🔄 In a Training Loop

haodi lei

bingyang-lei

·

https://www.haodilei.top/

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

upvoted a paper 15 days ago

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

updated a collection 15 days ago

View all activity

Organizations

bingyang-lei 's papers 4

arxiv:2608.14277

arxiv:2605.29343

arxiv:2605.14678

arxiv:2605.13301