Carnegie Mellon University

university

Verified

https://www.cmu.edu

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

fjzzq2002 submitted a paper 5 days ago

Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops

seungone authored a paper 8 days ago

Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization

seungone authored a paper 8 days ago

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

View all activity

Papers

Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

View all Papers

CarnegieMellonU 's papers 51

Submitted by

Ziqian Zhong

Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops

CarnegieMellonU

Carnegie Mellon University

Submitted by

Seungone Kim

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

CarnegieMellonU

Carnegie Mellon University

Submitted by

yubol-bobo

Same Question, Different Source, Different Answer: Auditing Source-Dependence in Medical Multi-Source RAG

CarnegieMellonU

Carnegie Mellon University

Submitted by

yubol-bobo

The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure

CarnegieMellonU

Carnegie Mellon University

Submitted by

Anmol Agarwal

Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization

CarnegieMellonU

Carnegie Mellon University

Submitted by

yubol-bobo

PANDO: Efficient Multimodal AI Agents via Online Skill Distillation

CarnegieMellonU

Carnegie Mellon University

Submitted by

Aviral Chharia

Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation

CarnegieMellonU

Carnegie Mellon University

Submitted by

yubol-bobo

CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM

CarnegieMellonU

Carnegie Mellon University

Submitted by

Seungone Kim

On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists

CarnegieMellonU

Carnegie Mellon University

Submitted by

Ziqian Zhong

Base Models Look Human To AI Detectors

CarnegieMellonU

Carnegie Mellon University

Submitted by

Jindong Wang

LatentUMM: Dual Latent Alignment for Unified Multimodal Models

CarnegieMellonU

Carnegie Mellon University

Submitted by

Jiarui Liu

MixSD: Mixed Contextual Self-Distillation for Knowledge Injection

CarnegieMellonU

Carnegie Mellon University

1

Submitted by

Yujia Zheng

From Generalist to Specialist Representation

CarnegieMellonU

Carnegie Mellon University

Submitted by

Ethan Ning

Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes

CarnegieMellonU

Carnegie Mellon University

Submitted by

Zhiqiu Lin

Building a Precise Video Language with Human-AI Oversight

CarnegieMellonU

Carnegie Mellon University

Submitted by

Shanshan Zhong

SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks

CarnegieMellonU

Carnegie Mellon University

Submitted by

Yujia Zheng

Diverse Dictionary Learning

CarnegieMellonU

Carnegie Mellon University

Submitted by

YiningHong

Symbolic Guardrails for Domain-Specific Agents: Stronger Safety and Security Guarantees Without Sacrificing Utility

CarnegieMellonU

Carnegie Mellon University

Submitted by

Jindong Wang

TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training

CarnegieMellonU

Carnegie Mellon University

Submitted by

Ethan Ning

Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines

CarnegieMellonU

Carnegie Mellon University

2

Submitted by

Prince Wang

AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks

CarnegieMellonU

Carnegie Mellon University

Submitted by

yubol-bobo

The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning

CarnegieMellonU

Carnegie Mellon University

Submitted by

Peter Pak

AdditiveLLM2: A Multi-modal Large Language Model for Additive Manufacturing

CarnegieMellonU

Carnegie Mellon University

2

Submitted by

yubol-bobo

When Documents Disagree: Measuring Institutional Variation in Transplant Guidance with Retrieval-Augmented Language Models

CarnegieMellonU

Carnegie Mellon University

Submitted by

Xiao Fang

In-the-Wild Camouflage Attack on Vehicle Detectors through Controllable Image Editing

CarnegieMellonU

Carnegie Mellon University

Submitted by

Shahriar

SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis

CarnegieMellonU

Carnegie Mellon University

Submitted by

Yehonathan Litman

EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing

CarnegieMellonU

Carnegie Mellon University

Submitted by

Wayne Chi

GameDevBench: Evaluating Agentic Capabilities Through Game Development

CarnegieMellonU

Carnegie Mellon University

Submitted by

Haoran Li

CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs

CarnegieMellonU

Carnegie Mellon University

Submitted by

Jinqi Luo

Reliable and Responsible Foundation Models: A Comprehensive Survey

CarnegieMellonU

Carnegie Mellon University

Submitted by

Jindong Wang

AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent

CarnegieMellonU

Carnegie Mellon University

Submitted by

Shuqi Ke

Value-Based Pre-Training with Downstream Feedback

CarnegieMellonU

Carnegie Mellon University

2

Submitted by

Ethan Ning

GPCR-Filter: a deep learning framework for efficient and precise GPCR modulator discovery

CarnegieMellonU

Carnegie Mellon University

4

Submitted by

Ethan Ning

Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search Requests

CarnegieMellonU

Carnegie Mellon University

2

Submitted by

Zihan Wang

CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives

CarnegieMellonU

Carnegie Mellon University

Submitted by

Seungone Kim

RefineBench: Evaluating Refinement Capability of Language Models via Checklists

CarnegieMellonU

Carnegie Mellon University

Image2Gcode: Image-to-G-code Generation for Additive Manufacturing Using Diffusion-Transformer Model

CarnegieMellonU

Carnegie Mellon University

Agentic Additive Manufacturing Alloy Discovery

CarnegieMellonU

Carnegie Mellon University

MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation

CarnegieMellonU

Carnegie Mellon University

PyNoetic: A modular python framework for no-code development of EEG brain-computer interfaces

CarnegieMellonU

Carnegie Mellon University

Submitted by

Xiao Fang

Adapting Vehicle Detectors for Aerial Imagery to Unseen Domains with Weak Supervision

CarnegieMellonU

Carnegie Mellon University

The Impact of Medication Non-adherence on Adverse Outcomes: Evidence from Schizophrenia Patients via Survival Analysis

CarnegieMellonU

Carnegie Mellon University

Safe-Construct: Redefining Construction Safety Violation Recognition as 3D Multi-View Engagement Task

CarnegieMellonU

Carnegie Mellon University

AdditiveLLM: Large Language Models Predict Defects in Additive Manufacturing

CarnegieMellonU

Carnegie Mellon University

Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba

CarnegieMellonU

Carnegie Mellon University

Human-VDM: Learning Single-Image 3D Human Gaussian Splatting from Video Diffusion Models

CarnegieMellonU

Carnegie Mellon University

Submitted by

yayati jadhav

LLM-3D Print: Large Language Models To Monitor and Control 3D Printing

CarnegieMellonU

Carnegie Mellon University

2

BeadSight: An Inexpensive Tactile Sensor Using Hydro-Gel Beads

CarnegieMellonU

Carnegie Mellon University

Deep Learning for Melt Pool Depth Contour Prediction From Surface Thermal Images via Vision Transformers

CarnegieMellonU

Carnegie Mellon University

ThermoPore: Predicting Part Porosity Based on Thermal Images Using Deep Learning

CarnegieMellonU

Carnegie Mellon University

Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter

CarnegieMellonU

Carnegie Mellon University