Yi Ding

Tuwhy's activity

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

authored a paper 1 day ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published 3 days ago • 126

updated 3 models 2 days ago

Tuwhy/Qwen3-4B-OPSA

Text Generation • 4B • Updated 2 days ago • 356 • 1

Tuwhy/Qwen3.5-9B-OPSA

Image-Text-to-Text • 10B • Updated 2 days ago • 12

Tuwhy/Qwen3-1.7B-OPSA

Text Generation • 2B • Updated 2 days ago • 357

upvoted a paper 2 days ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published 3 days ago • 126

updated a collection 2 days ago

On-Policy Self-Adaptation

Collection

Checkpoints of OPSA on different base models • 4 items • Updated 2 days ago • 1

submitted a paper to Daily Papers 2 days ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published 3 days ago • 126

published 3 models 2 days ago

Tuwhy/Qwen3-1.7B-OPSA

Text Generation • 2B • Updated 2 days ago • 357

Tuwhy/Qwen3.5-9B-OPSA

Image-Text-to-Text • 10B • Updated 2 days ago • 12

Tuwhy/Qwen3-4B-OPSA

Text Generation • 4B • Updated 2 days ago • 356 • 1

authored 2 papers about 1 month ago

Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control

Paper • 2604.26326 • Published May 10 • 15

Learning Self-Correction in Vision-Language Models via Rollout Augmentation

Paper • 2602.08503 • Published Feb 9 • 3

updated a collection about 1 month ago

On-Policy Self-Adaptation

Collection

Checkpoints of OPSA on different base models • 4 items • Updated 2 days ago • 1

upvoted a collection about 1 month ago

On-Policy Self-Adaptation

Collection

Checkpoints of OPSA on different base models • 4 items • Updated 2 days ago • 1

upvoted 2 papers 4 months ago

Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control

Paper • 2604.26326 • Published May 10 • 15

TEMPO: Scaling Test-time Training for Large Reasoning Models

Paper • 2604.19295 • Published Apr 21 • 37

updated a model 7 months ago

Tuwhy/Octopus-8B

Image-Text-to-Text • 9B • Updated Feb 16 • 12

upvoted a paper 7 months ago

Learning Self-Correction in Vision-Language Models via Rollout Augmentation

Paper • 2602.08503 • Published Feb 9 • 3