Joseph Williams

Joseph-Williams's activity

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

upvoted a paper 8 days ago

Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents

Paper • 2609.17653 • Published 13 days ago • 45

upvoted a paper 12 days ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published 21 days ago • 374

upvoted a paper 15 days ago

Beyond Solver Verdicts: Generative Reward Models for Autoformalization

Paper • 2609.11085 • Published 18 days ago • 34

upvoted a paper 17 days ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published about 1 month ago • 481

upvoted a paper 24 days ago

Last Translation Benchmark

Paper • 2609.04173 • Published 25 days ago • 43

upvoted 5 papers about 2 months ago

Evidence-RL: Towards Evidence-intensive Visual Reasoning

Paper • 2608.08021 • Published Aug 8 • 17

World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation

Paper • 2608.05369 • Published Aug 5 • 27

Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance

Paper • 2608.00782 • Published Aug 1 • 18

CAPEval: A Decoupled Caption Evaluation across Understanding and Generation

Paper • 2608.02589 • Published Aug 3 • 26

SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation

Paper • 2608.02287 • Published Aug 3 • 32