William Li PRO

williamium's activity

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

updated a model about 14 hours ago

unsup-opsd2/ckpts

Updated 3 minutes ago

updated a model 2 days ago

unsup-opsd/ckpts

Updated 2 days ago • 1

updated a dataset 2 days ago

williamium/finevision_v4

Viewer • Updated 2 days ago • 60.8k • 30

published a dataset 2 days ago

williamium/finevision_v4

Viewer • Updated 2 days ago • 60.8k • 30

updated a model 3 days ago

xvreason/video-reasoning-generalization-diffsyn

Updated 3 days ago • 1

published 2 models 8 days ago

s2vopd/S2VOPD-Qwen3.5-9B

Image-Text-to-Text • 9B • Updated 7 days ago • 18

s2vopd/S2VOPD-Qwen3.5-4B

Image-Text-to-Text • 5B • Updated 7 days ago • 17

updated 2 models 8 days ago

s2vopd/S2VOPD-Qwen3.5-9B

Image-Text-to-Text • 9B • Updated 7 days ago • 18

s2vopd/S2VOPD-Qwen3.5-4B

Image-Text-to-Text • 5B • Updated 7 days ago • 17

published a model 11 days ago

unsup-opsd2/ckpts

Updated 3 minutes ago

updated a dataset 20 days ago

williamium/finevision40k

Viewer • Updated 20 days ago • 40k • 151

updated a model 21 days ago

unsup-opsd/ckpts

Updated 2 days ago • 1

updated a model 27 days ago

xvreason/video-reasoning-generalization-diffsyn

Updated 3 days ago • 1

authored 5 papers about 1 month ago

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

Paper • 2608.16072 • Published Aug 17 • 50

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published Aug 14 • 126

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published Aug 9 • 180

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 • 81

updated a model about 1 month ago

unsup-opsd/ckpts

Updated 2 days ago • 1

upvoted a paper about 1 month ago

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

Paper • 2608.17253 • Published Aug 19 • 98