Jiaming Wang

Jessamine's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 3 papers 1 day ago

OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning

Paper • 2606.08572 • Published 4 days ago • 12

On the Geometry of On-Policy Distillation

Paper • 2606.07082 • Published 6 days ago • 62

CoVEBench: Can Video Editing Models Handle Complex Instructions?

Paper • 2606.08415 • Published 4 days ago • 46

upvoted 2 papers 2 days ago

Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills

Paper • 2606.07412 • Published 6 days ago • 12

UniSHARP: Universal Sharp Monocular View Synthesis

Paper • 2606.07514 • Published 6 days ago • 14

upvoted a collection 6 days ago

Agent Papers

Collection

4 items • Updated 6 days ago • 1

upvoted 3 papers 6 days ago

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published 10 days ago • 108

MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?

Paper • 2606.01993 • Published 9 days ago • 14

Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories

Paper • 2606.02060 • Published 10 days ago • 53

upvoted 3 papers 8 days ago

TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation

Paper • 2606.02320 • Published 10 days ago • 14

Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding

Paper • 2605.29707 • Published 14 days ago • 143

VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion

Paper • 2605.30351 • Published 14 days ago • 26

upvoted a paper 14 days ago

LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV

Paper • 2605.26244 • Published 17 days ago • 38

upvoted a paper about 1 month ago

HumanNet: Scaling Human-centric Video Learning to One Million Hours

Paper • 2605.06747 • Published May 7 • 52

upvoted 6 papers about 2 months ago

OpenGame: Open Agentic Coding for Games

Paper • 2604.18394 • Published Apr 20 • 81

WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models

Paper • 2604.18224 • Published Apr 20 • 22

Vero: An Open RL Recipe for General Visual Reasoning

Paper • 2604.04917 • Published Apr 6 • 33

DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation

Paper • 2604.14683 • Published Apr 16 • 36

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published Apr 14 • 110

CodeTracer: Towards Traceable Agent States

Paper • 2604.11641 • Published Apr 13 • 38