William Li PRO

williamium's activity

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

updated a model about 17 hours ago

unsup-opsd/ckpts

Updated about 12 hours ago

updated a model 1 day ago

xvreason/video-reasoning-generalization-diffsyn

Updated 1 day ago • 1

authored 5 papers 1 day ago

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

Paper • 2608.16072 • Published 6 days ago • 148

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 9 days ago • 167

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 14 days ago • 217

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 9 days ago • 162

upvoted a paper 3 days ago

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

Paper • 2608.17253 • Published 4 days ago • 91

submitted a paper to Daily Papers 3 days ago

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

Paper • 2608.17253 • Published 4 days ago • 91

commented a paper 3 days ago

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

Paper • 2608.14036 • Published 9 days ago • 162 •

4

updated a dataset 3 days ago

williamium/finevision40k

Viewer • Updated 3 days ago • 40k • 115

upvoted a paper 3 days ago

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

Paper • 2608.14036 • Published 9 days ago • 162

submitted a paper to Daily Papers 3 days ago

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

Paper • 2608.14036 • Published 9 days ago • 162

commented a paper 3 days ago

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

Paper • 2608.16072 • Published 6 days ago • 148 •

5

upvoted a paper 4 days ago

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

Paper • 2608.16072 • Published 6 days ago • 148

submitted a paper to Daily Papers 4 days ago

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

Paper • 2608.16072 • Published 6 days ago • 148

upvoted a paper 5 days ago

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 9 days ago • 167

submitted a paper to Daily Papers 5 days ago

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 9 days ago • 167

updated a dataset 8 days ago

williamium/u-opsd-backup

Updated 8 days ago • 3.27k

updated a model 8 days ago

williamium/ttground-r1-ckpts

Updated 8 days ago