haodi lei

bingyang-lei's activity

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

upvoted a paper 12 days ago

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

Paper • 2609.18708 • Published 13 days ago • 82

upvoted a paper 25 days ago

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Paper • 2609.04172 • Published 26 days ago • 103

updated a collection 25 days ago

Draft-OPD

Collection

9 items • Updated 25 days ago • 3

updated a model 25 days ago

bingyang-lei/qwen3-4b-eagle3-thinking-draftopd

0.2B • Updated 25 days ago • 29

published a model 25 days ago

bingyang-lei/qwen3-4b-eagle3-thinking-draftopd

0.2B • Updated 25 days ago • 29

updated a collection 25 days ago

Draft-OPD

Collection

9 items • Updated 25 days ago • 3

updated a model 25 days ago

bingyang-lei/qwen3-4b-eagle3-thinking-baseline

0.2B • Updated 25 days ago • 16

published a model 25 days ago

bingyang-lei/qwen3-4b-eagle3-thinking-baseline

0.2B • Updated 25 days ago • 16

updated a collection about 1 month ago

Draft-OPD

Collection

9 items • Updated 25 days ago • 3

authored a paper about 1 month ago

SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning

Paper • 2608.14277 • Published Aug 14 • 36

updated a collection about 1 month ago

SimpleOPD

Collection

3 items • Updated Aug 17 • 3

upvoted 2 papers about 1 month ago

SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning

Paper • 2608.14277 • Published Aug 14 • 36

Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning

Paper • 2608.14290 • Published Aug 14 • 35

updated a model about 2 months ago

bingyang-lei/qwen3-8b-thinking-dflash-draftopd-tvloss

1B • Updated Aug 14 • 17

published a model about 2 months ago

bingyang-lei/qwen3-8b-thinking-dflash-draftopd-tvloss

1B • Updated Aug 14 • 17

updated a model about 2 months ago

bingyang-lei/dflash-qwen3-8b-thinking

1B • Updated Aug 13 • 13

published a model about 2 months ago

bingyang-lei/dflash-qwen3-8b-thinking

1B • Updated Aug 13 • 13

upvoted a paper about 2 months ago

Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives

Paper • 2608.08160 • Published Aug 8 • 30

upvoted a collection about 2 months ago

SimpleOPD

Collection

3 items • Updated Aug 17 • 3

updated a collection about 2 months ago

SimpleOPD

Collection

3 items • Updated Aug 17 • 3