Xiaoliang Shi

xiaoliang-shi

3 1

·

XL-S224

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

Rufus-Air: An Open LLM Post-Training Recipe

upvoted a paper 6 days ago

Does Learning Protein Folding Generalize to Broader Reasoning?

upvoted a paper 24 days ago

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

View all activity

Organizations

xiaoliang-shi 's models

None public yet