William Li PRO

williamium's activity

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

updated a model about 10 hours ago

unsup-opsd/ckpts

Updated about 10 hours ago • 1

updated a model about 18 hours ago

unsup-opsd2/ckpts

Updated about 18 hours ago

published a model about 18 hours ago

unsup-opsd2/ckpts

Updated about 18 hours ago

updated a dataset 10 days ago

williamium/finevision40k

Viewer • Updated 10 days ago • 40k • 147

updated a model 17 days ago

xvreason/video-reasoning-generalization-diffsyn

Updated 17 days ago • 1

authored 5 papers 25 days ago

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published 30 days ago • 151

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published Aug 14 • 170

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published Aug 9 • 220

Attention Sinks and Outliers in Attention Residuals

Paper • 2605.17887 • Published May 18

Demystifying Agent Skills: Why They Work-Until They Don't

Paper • 2608.14036 • Published Aug 14 • 170

upvoted a paper 26 days ago

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

Paper • 2608.17253 • Published 28 days ago • 97

submitted a paper to Daily Papers 26 days ago

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

Paper • 2608.17253 • Published 28 days ago • 97

commented a paper 27 days ago

Demystifying Agent Skills: Why They Work-Until They Don't

Paper • 2608.14036 • Published Aug 14 • 170 •

4

upvoted a paper 27 days ago

Demystifying Agent Skills: Why They Work-Until They Don't

Paper • 2608.14036 • Published Aug 14 • 170

submitted a paper to Daily Papers 27 days ago

Demystifying Agent Skills: Why They Work-Until They Don't

Paper • 2608.14036 • Published Aug 14 • 170

commented a paper 27 days ago

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published 30 days ago • 151 •

6

upvoted a paper 28 days ago

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published 30 days ago • 151

submitted a paper to Daily Papers 28 days ago

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published 30 days ago • 151

upvoted a paper 29 days ago

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published Aug 14 • 170

submitted a paper to Daily Papers 29 days ago

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published Aug 14 • 170