Zhenghao Xu's picture

2 31

Zhenghao Xu

zhenghaoxu

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training

upvoted a paper 4 days ago

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

liked a model about 2 months ago

inclusionAI/LLaDA2.0-flash

View all activity

Organizations

zhenghaoxu 's models

None public yet