst": "author:akira_murata", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.24757", "dst": "author:kaoru_iwamoto", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.01541", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2009.01541", "dst": "author:giovanna_vittori", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.01541", "dst": "author:paolo_blondeaux", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.01541", "dst": "author:marco_mazzuoli", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.01541", "dst": "author:julian_simeonov", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.01541", "dst": "author:joseph_calantoni", "rel": "authored_by"}
{"type": "edge", "src": "paper:1408.6107", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1408.6107", "dst": "author:marek_buk_ek", "rel": "authored_by"}
{"type": "edge", "src": "paper:1408.6107", "dst": "author:pavel_hrab_k", "rel": "authored_by"}
{"type": "edge", "src": "paper:1408.6107", "dst": "author:milan_krb_lek", "rel": "authored_by"}
{"type": "edge", "src": "paper:2209.03003", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2209.03003", "dst": "author:xingchao_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2209.03003", "dst": "author:chengyue_gong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2209.03003", "dst": "author:qiang_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.16995", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2403.16995", "dst": "author:shujian_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.16995", "dst": "author:lemeng_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.16995", "dst": "author:chengyue_gong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.16995", "dst": "author:xingchao_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.20320", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2405.20320", "dst": "author:sangyun_lee", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.20320", "dst": "author:zinan_lin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.20320", "dst": "author:giulia_fanti", "rel": "authored_by"}
{"type": "edge", "src": "paper:1804.04562", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1804.04562", "dst": "author:juan_ignacio_polanco", "rel": "authored_by"}
{"type": "edge", "src": "paper:1804.04562", "dst": "author:ivana_vinkovic", "rel": "authored_by"}
{"type": "edge", "src": "paper:1804.04562", "dst": "author:nickolas_stelzenmuller", "rel": "authored_by"}
{"type": "edge", "src": "paper:1804.04562", "dst": "author:nicolas_mordant", "rel": "authored_by"}
{"type": "edge", "src": "paper:1804.04562", "dst": "author:micka_l_bourgoin", "rel": "authored_by"}
{"type": "edge", "src": "paper:1303.0217", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1303.0217", "dst": "author:j_bakosi", "rel": "authored_by"}
{"type": "edge", "src": "paper:1303.0217", "dst": "author:j_r_ristorcelli", "rel": "authored_by"}
{"type": "edge", "src": "paper:http://arxi", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:http://arxi", "dst": "author:vyacheslav_m_abramov", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.26282", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2509.26282", "dst": "author:anthony_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.26282", "dst": "author:alexander_wikner", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.26282", "dst": "author:amaury_lancelin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.26282", "dst": "author:pedram_hassanzadeh", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.26282", "dst": "author:amir_barati_farimani", "rel": "authored_by"}
{"type": "edge", "src": "paper:1602.00257", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1602.00257", "dst": "author:carsten_chong", "rel": "authored_by"}
{"type": "edge", "src": "paper:1110.3250", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1110.3250", "dst": "author:peter_bank", "rel": "authored_by"}
{"type": "edge", "src": "paper:1110.3250", "dst": "author:dmitry_kramkov", "rel": "authored_by"}
{"type": "edge", "src": "paper:1810.10520", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1810.10520", "dst": "author:john_mashford", "rel": "authored_by"}
{"type": "edge", "src": "paper:http://arxi", "dst": "author:jan_pospisil", "rel": "authored_by"}
{"type": "edge", "src": "paper:http://arxi", "dst": "author:roger_tribe", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.05852", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2504.05852", "dst": "author:nikolaj_t_m_cke", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.05852", "dst": "author:benjamin_sanderse", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.07333", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2508.07333", "dst": "author:yuhao_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.07333", "dst": "author:rui_hu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.07333", "dst": "author:yu_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.07333", "dst": "author:longbo_huang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.04939", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2006.04939", "dst": "author:m_ogren", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.20070", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2602.20070", "dst": "author:florentin_coeurdoux", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.20070", "dst": "author:etienne_lempereur", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.20070", "dst": "author:nathana_l_cuvelle_magar", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.20070", "dst": "author:st_phane_mallat", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.20070", "dst": "author:eric_vanden_eijnden", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.13770", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2508.13770", "dst": "author:martin_schi_dt", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.13770", "dst": "author:nikolaj_takata_m_cke", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.13770", "dst": "author:clara_marika_velte", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.09171", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2009.09171", "dst": "author:kohei_numata", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.09171", "dst": "author:kenichi_tanaka", "rel": "authored_by"}
{"type": "edge", "src": "paper:2007.02736", "dst": "axis:flowmatch", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2007.02736", "dst": "author:alessandro_artale", "rel": "authored_by"}
{"type": "edge", "src": "paper:2007.02736", "dst": "author:jean_christoph_jung", "rel": "authored_by"}
{"type": "edge", "src": "paper:2007.02736", "dst": "author:andrea_mazzullo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2007.02736", "dst": "author:ana_ozaki", "rel": "authored_by"}
{"type": "edge", "src": "paper:2007.02736", "dst": "author:frank_wolter", "rel": "authored_by"}
{"type": "edge", "src": "paper:2203.08195", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2203.08195", "dst": "author:yingwei_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2203.08195", "dst": "author:adams_wei_yu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2203.08195", "dst": "author:tianjian_meng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2203.08195", "dst": "author:ben_caine", "rel": "authored_by"}
{"type": "edge", "src": "paper:2203.08195", "dst": "author:jiquan_ngiam", "rel": "authored_by"}
{"type": "edge", "src": "paper:2411.05292", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2411.05292", "dst": "author:yun_zhao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2411.05292", "dst": "author:zhan_gong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2411.05292", "dst": "author:peiru_zheng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2411.05292", "dst": "author:hong_zhu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2411.05292", "dst": "author:shaohua_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2206.07705", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2206.07705", "dst": "author:wei_chih_hung", "rel": "authored_by"}
{"type": "edge", "src": "paper:2206.07705", "dst": "author:vincent_casser", "rel": "authored_by"}
{"type": "edge", "src": "paper:2206.07705", "dst": "author:henrik_kretzschmar", "rel": "authored_by"}
{"type": "edge", "src": "paper:2206.07705", "dst": "author:jyh_jing_hwang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2206.07705", "dst": "author:dragomir_anguelov", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.19048", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2406.19048", "dst": "author:yang_song", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.19048", "dst": "author:lin_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2211.13529", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2211.13529", "dst": "author:yecheol_kim", "rel": "authored_by"}
{"type": "edge", "src": "paper:2211.13529", "dst": "author:konyul_park", "rel": "authored_by"}
{"type": "edge", "src": "paper:2211.13529", "dst": "author:minwook_kim", "rel": "authored_by"}
{"type": "edge", "src": "paper:2211.13529", "dst": "author:dongsuk_kum", "rel": "authored_by"}
{"type": "edge", "src": "paper:2211.13529", "dst": "author:jun_won_choi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2004.12636", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2004.12636", "dst": "author:jin_hyeok_yoo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2004.12636", "dst": "author:yecheol_kim", "rel": "authored_by"}
{"type": "edge", "src": "paper:2004.12636", "dst": "author:jisong_kim", "rel": "authored_by"}
{"type": "edge", "src": "paper:2004.12636", "dst": "author:jun_won_choi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2212.04675", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2212.04675", "dst": "author:qi_jiang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2212.04675", "dst": "author:hao_sun", "rel": "authored_by"}
{"type": "edge", "src": "paper:2212.04675", "dst": "author:xi_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.14919", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2312.14919", "dst": "author:james_gunn", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.14919", "dst": "author:zygmunt_lenyk", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.14919", "dst": "author:anuj_sharma", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.14919", "dst": "author:andrea_donati", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.14919", "dst": "author:alexandru_buburuzan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.14600", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2408.14600", "dst": "author:yidi_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.14600", "dst": "author:jiahao_wen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.14600", "dst": "author:bin_ren", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.14600", "dst": "author:wenhao_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.14600", "dst": "author:zhenhuan_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.12276", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2009.12276", "dst": "author:juncong_fei", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.12276", "dst": "author:wenbo_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.12276", "dst": "author:philipp_heidenreich", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.12276", "dst": "author:sascha_wirges", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.12276", "dst": "author:christoph_stiller", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.01856", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2502.01856", "dst": "author:reza_sadeghian", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.01856", "dst": "author:niloofar_hooshyaripour", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.01856", "dst": "author:chris_joslin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.01856", "dst": "author:wonsook_lee", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.09738", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2006.09738", "dst": "author:michael_f_rst", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.09738", "dst": "author:oliver_wasenm_ller", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.09738", "dst": "author:didier_stricker", "rel": "authored_by"}
{"type": "edge", "src": "paper:2607.04587", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2607.04587", "dst": "author:heejun_park", "rel": "authored_by"}
{"type": "edge", "src": "paper:2607.04587", "dst": "author:jaeseok_jeong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2607.04587", "dst": "author:kuk_jin_yoon", "rel": "authored_by"}
{"type": "edge", "src": "paper:2205.14951", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2205.14951", "dst": "author:kaicheng_yu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2205.14951", "dst": "author:tang_tao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2205.14951", "dst": "author:hongwei_xie", "rel": "authored_by"}
{"type": "edge", "src": "paper:2205.14951", "dst": "author:zhiwei_lin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2205.14951", "dst": "author:zhongwei_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2110.00464", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2110.00464", "dst": "author:jonas_heylen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2110.00464", "dst": "author:mark_de_wolf", "rel": "authored_by"}
{"type": "edge", "src": "paper:2110.00464", "dst": "author:bruno_dawagne", "rel": "authored_by"}
{"type": "edge", "src": "paper:2110.00464", "dst": "author:marc_proesmans", "rel": "authored_by"}
{"type": "edge", "src": "paper:2110.00464", "dst": "author:luc_van_gool", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.12034", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2409.12034", "dst": "author:codru_andrei_diaconu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.12034", "dst": "author:konrad_heidler", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.12034", "dst": "author:jonathan_l_bamber", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.12034", "dst": "author:harry_zekollari", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.11113", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2105.04026", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2301.00942", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2603.29261", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1711.00146", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1903.03040", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2012.06469", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.23753", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1903.04717", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2302.04143", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2011.03712", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2403.12562", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1901.10610", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1901.10610", "dst": "author:myung_seok_shim", "rel": "authored_by"}
{"type": "edge", "src": "paper:1901.10610", "dst": "author:chenye_zhao", "rel": "authored_by"}
{"type": "edge", "src": "paper:1901.10610", "dst": "author:yang_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:1901.10610", "dst": "author:xuchong_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:1901.10610", "dst": "author:wenrui_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2107.02926", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2005.07431", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2005.07431", "dst": "author:felix_nobis", "rel": "authored_by"}
{"type": "edge", "src": "paper:2005.07431", "dst": "author:maximilian_geisslinger", "rel": "authored_by"}
{"type": "edge", "src": "paper:2005.07431", "dst": "author:markus_weber", "rel": "authored_by"}
{"type": "edge", "src": "paper:2005.07431", "dst": "author:johannes_betz", "rel": "authored_by"}
{"type": "edge", "src": "paper:2005.07431", "dst": "author:markus_lienkamp", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.10249", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2307.10249", "dst": "author:jisong_kim", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.10249", "dst": "author:minjae_seong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.10249", "dst": "author:geonho_bang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.10249", "dst": "author:dongsuk_kum", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.10249", "dst": "author:jun_won_choi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.19872", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2410.19872", "dst": "author:kun_shi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.19872", "dst": "author:shibo_he", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.19872", "dst": "author:zhenyu_shi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.19872", "dst": "author:anjun_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.19872", "dst": "author:zehui_xiong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.16440", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2403.16440", "dst": "author:zhiwei_lin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.16440", "dst": "author:zhe_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.16440", "dst": "author:zhongyu_xia", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.16440", "dst": "author:xinhao_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.16440", "dst": "author:yongtao_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2305.00397", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2305.00397", "dst": "author:su_pang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2305.00397", "dst": "author:daniel_morris", "rel": "authored_by"}
{"type": "edge", "src": "paper:2305.00397", "dst": "author:hayder_radha", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.04841", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2011.04841", "dst": "author:ramin_nabati", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.04841", "dst": "author:hairong_qi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2209.06535", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2209.06535", "dst": "author:youngseok_kim", "rel": "authored_by"}
{"type": "edge", "src": "paper:2209.06535", "dst": "author:sanmin_kim", "rel": "authored_by"}
{"type": "edge", "src": "paper:2209.06535", "dst": "author:jun_won_choi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2209.06535", "dst": "author:dongsuk_kum", "rel": "authored_by"}
{"type": "edge", "src": "paper:2102.05150", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2102.05150", "dst": "author:yizhou_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2102.05150", "dst": "author:zhongyu_jiang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2102.05150", "dst": "author:yudong_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2102.05150", "dst": "author:jenq_neng_hwang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2102.05150", "dst": "author:guanbin_xing", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.17977", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2501.17977", "dst": "author:lei_cheng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.17977", "dst": "author:siyang_cao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2411.10293", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2411.10293", "dst": "author:ryoma_yataka", "rel": "authored_by"}
{"type": "edge", "src": "paper:2411.10293", "dst": "author:adriano_cardace", "rel": "authored_by"}
{"type": "edge", "src": "paper:2411.10293", "dst": "author:pu_perry_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2411.10293", "dst": "author:petros_boufounos", "rel": "authored_by"}
{"type": "edge", "src": "paper:2411.10293", "dst": "author:ryuhei_takahashi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.10511", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2302.10511", "dst": "author:zizhang_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.10511", "dst": "author:guilian_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.10511", "dst": "author:yuanzhu_gan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.10511", "dst": "author:lei_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.10511", "dst": "author:jian_pu", "rel": "authored_by"}
{"type": "edge", "src": "paper:1907.06067", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1907.06067", "dst": "author:evgenii_razinkov", "rel": "authored_by"}
{"type": "edge", "src": "paper:1907.06067", "dst": "author:iuliia_saveleva", "rel": "authored_by"}
{"type": "edge", "src": "paper:1907.06067", "dst": "author:ji_i_matas", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.19215", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2510.19215", "dst": "author:xiaozhi_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.19215", "dst": "author:huijun_di", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.19215", "dst": "author:jian_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.19215", "dst": "author:feng_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.19215", "dst": "author:wei_liang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.20003", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2606.27556", "dst": "axis:fusion", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2606.27556", "dst": "author:ram_charan_akula", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.27556", "dst": "author:sivanathan_kandhasamy", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.27556", "dst": "author:manikandan_ganesan", "rel": "authored_by"}
{"type": "edge", "src": "paper:1606.00825", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1606.00825", "dst": "author:amirhossein_tavanaei", "rel": "authored_by"}
{"type": "edge", "src": "paper:1606.00825", "dst": "author:anthony_s_maida", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.14138", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2506.14138", "dst": "author:ashish_gautam", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.14138", "dst": "author:prasanna_date", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.14138", "dst": "author:shruti_kulkarni", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.14138", "dst": "author:robert_patton", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.14138", "dst": "author:thomas_potok", "rel": "authored_by"}
{"type": "edge", "src": "paper:1810.03199", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1810.03199", "dst": "author:bryce_bagley", "rel": "authored_by"}
{"type": "edge", "src": "paper:1810.03199", "dst": "author:blake_bordelon", "rel": "authored_by"}
{"type": "edge", "src": "paper:1810.03199", "dst": "author:benjamin_moseley", "rel": "authored_by"}
{"type": "edge", "src": "paper:1810.03199", "dst": "author:ralf_wessel", "rel": "authored_by"}
{"type": "edge", "src": "paper:1609.04846", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2503.17111", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2503.17111", "dst": "author:mikhail_kiselev", "rel": "authored_by"}
{"type": "edge", "src": "paper:2104.12579", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2104.12579", "dst": "author:lo_c_cordone", "rel": "authored_by"}
{"type": "edge", "src": "paper:2104.12579", "dst": "author:beno_t_miramond", "rel": "authored_by"}
{"type": "edge", "src": "paper:2104.12579", "dst": "author:sonia_ferrante", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.14841", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2505.14841", "dst": "author:yuchen_tian", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.14841", "dst": "author:assel_kembay", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.14841", "dst": "author:samuel_tensingh", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.14841", "dst": "author:nhan_duy_truong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.14841", "dst": "author:jason_k_eshraghian", "rel": "authored_by"}
{"type": "edge", "src": "paper:2001.10696", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2001.10696", "dst": "author:mingyuan_meng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2001.10696", "dst": "author:xingyu_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2001.10696", "dst": "author:shanlin_xiao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2001.10696", "dst": "author:zhiyi_yu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.17172", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2501.17172", "dst": "author:daniel_casanueva_morato", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.17172", "dst": "author:chenxi_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.17172", "dst": "author:giacomo_indiveri", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.17172", "dst": "author:juan_p_dominguez_morales", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.17172", "dst": "author:alejandro_linares_barranco", "rel": "authored_by"}
{"type": "edge", "src": "paper:2010.06746", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2010.06746", "dst": "author:rollin_omari", "rel": "authored_by"}
{"type": "edge", "src": "paper:2010.06746", "dst": "author:r_i_mckay", "rel": "authored_by"}
{"type": "edge", "src": "paper:2010.06746", "dst": "author:tom_gedeon", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.11555", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2307.11555", "dst": "author:laurent_u_perrinet", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.12060", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2603.12060", "dst": "author:sophie_jaffard", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.12060", "dst": "author:ivo_f_sbalzarini", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.20633", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2407.20633", "dst": "author:waseem_shariff", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.20633", "dst": "author:paul_kielty", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.20633", "dst": "author:joseph_lemley", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.20633", "dst": "author:peter_corcoran", "rel": "authored_by"}
{"type": "edge", "src": "paper:2205.04339", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2205.04339", "dst": "author:lo_c_cordone", "rel": "authored_by"}
{"type": "edge", "src": "paper:2205.04339", "dst": "author:beno_t_miramond", "rel": "authored_by"}
{"type": "edge", "src": "paper:2205.04339", "dst": "author:philippe_thierion", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.09985", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2006.09985", "dst": "author:riccardo_massa", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.09985", "dst": "author:alberto_marchisio", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.09985", "dst": "author:maurizio_martina", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.09985", "dst": "author:muhammad_shafique", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.04765", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2006.04765", "dst": "author:ioannis_polykretis", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.04765", "dst": "author:konstantinos_p_michmizos", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.03369", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2306.03369", "dst": "author:pei_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.03369", "dst": "author:shuo_zhu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.03369", "dst": "author:edmund_y_lam", "rel": "authored_by"}
{"type": "edge", "src": "paper:2109.12308", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2109.12308", "dst": "author:carlo_michaelis", "rel": "authored_by"}
{"type": "edge", "src": "paper:2109.12308", "dst": "author:andrew_b_lehr", "rel": "authored_by"}
{"type": "edge", "src": "paper:2109.12308", "dst": "author:winfried_oed", "rel": "authored_by"}
{"type": "edge", "src": "paper:2109.12308", "dst": "author:christian_tetzlaff", "rel": "authored_by"}
{"type": "edge", "src": "paper:2008.11642", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2008.11642", "dst": "author:carlo_michaelis", "rel": "authored_by"}
{"type": "edge", "src": "paper:2008.11642", "dst": "author:andrew_b_lehr", "rel": "authored_by"}
{"type": "edge", "src": "paper:2008.11642", "dst": "author:christian_tetzlaff", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.13747", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2602.13747", "dst": "author:evan_eames", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.13747", "dst": "author:priyadarshini_kannan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.13747", "dst": "author:ronan_sangouard", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.13747", "dst": "author:philipp_plank", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.13747", "dst": "author:elvin_hajizada", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.10053", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2504.10053", "dst": "author:kevin_max", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.10053", "dst": "author:larissa_sames", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.10053", "dst": "author:shimeng_ye", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.10053", "dst": "author:jan_steink_hler", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.10053", "dst": "author:federico_corradi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.03076", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2408.03076", "dst": "author:alessandro_pierro", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.03076", "dst": "author:philipp_stratmann", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.03076", "dst": "author:gabriel_andres_fonseca_guerra", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.03076", "dst": "author:sumedh_risbud", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.03076", "dst": "author:timothy_shea", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.13762", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2307.13762", "dst": "author:gavin_parpart", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.13762", "dst": "author:sumedh_r_risbud", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.13762", "dst": "author:garrett_t_kenyon", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.13762", "dst": "author:yijing_watkins", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.00534", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2011.00534", "dst": "author:julien_dupeyroux", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.00534", "dst": "author:jesse_hagenaars", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.00534", "dst": "author:federico_paredes_vall_s", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.00534", "dst": "author:guido_de_croon", "rel": "authored_by"}
{"type": "edge", "src": "paper:2109.10835", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2109.10835", "dst": "author:srijanie_dey", "rel": "authored_by"}
{"type": "edge", "src": "paper:2109.10835", "dst": "author:alexander_dimitrov", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.09466", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2508.09466", "dst": "author:tam_ngoc_bang_nguyen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.09466", "dst": "author:anh_dzung_doan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.09466", "dst": "author:zhipeng_cai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.09466", "dst": "author:tat_jun_chin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.16792", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2508.16792", "dst": "author:felix_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.16792", "dst": "author:bradley_h_theilman", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.16792", "dst": "author:fred_rothganger", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.16792", "dst": "author:william_severa", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.16792", "dst": "author:craig_m_vineyard", "rel": "authored_by"}
{"type": "edge", "src": "paper:1812.01739", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1812.01739", "dst": "author:peter_blouw", "rel": "authored_by"}
{"type": "edge", "src": "paper:1812.01739", "dst": "author:xuan_choo", "rel": "authored_by"}
{"type": "edge", "src": "paper:1812.01739", "dst": "author:eric_hunsberger", "rel": "authored_by"}
{"type": "edge", "src": "paper:1812.01739", "dst": "author:chris_eliasmith", "rel": "authored_by"}
{"type": "edge", "src": "paper:2107.00401", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2107.00401", "dst": "author:alberto_viale", "rel": "authored_by"}
{"type": "edge", "src": "paper:2107.00401", "dst": "author:alberto_marchisio", "rel": "authored_by"}
{"type": "edge", "src": "paper:2107.00401", "dst": "author:maurizio_martina", "rel": "authored_by"}
{"type": "edge", "src": "paper:2107.00401", "dst": "author:guido_masera", "rel": "authored_by"}
{"type": "edge", "src": "paper:2107.00401", "dst": "author:muhammad_shafique", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.03911", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.03911", "dst": "author:kenneth_stewart", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.03911", "dst": "author:roxana_leontie", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.03911", "dst": "author:samantha_chapin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.03911", "dst": "author:joe_hays", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.03911", "dst": "author:sumit_bam_shrestha", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.04640", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2304.04640", "dst": "author:jason_yik", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.04640", "dst": "author:korneel_van_den_berghe", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.04640", "dst": "author:douwe_den_blanken", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.04640", "dst": "author:younes_bouhadjar", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.04640", "dst": "author:maxime_fabre", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.20729", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2502.20729", "dst": "author:ben_walters", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.20729", "dst": "author:yeshwanth_bethi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.20729", "dst": "author:taylor_kergan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.20729", "dst": "author:binh_nguyen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.20729", "dst": "author:amirali_amirsoleimani", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.10742", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2601.10742", "dst": "author:am_lie_gruel", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.10742", "dst": "author:pierre_lewden", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.10742", "dst": "author:adrien_f_vincent", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.10742", "dst": "author:sylvain_sa_ghi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.12055", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2401.12055", "dst": "author:murat_isik", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.12055", "dst": "author:hiruna_vishwamith", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.12055", "dst": "author:yusuf_sur", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.12055", "dst": "author:kayode_inadagbo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.12055", "dst": "author:i_can_dikmen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.12013", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2011.12013", "dst": "author:herbert_jaeger", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.08802", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2304.08802", "dst": "author:stein_stroobants", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.08802", "dst": "author:julien_dupeyroux", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.08802", "dst": "author:guido_c_h_e_de_croon", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.01305", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2405.01305", "dst": "author:madison_cotteret", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.01305", "dst": "author:hugh_greatorex", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.01305", "dst": "author:alpha_renner", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.01305", "dst": "author:junren_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.01305", "dst": "author:emre_neftci", "rel": "authored_by"}
{"type": "edge", "src": "paper:2004.14942", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2004.14942", "dst": "author:adnan_mehonic", "rel": "authored_by"}
{"type": "edge", "src": "paper:2004.14942", "dst": "author:abu_sebastian", "rel": "authored_by"}
{"type": "edge", "src": "paper:2004.14942", "dst": "author:bipin_rajendran", "rel": "authored_by"}
{"type": "edge", "src": "paper:2004.14942", "dst": "author:osvaldo_simeone", "rel": "authored_by"}
{"type": "edge", "src": "paper:2004.14942", "dst": "author:eleni_vasilaki", "rel": "authored_by"}
{"type": "edge", "src": "paper:1211.0310", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1211.0310", "dst": "author:lsst_dark_energy_science_collaboration", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.04727", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2604.04727", "dst": "author:keshava_katti", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.04727", "dst": "author:pratik_chaudhari", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.04727", "dst": "author:deep_jariwala", "rel": "authored_by"}
{"type": "edge", "src": "paper:http://arxi", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:http://arxi", "dst": "author:the_dark_energy_survey_collaboration", "rel": "authored_by"}
{"type": "edge", "src": "paper:1810.12640", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1810.12640", "dst": "author:lyes_khacef", "rel": "authored_by"}
{"type": "edge", "src": "paper:1810.12640", "dst": "author:bernard_girau", "rel": "authored_by"}
{"type": "edge", "src": "paper:1810.12640", "dst": "author:nicolas_rougier", "rel": "authored_by"}
{"type": "edge", "src": "paper:1810.12640", "dst": "author:andres_upegui", "rel": "authored_by"}
{"type": "edge", "src": "paper:1810.12640", "dst": "author:benoit_miramond", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.22352", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2410.22352", "dst": "author:steven_abreu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.22352", "dst": "author:jens_e_pedersen", "rel": "authored_by"}
{"type": "edge", "src": "paper:1609.02545", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1609.02545", "dst": "author:wilten_nicola", "rel": "authored_by"}
{"type": "edge", "src": "paper:1609.02545", "dst": "author:claudia_clopath", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.00232", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2302.00232", "dst": "author:mingqing_xiao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.00232", "dst": "author:qingyan_meng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.00232", "dst": "author:zongpeng_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.00232", "dst": "author:yisen_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.00232", "dst": "author:zhouchen_lin", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.06378", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1908.06378", "dst": "author:wenrui_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.06378", "dst": "author:peng_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2104.00035", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2104.00035", "dst": "author:tamer_lmez", "rel": "authored_by"}
{"type": "edge", "src": "paper:2104.00035", "dst": "author:z_mray_dokur", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.01654", "dst": "axis:neuro", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2405.11907", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2405.11907", "dst": "author:ramansh_sharma", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.11907", "dst": "author:varun_shankar", "rel": "authored_by"}
{"type": "edge", "src": "paper:http://arxi", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:http://arxi", "dst": "author:arupkumar_pal", "rel": "authored_by"}
{"type": "edge", "src": "paper:2204.03193", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2204.03193", "dst": "author:jiahao_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2204.03193", "dst": "author:shiqi_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2204.03193", "dst": "author:guang_lin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.12344", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2509.12344", "dst": "author:arth_sojitra", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.12344", "dst": "author:mrigank_dhingra", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.12344", "dst": "author:omer_san", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.10368", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2507.10368", "dst": "author:yongjin_choi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.10368", "dst": "author:chenying_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.10368", "dst": "author:jorge_macedo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.09395", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2501.09395", "dst": "author:hwijae_son", "rel": "authored_by"}
{"type": "edge", "src": "paper:1510.08231", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1510.08231", "dst": "author:hachem_kadri", "rel": "authored_by"}
{"type": "edge", "src": "paper:1510.08231", "dst": "author:emmanuel_duflos", "rel": "authored_by"}
{"type": "edge", "src": "paper:1510.08231", "dst": "author:philippe_preux", "rel": "authored_by"}
{"type": "edge", "src": "paper:1510.08231", "dst": "author:st_phane_canu", "rel": "authored_by"}
{"type": "edge", "src": "paper:1510.08231", "dst": "author:alain_rakotomamonjy", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.00317", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2503.00317", "dst": "author:zhaoxi_jiang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.00317", "dst": "author:fei_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.12293", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2409.12293", "dst": "author:frank_cole", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.12293", "dst": "author:yulong_lu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.12293", "dst": "author:wuzhe_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2409.12293", "dst": "author:tianhao_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.08893", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2506.09781", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2506.09781", "dst": "author:chungpa_lee", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.09781", "dst": "author:sehee_lim", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.09781", "dst": "author:kibok_lee", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.09781", "dst": "author:jy_yong_sohn", "rel": "authored_by"}
{"type": "edge", "src": "paper:1910.03193", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1910.03193", "dst": "author:lu_lu", "rel": "authored_by"}
{"type": "edge", "src": "paper:1910.03193", "dst": "author:pengzhan_jin", "rel": "authored_by"}
{"type": "edge", "src": "paper:1910.03193", "dst": "author:george_em_karniadakis", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.10932", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2504.10932", "dst": "author:bo_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.10932", "dst": "author:lizuo_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.10932", "dst": "author:wei_cai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2212.04663", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2212.04663", "dst": "author:wuzhe_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2212.04663", "dst": "author:yulong_lu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2212.04663", "dst": "author:li_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:1905.07435", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1905.07435", "dst": "author:harkirat_singh_behl", "rel": "authored_by"}
{"type": "edge", "src": "paper:1905.07435", "dst": "author:at_l_m_g_ne_baydin", "rel": "authored_by"}
{"type": "edge", "src": "paper:1905.07435", "dst": "author:philip_h_s_torr", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.14753", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2006.02361", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2006.02361", "dst": "author:akshunna_s_dogra", "rel": "authored_by"}
{"type": "edge", "src": "paper:2006.02361", "dst": "author:william_t_redman", "rel": "authored_by"}
{"type": "edge", "src": "paper:1804.03587", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1804.03587", "dst": "author:xin_fang", "rel": "authored_by"}
{"type": "edge", "src": "paper:1804.03587", "dst": "author:ghislain_fourier", "rel": "authored_by"}
{"type": "edge", "src": "paper:1010.5964", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1010.5964", "dst": "author:maurice_robert_kibler", "rel": "authored_by"}
{"type": "edge", "src": "paper:1609.04846", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2509.25500", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2509.25500", "dst": "author:benjamin_jaye", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.25500", "dst": "author:rahul_sethi", "rel": "authored_by"}
{"type": "edge", "src": "paper:http://arxi", "dst": "author:manuel_calixto", "rel": "authored_by"}
{"type": "edge", "src": "paper:http://arxi", "dst": "author:julio_guerrero", "rel": "authored_by"}
{"type": "edge", "src": "paper:http://arxi", "dst": "author:juan_carlos_s_nchez_monreal", "rel": "authored_by"}
{"type": "edge", "src": "paper:0904.4716", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:0904.4716", "dst": "author:manuel_calixto", "rel": "authored_by"}
{"type": "edge", "src": "paper:0904.4716", "dst": "author:julio_guerrero", "rel": "authored_by"}
{"type": "edge", "src": "paper:0904.4716", "dst": "author:juan_carlos_s_nchez_monreal", "rel": "authored_by"}
{"type": "edge", "src": "paper:1605.09340", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1605.09340", "dst": "author:jan_rozendaal", "rel": "authored_by"}
{"type": "edge", "src": "paper:1605.09340", "dst": "author:mark_veraar", "rel": "authored_by"}
{"type": "edge", "src": "paper:2202.04211", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2202.04211", "dst": "author:arne_hendrickx", "rel": "authored_by"}
{"type": "edge", "src": "paper:2203.07923", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2203.07923", "dst": "author:david_beltran", "rel": "authored_by"}
{"type": "edge", "src": "paper:2203.07923", "dst": "author:olli_saari", "rel": "authored_by"}
{"type": "edge", "src": "paper:1406.0636", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1406.0636", "dst": "author:ubertino_battisti", "rel": "authored_by"}
{"type": "edge", "src": "paper:1406.0636", "dst": "author:sandro_coriasco", "rel": "authored_by"}
{"type": "edge", "src": "paper:1406.0636", "dst": "author:elmar_schrohe", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.05639", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2307.05639", "dst": "author:danny_d_agostino", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.05639", "dst": "author:ilija_ilievski", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.05639", "dst": "author:christine_annette_shoemaker", "rel": "authored_by"}
{"type": "edge", "src": "paper:1901.06610", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1901.06610", "dst": "author:jader_abreu", "rel": "authored_by"}
{"type": "edge", "src": "paper:1901.06610", "dst": "author:luis_fred", "rel": "authored_by"}
{"type": "edge", "src": "paper:1901.06610", "dst": "author:david_mac_do", "rel": "authored_by"}
{"type": "edge", "src": "paper:1901.06610", "dst": "author:cleber_zanchettin", "rel": "authored_by"}
{"type": "edge", "src": "paper:1506.01230", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1506.01230", "dst": "author:benjamin_gess", "rel": "authored_by"}
{"type": "edge", "src": "paper:1506.01230", "dst": "author:jonas_m_t_lle", "rel": "authored_by"}
{"type": "edge", "src": "paper:1012.4657", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1012.4657", "dst": "author:jussi_behrndt", "rel": "authored_by"}
{"type": "edge", "src": "paper:1012.4657", "dst": "author:jonathan_rohleder", "rel": "authored_by"}
{"type": "edge", "src": "paper:1005.4095", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1005.4095", "dst": "author:arnulf_jentzen", "rel": "authored_by"}
{"type": "edge", "src": "paper:1005.4095", "dst": "author:michael_roeckner", "rel": "authored_by"}
{"type": "edge", "src": "paper:1210.5831", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1210.5831", "dst": "author:st_phane_junca", "rel": "authored_by"}
{"type": "edge", "src": "paper:1210.5831", "dst": "author:bruno_lombard", "rel": "authored_by"}
{"type": "edge", "src": "paper:1912.05497", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1912.05497", "dst": "author:mourad_choulli", "rel": "authored_by"}
{"type": "edge", "src": "paper:2303.02304", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2303.02304", "dst": "author:xiongye_xiao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2303.02304", "dst": "author:defu_cao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2303.02304", "dst": "author:ruochen_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2303.02304", "dst": "author:gaurav_gupta", "rel": "authored_by"}
{"type": "edge", "src": "paper:2303.02304", "dst": "author:gengshuo_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:1204.6613", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1204.6613", "dst": "author:paul_m_n_feehan", "rel": "authored_by"}
{"type": "edge", "src": "paper:0801.3838", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:0801.3838", "dst": "author:hiroshi_isozaki", "rel": "authored_by"}
{"type": "edge", "src": "paper:0801.3838", "dst": "author:j_r_me_le_rousseau", "rel": "authored_by"}
{"type": "edge", "src": "paper:1210.6727", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1210.6727", "dst": "author:paul_m_n_feehan", "rel": "authored_by"}
{"type": "edge", "src": "paper:1210.6727", "dst": "author:camelia_pop", "rel": "authored_by"}
{"type": "edge", "src": "paper:1506.03252", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1506.03252", "dst": "author:david_j_pr_mel", "rel": "authored_by"}
{"type": "edge", "src": "paper:1506.03252", "dst": "author:mathias_trabs", "rel": "authored_by"}
{"type": "edge", "src": "paper:1805.06925", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1805.06925", "dst": "author:ahmed_fitouhi", "rel": "authored_by"}
{"type": "edge", "src": "paper:1805.06925", "dst": "author:in_ss_jebabli", "rel": "authored_by"}
{"type": "edge", "src": "paper:1805.06925", "dst": "author:elina_l_shishkina", "rel": "authored_by"}
{"type": "edge", "src": "paper:1805.06925", "dst": "author:sergei_m_sitnik", "rel": "authored_by"}
{"type": "edge", "src": "paper:1804.08515", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1804.08515", "dst": "author:charles_curry", "rel": "authored_by"}
{"type": "edge", "src": "paper:1804.08515", "dst": "author:kurusch_ebrahimi_fard", "rel": "authored_by"}
{"type": "edge", "src": "paper:1804.08515", "dst": "author:dominique_manchon", "rel": "authored_by"}
{"type": "edge", "src": "paper:1804.08515", "dst": "author:hans_z_munthe_kaas", "rel": "authored_by"}
{"type": "edge", "src": "paper:2005.00865", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2005.00865", "dst": "author:teven_le_scao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2012.10726", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2012.10726", "dst": "author:john_ioannis_stavroulakis", "rel": "authored_by"}
{"type": "edge", "src": "paper:2012.10726", "dst": "author:elena_braverman", "rel": "authored_by"}
{"type": "edge", "src": "paper:1709.07098", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1709.07098", "dst": "author:davar_khoshnevisan", "rel": "authored_by"}
{"type": "edge", "src": "paper:1709.07098", "dst": "author:andrey_sarantsev", "rel": "authored_by"}
{"type": "edge", "src": "paper:2309.17345", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2309.17345", "dst": "author:daniel_badawi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2309.17345", "dst": "author:eduardo_gildin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2107.00465", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2107.00465", "dst": "author:rahul_nellikkath", "rel": "authored_by"}
{"type": "edge", "src": "paper:2107.00465", "dst": "author:spyros_chatzivasileiadis", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.04544", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2009.04544", "dst": "author:levi_mcclenny", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.04544", "dst": "author:ulisses_braga_neto", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.01654", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2501.04013", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2501.04013", "dst": "author:avetik_arakelyan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2501.04013", "dst": "author:rafayel_barkhudaryan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.16969", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2408.16969", "dst": "author:hanwen_bi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2408.16969", "dst": "author:thushara_d_abhayapala", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.23003", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2604.23003", "dst": "author:leszek_siwik", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.23003", "dst": "author:maciej_sikora", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.23003", "dst": "author:natalia_leszczy_ska", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.23003", "dst": "author:tomasz_maciej_ciesielski", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.23003", "dst": "author:eirik_valseth", "rel": "authored_by"}
{"type": "edge", "src": "paper:1803.02421", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2302.08332", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2302.08332", "dst": "author:shawn_g_rosofsky", "rel": "authored_by"}
{"type": "edge", "src": "paper:2302.08332", "dst": "author:e_a_huerta", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.13425", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2509.13425", "dst": "author:julian_evan_chrisnanto", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.13425", "dst": "author:salsabila_rahma_alia", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.13425", "dst": "author:yulison_herry_chrisnanto", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.13425", "dst": "author:ferry_faizal", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.18131", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2509.18131", "dst": "author:jean_michel_tucny", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.18131", "dst": "author:abhisek_ganguly", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.18131", "dst": "author:santosh_ansumali", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.18131", "dst": "author:sauro_succi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.22189", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.22189", "dst": "author:jose_i_aizpurua", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.20731", "dst": "axis:pinn", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2604.20731", "dst": "author:askold_vilkha", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.20731", "dst": "author:tomasz_s_u_alec", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.20731", "dst": "author:marcin_o", "rel": "authored_by"}
{"type": "edge", "src": "paper:2604.20731", "dst": "author:maciej_paszy_ski", "rel": "authored_by"}
{"type": "edge", "src": "paper:1311.2485", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1311.2485", "dst": "author:ognyan_oreshkov", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.17156", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.17156", "dst": "author:samira_sayedsalehi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.17156", "dst": "author:nader_bagherzadeh", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.17156", "dst": "author:maxim_shcherbakov", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.17156", "dst": "author:jean_luc_gaudiot", "rel": "authored_by"}
{"type": "edge", "src": "paper:1610.04013", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1610.04013", "dst": "author:todd_brun", "rel": "authored_by"}
{"type": "edge", "src": "paper:1610.04013", "dst": "author:min_hsiu_hsieh", "rel": "authored_by"}
{"type": "edge", "src": "paper:1609.04846", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:http://arxi", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:http://arxi", "dst": "author:hsun_hsien_chang", "rel": "authored_by"}
{"type": "edge", "src": "paper:http://arxi", "dst": "author:a_m_steane", "rel": "authored_by"}
{"type": "edge", "src": "paper:0811.3734", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:0811.3734", "dst": "author:takao_aoki", "rel": "authored_by"}
{"type": "edge", "src": "paper:0811.3734", "dst": "author:go_takahashi", "rel": "authored_by"}
{"type": "edge", "src": "paper:0811.3734", "dst": "author:tadashi_kajiya", "rel": "authored_by"}
{"type": "edge", "src": "paper:0811.3734", "dst": "author:jun_ichi_yoshikawa", "rel": "authored_by"}
{"type": "edge", "src": "paper:0811.3734", "dst": "author:samuel_l_braunstein", "rel": "authored_by"}
{"type": "edge", "src": "paper:1910.03672", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1910.03672", "dst": "author:todd_a_brun", "rel": "authored_by"}
{"type": "edge", "src": "paper:2311.00487", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2311.00487", "dst": "author:d_v_babukhin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.19833", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2504.19833", "dst": "author:valentine_nyirahafashimana", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.19833", "dst": "author:nurisya_mohd_shah", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.19833", "dst": "author:umair_abdul_halim", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.19833", "dst": "author:mohamed_othman", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.19833", "dst": "author:sharifah_kartini_said_husain", "rel": "authored_by"}
{"type": "edge", "src": "paper:1307.5893", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1307.5893", "dst": "author:kevin_c_young", "rel": "authored_by"}
{"type": "edge", "src": "paper:1307.5893", "dst": "author:mohan_sarovar", "rel": "authored_by"}
{"type": "edge", "src": "paper:1307.5893", "dst": "author:robin_blume_kohout", "rel": "authored_by"}
{"type": "edge", "src": "paper:1307.5892", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1307.5892", "dst": "author:mohan_sarovar", "rel": "authored_by"}
{"type": "edge", "src": "paper:1307.5892", "dst": "author:kevin_c_young", "rel": "authored_by"}
{"type": "edge", "src": "paper:1907.10552", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1907.10552", "dst": "author:tam_s_kriv_chy", "rel": "authored_by"}
{"type": "edge", "src": "paper:1907.10552", "dst": "author:yu_cai", "rel": "authored_by"}
{"type": "edge", "src": "paper:1907.10552", "dst": "author:daniel_cavalcanti", "rel": "authored_by"}
{"type": "edge", "src": "paper:1907.10552", "dst": "author:arash_tavakoli", "rel": "authored_by"}
{"type": "edge", "src": "paper:1907.10552", "dst": "author:nicolas_gisin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.07362", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2304.07362", "dst": "author:evgenii_egorov", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.07362", "dst": "author:roberto_bondesan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.07362", "dst": "author:max_welling", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.07522", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2601.07522", "dst": "author:nobumasa_ishida", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.07522", "dst": "author:yoshihiko_hasegawa", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.04338", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2006.16189", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2201.12150", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2302.08893", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2304.02381", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2303.15563", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1905.04749", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2602.11092", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1705.05172", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1810.13348", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1810.13348", "dst": "author:keyang_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:1810.13348", "dst": "author:mike_lam", "rel": "authored_by"}
{"type": "edge", "src": "paper:1810.13348", "dst": "author:jingzhi_pang", "rel": "authored_by"}
{"type": "edge", "src": "paper:1810.13348", "dst": "author:xin_gao", "rel": "authored_by"}
{"type": "edge", "src": "paper:1810.13348", "dst": "author:charlotte_band", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.08759", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1906.01101", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2404.12511", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.07737", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.07737", "dst": "author:andrew_w_senior", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.07737", "dst": "author:thomas_edlich", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.07737", "dst": "author:francisco_j_h_heras", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.07737", "dst": "author:lei_m_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.07737", "dst": "author:oscar_higgott", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.01393", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1908.02829", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1908.02829", "dst": "author:shawn_x_cui", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.02829", "dst": "author:dawei_ding", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.02829", "dst": "author:xizhi_han", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.02829", "dst": "author:geoffrey_penington", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.02829", "dst": "author:daniel_ranard", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.11442", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2304.11442", "dst": "author:guillaume_dauphinais", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.11442", "dst": "author:david_w_kribs", "rel": "authored_by"}
{"type": "edge", "src": "paper:2304.11442", "dst": "author:michael_vasmer", "rel": "authored_by"}
{"type": "edge", "src": "paper:2203.09234", "dst": "axis:qec", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2203.09234", "dst": "author:sangil_kwon", "rel": "authored_by"}
{"type": "edge", "src": "paper:2203.09234", "dst": "author:shohei_watabe", "rel": "authored_by"}
{"type": "edge", "src": "paper:2203.09234", "dst": "author:jaw_shen_tsai", "rel": "authored_by"}
{"type": "edge", "src": "paper:http://arxi", "dst": "author:a_j_scott", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.00978", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2306.00978", "dst": "author:ji_lin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.00978", "dst": "author:jiaming_tang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.00978", "dst": "author:haotian_tang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.00978", "dst": "author:shang_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.00978", "dst": "author:wei_ming_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.08692", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.08692", "dst": "author:beshr_islambouli", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.08692", "dst": "author:david_jin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.10205", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2506.10205", "dst": "author:jing_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.10205", "dst": "author:toshiaki_koike_akino", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.10205", "dst": "author:ye_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.10205", "dst": "author:hassan_mansour", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.10205", "dst": "author:matthew_brand", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.26339", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.26339", "dst": "author:preetam_sharma", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.26339", "dst": "author:kacper_dobek", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.05868", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2606.05868", "dst": "author:psbc_llm_team", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.05868", "dst": "author:huawei_llm_team", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.05868", "dst": "author:ruihan_long", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.05868", "dst": "author:junjie_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.05868", "dst": "author:tianan_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.14302", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2505.14302", "dst": "author:mengzhao_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.14302", "dst": "author:chaoyi_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.14302", "dst": "author:jing_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.14302", "dst": "author:yutao_zeng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.14302", "dst": "author:zeyue_xue", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.05352", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2504.05352", "dst": "author:siqing_song", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.05352", "dst": "author:chuang_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.05352", "dst": "author:ruiqi_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.05352", "dst": "author:yi_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2504.05352", "dst": "author:xu_yao_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.16299", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2406.16299", "dst": "author:yifei_gao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.16299", "dst": "author:jie_ou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.16299", "dst": "author:lei_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.16299", "dst": "author:yuting_xiao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.16299", "dst": "author:zhiyuan_xiang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.15508", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2407.15508", "dst": "author:yifei_gao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.15508", "dst": "author:jie_ou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.15508", "dst": "author:lei_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.15508", "dst": "author:jun_cheng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.15508", "dst": "author:mengchu_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.04532", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2405.04532", "dst": "author:yujun_lin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.04532", "dst": "author:haotian_tang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.04532", "dst": "author:shang_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.04532", "dst": "author:zhekai_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.04532", "dst": "author:guangxuan_xiao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.22873", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2601.22873", "dst": "author:li_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.22873", "dst": "author:hao_jiang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.22873", "dst": "author:junjie_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.22873", "dst": "author:tianrui_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.22873", "dst": "author:haizhou_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.12065", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2402.12065", "dst": "author:yuxuan_yue", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.12065", "dst": "author:zhihang_yuan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.12065", "dst": "author:haojie_duanmu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.12065", "dst": "author:sifan_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.12065", "dst": "author:jianlong_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.19296", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2603.19296", "dst": "author:toshiaki_koike_akino", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.19296", "dst": "author:jing_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.19296", "dst": "author:ye_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.08044", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2407.08044", "dst": "author:xijie_huang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.08044", "dst": "author:zechun_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.08044", "dst": "author:shih_yang_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.08044", "dst": "author:kwang_ting_cheng", "rel": "authored_by"}
{"type": "edge", "src": "paper:1702.03044", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1702.03044", "dst": "author:aojun_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:1702.03044", "dst": "author:anbang_yao", "rel": "authored_by"}
{"type": "edge", "src": "paper:1702.03044", "dst": "author:yiwen_guo", "rel": "authored_by"}
{"type": "edge", "src": "paper:1702.03044", "dst": "author:lin_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:1702.03044", "dst": "author:yurong_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2210.17323", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2210.17323", "dst": "author:elias_frantar", "rel": "authored_by"}
{"type": "edge", "src": "paper:2210.17323", "dst": "author:saleh_ashkboos", "rel": "authored_by"}
{"type": "edge", "src": "paper:2210.17323", "dst": "author:torsten_hoefler", "rel": "authored_by"}
{"type": "edge", "src": "paper:2210.17323", "dst": "author:dan_alistarh", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.18553", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2507.18553", "dst": "author:jiale_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.18553", "dst": "author:yalda_shabanzadeh", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.18553", "dst": "author:elvir_crn_evi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.18553", "dst": "author:torsten_hoefler", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.18553", "dst": "author:dan_alistarh", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.08155", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2406.08155", "dst": "author:pingzhi_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.08155", "dst": "author:xiaolong_jin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.08155", "dst": "author:zhen_tan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.08155", "dst": "author:yu_cheng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.08155", "dst": "author:tianlong_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.16989", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2509.16989", "dst": "author:he_xiao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.16989", "dst": "author:runming_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.16989", "dst": "author:qingyao_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.16989", "dst": "author:wendong_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.16989", "dst": "author:zhen_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.03332", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2508.03332", "dst": "author:he_xiao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.03332", "dst": "author:qingyao_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.03332", "dst": "author:dirui_xie", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.03332", "dst": "author:wendong_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.03332", "dst": "author:zunhai_su", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.01412", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2606.01412", "dst": "author:shihao_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.01412", "dst": "author:rayan_saab", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.09430", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.09430", "dst": "author:junkang_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.09430", "dst": "author:yefei_he", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.09430", "dst": "author:feng_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.09430", "dst": "author:weijie_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.09430", "dst": "author:bohan_zhuang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.02351", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2505.02351", "dst": "author:jie_kong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.02351", "dst": "author:junxiang_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.02351", "dst": "author:jiheng_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.02351", "dst": "author:yalong_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.02351", "dst": "author:shouhua_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.21321", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2502.21321", "dst": "author:komal_kumar", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.21321", "dst": "author:tajamul_ashraf", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.21321", "dst": "author:omkar_thawakar", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.21321", "dst": "author:rao_muhammad_anwer", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.21321", "dst": "author:hisham_cholakkal", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.12991", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2509.12991", "dst": "author:ya_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.12991", "dst": "author:yujie_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.12991", "dst": "author:xiaohan_fan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2509.12991", "dst": "author:wei_zhao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2308.07662", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2308.07662", "dst": "author:edouard_yvinec", "rel": "authored_by"}
{"type": "edge", "src": "paper:2308.07662", "dst": "author:arnaud_dapogny", "rel": "authored_by"}
{"type": "edge", "src": "paper:2308.07662", "dst": "author:kevin_bailly", "rel": "authored_by"}
{"type": "edge", "src": "paper:2601.11663", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2601.11663", "dst": "author:bruce_changlong_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.07190", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1911.07190", "dst": "author:yury_nahshan", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.07190", "dst": "author:brian_chmiel", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.07190", "dst": "author:chaim_baskin", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.07190", "dst": "author:evgenii_zheltonozhskii", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.07190", "dst": "author:ron_banner", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.11222", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.11222", "dst": "author:ryan_lucas", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.11222", "dst": "author:mehdi_makni", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.11222", "dst": "author:xiang_meng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.11222", "dst": "author:adam_deng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.11222", "dst": "author:rahul_mazumder", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.11651", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2310.00034", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2312.10793", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2304.12244", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2410.05265", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2410.05265", "dst": "author:mengzhao_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.05265", "dst": "author:yi_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.05265", "dst": "author:jiahao_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.05265", "dst": "author:yi_bin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.05265", "dst": "author:wenqi_shao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.21676", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2308.16149", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2405.19266", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2405.11357", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2405.11357", "dst": "author:andrew_shin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2405.11357", "dst": "author:kunitake_kaneko", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.05434", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2312.05434", "dst": "author:hongzhan_lin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.05434", "dst": "author:ziyang_luo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.05434", "dst": "author:jing_ma", "rel": "authored_by"}
{"type": "edge", "src": "paper:2312.05434", "dst": "author:long_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.04848", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2508.04848", "dst": "author:chang_tian", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.04848", "dst": "author:matthew_b_blaschko", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.04848", "dst": "author:mingzhe_xing", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.04848", "dst": "author:xiuxing_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.04848", "dst": "author:yinliang_yue", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.14679", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2402.14679", "dst": "author:yiming_ai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.14679", "dst": "author:zhiwei_he", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.14679", "dst": "author:ziyin_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.14679", "dst": "author:wenhong_zhu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.14679", "dst": "author:hongkun_hao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.08568", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2306.08568", "dst": "author:ziyang_luo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.08568", "dst": "author:can_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.08568", "dst": "author:pu_zhao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.08568", "dst": "author:qingfeng_sun", "rel": "authored_by"}
{"type": "edge", "src": "paper:2306.08568", "dst": "author:xiubo_geng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.12036", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2407.12036", "dst": "author:giorgio_roffo", "rel": "authored_by"}
{"type": "edge", "src": "paper:1609.04846", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1909.13144", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1909.13144", "dst": "author:yuhang_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:1909.13144", "dst": "author:xin_dong", "rel": "authored_by"}
{"type": "edge", "src": "paper:1909.13144", "dst": "author:wei_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:1902.06822", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1902.06822", "dst": "author:yoni_choukroun", "rel": "authored_by"}
{"type": "edge", "src": "paper:1902.06822", "dst": "author:eli_kravchik", "rel": "authored_by"}
{"type": "edge", "src": "paper:1902.06822", "dst": "author:fan_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:1902.06822", "dst": "author:pavel_kisilev", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.11396", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.11396", "dst": "author:yupeng_su", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.11396", "dst": "author:ruijie_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.11396", "dst": "author:ziyue_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.11396", "dst": "author:yequan_zhao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.11396", "dst": "author:zheng_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.05530", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2505.05530", "dst": "author:kai_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.05530", "dst": "author:qian_zheng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.05530", "dst": "author:kaiwen_tao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.05530", "dst": "author:zhiteng_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.05530", "dst": "author:haotong_qin", "rel": "authored_by"}
{"type": "edge", "src": "paper:2502.01654", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2009.08695", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2009.08695", "dst": "author:zhaohui_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.08695", "dst": "author:yunhe_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.08695", "dst": "author:kai_han", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.08695", "dst": "author:chunjing_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.08695", "dst": "author:chao_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2210.15189", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2210.15189", "dst": "author:panagiotis_rizomiliotis", "rel": "authored_by"}
{"type": "edge", "src": "paper:2210.15189", "dst": "author:christos_diou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2210.15189", "dst": "author:aikaterini_triakosia", "rel": "authored_by"}
{"type": "edge", "src": "paper:2210.15189", "dst": "author:ilias_kyrannas", "rel": "authored_by"}
{"type": "edge", "src": "paper:2210.15189", "dst": "author:konstantinos_tserpes", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.05033", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1908.05033", "dst": "author:ruihao_gong", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.05033", "dst": "author:xianglong_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.05033", "dst": "author:shenghu_jiang", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.05033", "dst": "author:tianxiang_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:1908.05033", "dst": "author:peng_hu", "rel": "authored_by"}
{"type": "edge", "src": "paper:1708.01001", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1708.01001", "dst": "author:yinpeng_dong", "rel": "authored_by"}
{"type": "edge", "src": "paper:1708.01001", "dst": "author:renkun_ni", "rel": "authored_by"}
{"type": "edge", "src": "paper:1708.01001", "dst": "author:jianguo_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:1708.01001", "dst": "author:yurong_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:1708.01001", "dst": "author:jun_zhu", "rel": "authored_by"}
{"type": "edge", "src": "paper:1803.02421", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2307.00331", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2307.00331", "dst": "author:xijie_huang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.00331", "dst": "author:zhiqiang_shen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.00331", "dst": "author:pingcheng_dong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2307.00331", "dst": "author:kwang_ting_cheng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.29337", "dst": "axis:quant", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2606.29337", "dst": "author:yidong_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.29337", "dst": "author:chengyu_shi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.29337", "dst": "author:jiahao_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.29727", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2603.29727", "dst": "author:latent_labs_team", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.29727", "dst": "author:sebastian_m_schmon", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.29727", "dst": "author:daniella_pretorius", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.29727", "dst": "author:simon_mathis", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.29727", "dst": "author:rebecca_bartke_croughan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.19375", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2507.19375", "dst": "author:latent_labs_team", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.19375", "dst": "author:alex_bridgland", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.19375", "dst": "author:jonathan_crabb", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.19375", "dst": "author:henry_kenlay", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.19375", "dst": "author:daniella_pretorius", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.20263", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.20263", "dst": "author:latent_labs_team", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.20263", "dst": "author:henry_kenlay", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.20263", "dst": "author:daniella_pretorius", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.20263", "dst": "author:jonathan_crabb", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.20263", "dst": "author:alex_bridgland", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.15725", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.15725", "dst": "author:tianqiu_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.15725", "dst": "author:muyang_lyu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.15725", "dst": "author:yufan_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.15725", "dst": "author:fang_fang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.15725", "dst": "author:si_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2607.04464", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2607.04464", "dst": "author:donna_vakalis", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.18938", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2503.18938", "dst": "author:shenyuan_gao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.18938", "dst": "author:siyuan_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.18938", "dst": "author:yilun_du", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.18938", "dst": "author:jun_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2503.18938", "dst": "author:chuang_gan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.31361", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.31361", "dst": "author:tomas_leroy_stone", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.09828", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2606.09828", "dst": "author:weijie_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.09828", "dst": "author:haoyu_zhao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.09828", "dst": "author:yifan_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.09828", "dst": "author:feng_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.09828", "dst": "author:zeyu_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.13295", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2606.13295", "dst": "author:simultaneous_latent_budget_trees_for_stratified_classification_cristian_buoncomp", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.13295", "dst": "author:stefano_pellegrino", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.13295", "dst": "author:giulia_vannucci", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.13295", "dst": "author:raffaele_dubbioso", "rel": "authored_by"}
{"type": "edge", "src": "paper:2606.13295", "dst": "author:roberta_siciliano", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.10104", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2602.10104", "dst": "author:yuxin_jiang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.10104", "dst": "author:yuchao_gu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.10104", "dst": "author:ivor_w_tsang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.10104", "dst": "author:mike_zheng_shou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.00613", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2506.00613", "dst": "author:julian_quevedo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.00613", "dst": "author:ansh_kumar_sharma", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.00613", "dst": "author:yixiang_sun", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.00613", "dst": "author:varad_suryavanshi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.00613", "dst": "author:percy_liang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.07092", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2510.07092", "dst": "author:riccardo_mereu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.07092", "dst": "author:aidan_scannell", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.07092", "dst": "author:yuxin_hou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.07092", "dst": "author:yi_zhao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2510.07092", "dst": "author:aditya_jitta", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.04715", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2603.04715", "dst": "author:gavin_wong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.00005", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.00005", "dst": "author:agniprabha_chakraborty", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.23993", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.23993", "dst": "author:siqiao_huang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.23993", "dst": "author:partha_kaushik", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.23993", "dst": "author:michael_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.23993", "dst": "author:hengkai_pan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.23993", "dst": "author:kaiwen_geng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.00804", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2009.00804", "dst": "author:zhihui_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.00804", "dst": "author:jingwen_leng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.00804", "dst": "author:lingxiao_ma", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.00804", "dst": "author:youshan_miao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2009.00804", "dst": "author:chao_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:2207.13219", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2207.13219", "dst": "author:marcelo_orenes_vera", "rel": "authored_by"}
{"type": "edge", "src": "paper:2207.13219", "dst": "author:esin_tureci", "rel": "authored_by"}
{"type": "edge", "src": "paper:2207.13219", "dst": "author:david_wentzlaff", "rel": "authored_by"}
{"type": "edge", "src": "paper:2207.13219", "dst": "author:margaret_martonosi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.10489", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2508.10489", "dst": "author:jonas_ulmen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.10489", "dst": "author:ganesh_sundaram", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.10489", "dst": "author:daniel_g_rges", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.19171", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2402.19171", "dst": "author:vittorio_cortellessa", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.19171", "dst": "author:j_andres_diaz_pace", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.19171", "dst": "author:daniele_di_pompeo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2402.19171", "dst": "author:michele_tucci", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.20486", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2412.20486", "dst": "author:takumi_kobori", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.20486", "dst": "author:yasunari_suzuki", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.20486", "dst": "author:yosuke_ueno", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.20486", "dst": "author:teruo_tanimoto", "rel": "authored_by"}
{"type": "edge", "src": "paper:2412.20486", "dst": "author:synge_todo", "rel": "authored_by"}
{"type": "edge", "src": "paper:1306.0089", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1306.0089", "dst": "author:amitabha_sinha", "rel": "authored_by"}
{"type": "edge", "src": "paper:1306.0089", "dst": "author:mitrava_sarkar", "rel": "authored_by"}
{"type": "edge", "src": "paper:1306.0089", "dst": "author:soumojit_acharyya", "rel": "authored_by"}
{"type": "edge", "src": "paper:1306.0089", "dst": "author:suranjan_chakraborty", "rel": "authored_by"}
{"type": "edge", "src": "paper:2603.00049", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2603.00049", "dst": "author:yongchao_huang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.09343", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2505.09343", "dst": "author:chenggang_zhao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.09343", "dst": "author:chengqi_deng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.09343", "dst": "author:chong_ruan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.09343", "dst": "author:damai_dai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2505.09343", "dst": "author:huazuo_gao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.10942", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2512.10942", "dst": "author:delong_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.10942", "dst": "author:mustafa_shukor", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.10942", "dst": "author:theo_moutakanni", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.10942", "dst": "author:willy_chung", "rel": "authored_by"}
{"type": "edge", "src": "paper:2512.10942", "dst": "author:jade_yu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2211.10831", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2211.10831", "dst": "author:vlad_sobal", "rel": "authored_by"}
{"type": "edge", "src": "paper:2211.10831", "dst": "author:jyothir_s", "rel": "authored_by"}
{"type": "edge", "src": "paper:2211.10831", "dst": "author:siddhartha_jalagam", "rel": "authored_by"}
{"type": "edge", "src": "paper:2211.10831", "dst": "author:nicolas_carion", "rel": "authored_by"}
{"type": "edge", "src": "paper:2211.10831", "dst": "author:kyunghyun_cho", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.03755", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2410.03755", "dst": "author:dengsheng_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.03755", "dst": "author:jie_hu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.03755", "dst": "author:xiaoming_wei", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.03755", "dst": "author:enhua_wu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2301.07516", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2301.07516", "dst": "author:daniele_di_pompeo", "rel": "authored_by"}
{"type": "edge", "src": "paper:2301.07516", "dst": "author:michele_tucci", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.10733", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2407.10733", "dst": "author:dong_hee_kim", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.10733", "dst": "author:sungduk_cho", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.10733", "dst": "author:hyeonwoo_cho", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.10733", "dst": "author:chanmin_park", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.10733", "dst": "author:jinyoung_kim", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.18194", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2506.18194", "dst": "author:francesco_piccoli", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.18194", "dst": "author:gabriel_vogel", "rel": "authored_by"}
{"type": "edge", "src": "paper:2506.18194", "dst": "author:jana_m_weber", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.16432", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2404.16432", "dst": "author:ayumu_saito", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.16432", "dst": "author:prachi_kudeshia", "rel": "authored_by"}
{"type": "edge", "src": "paper:2404.16432", "dst": "author:jiju_poovvancheri", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.05131", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2403.05131", "dst": "author:fachrina_dewi_puspitasari", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.05131", "dst": "author:chaoning_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.05131", "dst": "author:joseph_cho", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.05131", "dst": "author:adnan_haider", "rel": "authored_by"}
{"type": "edge", "src": "paper:2403.05131", "dst": "author:noor_ul_eman", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.22882", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.22882", "dst": "author:kaichen_zhou", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.22882", "dst": "author:yuzhen_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.22882", "dst": "author:fangneng_zhan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.22882", "dst": "author:hang_hua", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.22882", "dst": "author:grace_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.24322", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.24322", "dst": "author:nahid_alam", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.08585", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2511.08585", "dst": "author:jingtong_yue", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.08585", "dst": "author:ziqi_huang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.08585", "dst": "author:zhaoxi_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.08585", "dst": "author:xintao_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2511.08585", "dst": "author:pengfei_wan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.12822", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2410.12822", "dst": "author:marc_rigter", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.12822", "dst": "author:tarun_gupta", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.12822", "dst": "author:agrin_hilmkil", "rel": "authored_by"}
{"type": "edge", "src": "paper:2410.12822", "dst": "author:chao_ma", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.00367", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2407.00367", "dst": "author:peng_dai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.00367", "dst": "author:feitong_tan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.00367", "dst": "author:qiangeng_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.00367", "dst": "author:david_futschik", "rel": "authored_by"}
{"type": "edge", "src": "paper:2407.00367", "dst": "author:ruofei_du", "rel": "authored_by"}
{"type": "edge", "src": "paper:1709.06342", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1709.06342", "dst": "author:mai_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:1709.06342", "dst": "author:chen_li", "rel": "authored_by"}
{"type": "edge", "src": "paper:1709.06342", "dst": "author:zulin_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:1709.06342", "dst": "author:zhenzhong_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:1709.06342", "dst": "author:zhenyu_guan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.09985", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2401.09985", "dst": "author:xiaofeng_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.09985", "dst": "author:zheng_zhu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.09985", "dst": "author:guan_huang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.09985", "dst": "author:boyuan_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2401.09985", "dst": "author:xinze_chen", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.16869", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2507.16869", "dst": "author:yue_ma", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.16869", "dst": "author:kunyu_feng", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.16869", "dst": "author:zhongyuan_hu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.16869", "dst": "author:xinyu_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.16869", "dst": "author:yucheng_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2305.14669", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2305.14669", "dst": "author:yexing_song", "rel": "authored_by"}
{"type": "edge", "src": "paper:2305.14669", "dst": "author:meilin_wang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2305.14669", "dst": "author:zhijing_yang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2305.14669", "dst": "author:xiaoyu_xian", "rel": "authored_by"}
{"type": "edge", "src": "paper:2305.14669", "dst": "author:yukai_shi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.08048", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2508.08048", "dst": "author:peng_dai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.08048", "dst": "author:feitong_tan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.08048", "dst": "author:qiangeng_xu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.08048", "dst": "author:yihua_huang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2508.08048", "dst": "author:david_futschik", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.27589", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2605.27589", "dst": "author:kunlin_cai", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.27589", "dst": "author:rui_song", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.27589", "dst": "author:jinghuai_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.27589", "dst": "author:kaiyuan_zhang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2605.27589", "dst": "author:pranav_bodapati", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.09455", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2406.09455", "dst": "author:jiannan_xiang", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.09455", "dst": "author:guangyi_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.09455", "dst": "author:yi_gu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.09455", "dst": "author:qiyue_gao", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.09455", "dst": "author:yuting_ning", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.12375", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2602.12375", "dst": "author:abdul_wahab", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.12375", "dst": "author:raksha_kumaraswamy", "rel": "authored_by"}
{"type": "edge", "src": "paper:2602.12375", "dst": "author:martha_white", "rel": "authored_by"}
{"type": "edge", "src": "paper:1711.10137", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1711.10137", "dst": "author:jake_bruce", "rel": "authored_by"}
{"type": "edge", "src": "paper:1711.10137", "dst": "author:niko_suenderhauf", "rel": "authored_by"}
{"type": "edge", "src": "paper:1711.10137", "dst": "author:piotr_mirowski", "rel": "authored_by"}
{"type": "edge", "src": "paper:1711.10137", "dst": "author:raia_hadsell", "rel": "authored_by"}
{"type": "edge", "src": "paper:1711.10137", "dst": "author:michael_milford", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.02910", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2507.02910", "dst": "author:geonwoo_cho", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.02910", "dst": "author:jaegyun_im", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.02910", "dst": "author:doyoon_kim", "rel": "authored_by"}
{"type": "edge", "src": "paper:2507.02910", "dst": "author:sundong_kim", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.05037", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1807.05037", "dst": "author:chris_cundy", "rel": "authored_by"}
{"type": "edge", "src": "paper:1807.05037", "dst": "author:daniel_filan", "rel": "authored_by"}
{"type": "edge", "src": "paper:2301.08028", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2301.08028", "dst": "author:jacob_beck", "rel": "authored_by"}
{"type": "edge", "src": "paper:2301.08028", "dst": "author:risto_vuorio", "rel": "authored_by"}
{"type": "edge", "src": "paper:2301.08028", "dst": "author:evan_zheran_liu", "rel": "authored_by"}
{"type": "edge", "src": "paper:2301.08028", "dst": "author:zheng_xiong", "rel": "authored_by"}
{"type": "edge", "src": "paper:2301.08028", "dst": "author:luisa_zintgraf", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.04896", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2406.04896", "dst": "author:motoki_omura", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.04896", "dst": "author:takayuki_osa", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.04896", "dst": "author:yusuke_mukuta", "rel": "authored_by"}
{"type": "edge", "src": "paper:2406.04896", "dst": "author:tatsuya_harada", "rel": "authored_by"}
{"type": "edge", "src": "paper:1809.09501", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1809.09501", "dst": "author:matthieu_geist", "rel": "authored_by"}
{"type": "edge", "src": "paper:1809.09501", "dst": "author:bruno_scherrer", "rel": "authored_by"}
{"type": "edge", "src": "paper:1705.00470", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1705.00470", "dst": "author:thomas_m_moerland", "rel": "authored_by"}
{"type": "edge", "src": "paper:1705.00470", "dst": "author:joost_broekens", "rel": "authored_by"}
{"type": "edge", "src": "paper:1705.00470", "dst": "author:catholijn_m_jonker", "rel": "authored_by"}
{"type": "edge", "src": "paper:1904.09489", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1904.09489", "dst": "author:joel_ruben_antony_moniz", "rel": "authored_by"}
{"type": "edge", "src": "paper:1904.09489", "dst": "author:barun_patra", "rel": "authored_by"}
{"type": "edge", "src": "paper:1904.09489", "dst": "author:sarthak_garg", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.04947", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1911.04947", "dst": "author:hardik_meisheri", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.04947", "dst": "author:omkar_shelke", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.04947", "dst": "author:richa_verma", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.04947", "dst": "author:harshad_khadilkar", "rel": "authored_by"}
{"type": "edge", "src": "paper:1909.11939", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1909.11939", "dst": "author:yannis_flet_berliac", "rel": "authored_by"}
{"type": "edge", "src": "paper:1909.11939", "dst": "author:philippe_preux", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.02511", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2011.02511", "dst": "author:julia_kreutzer", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.02511", "dst": "author:stefan_riezler", "rel": "authored_by"}
{"type": "edge", "src": "paper:2011.02511", "dst": "author:carolin_lawrence", "rel": "authored_by"}
{"type": "edge", "src": "paper:1907.04543", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1907.04543", "dst": "author:rishabh_agarwal", "rel": "authored_by"}
{"type": "edge", "src": "paper:1907.04543", "dst": "author:dale_schuurmans", "rel": "authored_by"}
{"type": "edge", "src": "paper:1907.04543", "dst": "author:mohammad_norouzi", "rel": "authored_by"}
{"type": "edge", "src": "paper:2112.01195", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:2112.01195", "dst": "author:oleg_svidchenko", "rel": "authored_by"}
{"type": "edge", "src": "paper:2112.01195", "dst": "author:aleksei_shpilman", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.09560", "dst": "axis:worldmodel", "rel": "paper_in_axis"}
{"type": "edge", "src": "paper:1911.09560", "dst": "author:andrea_agostinelli", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.09560", "dst": "author:kai_arulkumaran", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.09560", "dst": "author:marta_sarrico", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.09560", "dst": "author:pierre_richemond", "rel": "authored_by"}
{"type": "edge", "src": "paper:1911.09560", "dst": "author:anil_anthony_bharath", "rel": "authored_by"}
{"type": "edge", "src": "paper:1906.02243", "dst": "axis:energy", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2007.03051", "dst": "axis:energy", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:1907.10597", "dst": "axis:energy", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2211.02001", "dst": "axis:energy", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2210.17323", "dst": "axis:quant", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2306.00978", "dst": "axis:quant", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2208.07339", "dst": "axis:quant", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2305.14314", "dst": "axis:quant", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:1901.09948", "dst": "axis:neuro", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2109.12894", "dst": "axis:neuro", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2311.16863", "dst": "axis:defense", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:1806.06771", "dst": "axis:pinn", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2010.08895", "dst": "axis:pinn", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:1910.03193", "dst": "axis:pinn", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2207.06431", "dst": "axis:qec", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2210.03629", "dst": "axis:agents", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2308.08155", "dst": "axis:agents", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2310.03714", "dst": "axis:agents", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:1803.10122", "dst": "axis:worldmodel", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2301.04104", "dst": "axis:worldmodel", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2402.15391", "dst": "axis:worldmodel", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2301.08243", "dst": "axis:worldmodel", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2210.02747", "dst": "axis:flowmatch", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2209.03003", "dst": "axis:flowmatch", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "paper:2303.08797", "dst": "axis:flowmatch", "rel": "anchor_paper_in_axis"}
{"type": "edge", "src": "lab:intel_ncl", "dst": "axis:neuro", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:lava_nc", "dst": "axis:neuro", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:open_neuromorphic", "dst": "axis:neuro", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:inrc", "dst": "axis:neuro", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:ibm_truenorth", "dst": "axis:neuro", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:sensetime_snn", "dst": "axis:neuro", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:ucsc_neuromorphic", "dst": "axis:neuro", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:human_brain_project", "dst": "axis:neuro", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:spinnaker", "dst": "axis:neuro", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:mlco2", "dst": "axis:energy", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:codecarbon", "dst": "axis:energy", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:green_algorithms", "dst": "axis:energy", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:mlperf_power", "dst": "axis:energy", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:carbontracker_org", "dst": "axis:energy", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:hf_efficiency", "dst": "axis:quant", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:mit_han_lab", "dst": "axis:quant", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:neuralmagic", "dst": "axis:quant", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:ggml_org", "dst": "axis:quant", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:bitsandbytes_fdn", "dst": "axis:quant", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:darpa", "dst": "axis:defense", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:jco_cuas", "dst": "axis:defense", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:dhs_cuas", "dst": "axis:defense", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:nato_mda", "dst": "axis:defense", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:faa_uas", "dst": "axis:defense", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:nrl", "dst": "axis:defense", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:afrl", "dst": "axis:defense", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:nvidia_modulus", "dst": "axis:pinn", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:brown_crunch", "dst": "axis:pinn", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:caltech_ai4science", "dst": "axis:pinn", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:neuraloperator_org", "dst": "axis:pinn", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:lu_group_deepxde", "dst": "axis:pinn", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:google_quantum_ai", "dst": "axis:qec", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:ibm_quantum", "dst": "axis:qec", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:qec_zoo", "dst": "axis:qec", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:qiskit_qec", "dst": "axis:qec", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:stim_org", "dst": "axis:qec", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:riverlane", "dst": "axis:qec", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:langchain_ai", "dst": "axis:agents", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:microsoft_autogen", "dst": "axis:agents", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:crewai_inc", "dst": "axis:agents", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:openai_agents", "dst": "axis:agents", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:hf_smolagents", "dst": "axis:agents", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:stanford_dspy", "dst": "axis:agents", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:metagpt_org", "dst": "axis:agents", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:meta_fair", "dst": "axis:worldmodel", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:deepmind_worldmodel", "dst": "axis:worldmodel", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:wayve", "dst": "axis:worldmodel", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:worldlabs", "dst": "axis:worldmodel", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:decart_ai", "dst": "axis:worldmodel", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:mit_flowmatch", "dst": "axis:flowmatch", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:stability_ai", "dst": "axis:flowmatch", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:blackforest_labs", "dst": "axis:flowmatch", "rel": "org_leads_axis"}
{"type": "edge", "src": "lab:ut_austin_liu", "dst": "axis:flowmatch", "rel": "org_leads_axis"}
{"type": "edge", "src": "person:song_han", "dst": "axis:quant", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:tim_dettmers", "dst": "axis:quant", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:elias_frantar", "dst": "axis:quant", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:ji_lin", "dst": "axis:quant", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:emma_strubell", "dst": "axis:energy", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:sasha_luccioni", "dst": "axis:energy", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:roy_schwartz", "dst": "axis:energy", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:jason_eshraghian", "dst": "axis:neuro", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:mike_davies", "dst": "axis:neuro", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:wei_fang", "dst": "axis:neuro", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:george_karniadakis", "dst": "axis:pinn", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:maziar_raissi", "dst": "axis:pinn", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:zongyi_li", "dst": "axis:pinn", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:anima_anandkumar", "dst": "axis:pinn", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:lu_lu", "dst": "axis:pinn", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:craig_gidney", "dst": "axis:qec", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:harupy_higgott", "dst": "axis:qec", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:yann_lecun", "dst": "axis:worldmodel", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:danijar_hafner", "dst": "axis:worldmodel", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:david_ha", "dst": "axis:worldmodel", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:yaron_lipman", "dst": "axis:flowmatch", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:qiang_liu", "dst": "axis:flowmatch", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:harrison_chase", "dst": "axis:agents", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:omar_khattab", "dst": "axis:agents", "rel": "person_leads_axis"}
{"type": "edge", "src": "person:chi_wang", "dst": "axis:agents", "rel": "person_leads_axis"}
{"type": "edge", "src": "dataset:mlperf_inference", "dst": "axis:energy", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:dawnbench", "dst": "axis:energy", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:ml_emissions_calc", "dst": "axis:energy", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:mmlu_quant", "dst": "axis:quant", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:lm_eval_harness", "dst": "axis:quant", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:nmnist", "dst": "axis:neuro", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:dvs_gesture", "dst": "axis:neuro", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:shd_ssc", "dst": "axis:neuro", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:intel_ndns", "dst": "axis:neuro", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:prophesee_gen", "dst": "axis:neuro", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:drone_vs_bird", "dst": "axis:defense", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:anti_uav", "dst": "axis:defense", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:seaships", "dst": "axis:defense", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:nuscenes", "dst": "axis:fusion", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:kitti", "dst": "axis:fusion", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:waymo_open", "dst": "axis:fusion", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:pdebench", "dst": "axis:pinn", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:pdearena", "dst": "axis:pinn", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:google_qec_data", "dst": "axis:qec", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:gsm8k", "dst": "axis:agents", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:gaia_bench", "dst": "axis:agents", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:swe_bench", "dst": "axis:agents", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:webarena", "dst": "axis:agents", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:atari100k", "dst": "axis:worldmodel", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:dmc_suite", "dst": "axis:worldmodel", "rel": "dataset_for_axis"}
{"type": "edge", "src": "dataset:imagenet_flow", "dst": "axis:flowmatch", "rel": "dataset_for_axis"}
{"type": "edge", "src": "lab:ucsc_neuromorphic", "dst": "repo:jeshraghian/snntorch", "rel": "org_maintains_repo"}
{"type": "edge", "src": "lab:sensetime_snn", "dst": "repo:fangwei123456/spikingjelly", "rel": "org_maintains_repo"}
{"type": "edge", "src": "lab:bitsandbytes_fdn", "dst": "repo:bitsandbytes-foundation/bitsandbytes", "rel": "org_maintains_repo"}
{"type": "edge", "src": "lab:langchain_ai", "dst": "repo:langchain-ai/langgraph", "rel": "org_maintains_repo"}
{"type": "edge", "src": "lab:langchain_ai", "dst": "repo:langchain-ai/langchain", "rel": "org_maintains_repo"}
{"type": "edge", "src": "lab:microsoft_autogen", "dst": "repo:microsoft/autogen", "rel": "org_maintains_repo"}
{"type": "edge", "src": "lab:ut_austin_liu", "dst": "repo:gnobitab/RectifiedFlow", "rel": "org_maintains_repo"}
{"type": "edge", "src": "person:song_han", "dst": "paper:2306.00978", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:tim_dettmers", "dst": "paper:2208.07339", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:tim_dettmers", "dst": "paper:2305.14314", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:elias_frantar", "dst": "paper:2210.17323", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:ji_lin", "dst": "paper:2306.00978", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:emma_strubell", "dst": "paper:1906.02243", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:roy_schwartz", "dst": "paper:1907.10597", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:jason_eshraghian", "dst": "paper:2109.12894", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:george_karniadakis", "dst": "paper:1806.06771", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:george_karniadakis", "dst": "paper:1910.03193", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:maziar_raissi", "dst": "paper:1806.06771", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:zongyi_li", "dst": "paper:2010.08895", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:lu_lu", "dst": "paper:1910.03193", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:craig_gidney", "dst": "paper:2207.06431", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:yann_lecun", "dst": "paper:2301.08243", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:danijar_hafner", "dst": "paper:2301.04104", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:david_ha", "dst": "paper:1803.10122", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:yaron_lipman", "dst": "paper:2210.02747", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:qiang_liu", "dst": "paper:2209.03003", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:omar_khattab", "dst": "paper:2310.03714", "rel": "person_authored_paper"}
{"type": "edge", "src": "person:chi_wang", "dst": "paper:2308.08155", "rel": "person_authored_paper"}