substance0724

AI & ML interests

None defined yet.

Recent Activity

zhouxiangxin  submitted a paper about 7 hours ago

Rethinking the Divergence Regularization in LLM RL

zhouxiangxin  authored a paper 4 months ago

Rethinking the Trust Region in LLM Reinforcement Learning

zhouxiangxin  authored a paper 7 months ago

Defeating the Training-Inference Mismatch via FP16

View all activity

Team members 2