William Li

williamium's activity

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

updated a model 4 days ago

williamium/indirect_caption

Updated 4 days ago

upvoted a paper 4 days ago

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

Paper • 2603.22281 • Published 5 days ago • 13

upvoted a paper 5 days ago

VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding

Paper • 2603.22285 • Published 5 days ago • 49

updated a model 18 days ago

williamium/AdaptRL

Updated 18 days ago

updated a dataset 22 days ago

williamium/embodied-video-rl

Viewer • Updated 22 days ago • 1.36k • 25

published a dataset 22 days ago

williamium/embodied-video-rl

Viewer • Updated 22 days ago • 1.36k • 25

published a model 22 days ago

williamium/embodied-video-rl

Updated 22 days ago

published a model 23 days ago

williamium/indirect_caption

Updated 4 days ago

published a model 24 days ago

williamium/AdaptRL

Updated 18 days ago

upvoted an article about 1 month ago

view article

Article

Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?

• 

Feb 25

•

13

upvoted a paper about 1 month ago

A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published Feb 23 • 517

published a dataset about 1 month ago

phy-gen/counterfactual-physics

Viewer • Updated 22 days ago • 26.2k • 11.8k

upvoted 2 papers about 1 month ago

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Paper • 2602.12670 • Published Feb 13 • 56

Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs

Paper • 2602.10388 • Published Feb 11 • 244

updated a dataset about 1 month ago

mm-eval/MMBench-en-V11

Viewer • Updated 3 days ago • 7.3k • 72

authored 3 papers about 2 months ago

CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards

Paper • 2510.08529 • Published Oct 9, 2025 • 19

Think3D: Thinking with Space for Spatial Reasoning

Paper • 2601.13029 • Published Jan 19 • 48

TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents

Paper • 2602.07274 • Published Feb 6 • 208

upvoted 2 papers about 2 months ago

ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning

Paper • 2602.02192 • Published Feb 2 • 12

Towards Agentic Intelligence for Materials Science

Paper • 2602.00169 • Published Jan 29 • 47