Aozhe Wang

@aozhe-wang · 1 works

Researcher working on post-training methods for mathematical reasoning in large language models.

Recent posts by Aozhe Wang

• TTPO: Test-Time Policy Optimization - Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Distillation (OPSD), have driven rapid progress in mathematical reasoning for large language models,… · Paper · arxiv.org