Lei Zhao

leizhao7's activity

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

authored 2 papers about 14 hours ago

When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing

Paper • 2610.35497 • Published 10 days ago

Why On-Policy Distillation Sometimes Fails: Vanishing Learning Signals

Paper • 2610.11247 • Published 28 days ago

updated 2 models 5 days ago

leizhao7/VideoEdit-Qwen3.6-35B-A3B

Image-Text-to-Text • 35B • Updated 5 days ago • 52 • 1

leizhao7/VideoEdit-Qwen3.5-9B

Image-Text-to-Text • 9B • Updated 5 days ago • 44

liked a model 6 days ago

leizhao7/VideoEdit-Qwen3.6-35B-A3B

Image-Text-to-Text • 35B • Updated 5 days ago • 52 • 1

published 2 models 7 days ago

leizhao7/VideoEdit-Qwen3.6-35B-A3B

Image-Text-to-Text • 35B • Updated 5 days ago • 52 • 1

leizhao7/VideoEdit-Qwen3.5-9B

Image-Text-to-Text • 9B • Updated 5 days ago • 44

updated a model 9 days ago

leizhao7/R1-Distill-Qwen-1.5B-OPD-R1-7B-Step200

Text Generation • 2B • Updated 9 days ago • 233

updated a collection 9 days ago

OPD Learning Signals

Collection

7 items • Updated 9 days ago • 1

published a model 9 days ago

leizhao7/R1-Distill-Qwen-1.5B-OPD-R1-7B-Step200

Text Generation • 2B • Updated 9 days ago • 233

updated a model 9 days ago

leizhao7/R1-Distill-Qwen-1.5B-OPD-Skywork-7B-Step200

Text Generation • 2B • Updated 9 days ago • 232

updated a collection 9 days ago

OPD Learning Signals

Collection

7 items • Updated 9 days ago • 1

published a model 9 days ago

leizhao7/R1-Distill-Qwen-1.5B-OPD-Skywork-7B-Step200

Text Generation • 2B • Updated 9 days ago • 232

updated a model 9 days ago

leizhao7/R1-Distill-Qwen-1.5B-OPD-JustRL-Step200

Text Generation • 2B • Updated 9 days ago • 216

updated a collection 9 days ago

OPD Learning Signals

Collection

7 items • Updated 9 days ago • 1

published a model 9 days ago

leizhao7/R1-Distill-Qwen-1.5B-OPD-JustRL-Step200

Text Generation • 2B • Updated 9 days ago • 216

updated a model 9 days ago

leizhao7/Qwen3-1.7B-OPD-Qwen3-4B-Step200

Text Generation • 2B • Updated 9 days ago • 214

updated a collection 9 days ago

OPD Learning Signals

Collection

7 items • Updated 9 days ago • 1

published a model 9 days ago

leizhao7/Qwen3-1.7B-OPD-Qwen3-4B-Step200

Text Generation • 2B • Updated 9 days ago • 214

updated a model 9 days ago

leizhao7/Qwen3-1.7B-OPD-RL-Math-Step200

Text Generation • 2B • Updated 9 days ago • 202