About Me

I am learning to scale reinforcement learning for large language models.

CV  |  Google Scholar  |  GitHub  |  Kaggle  |  Zhihu

Projects

• RL2: Ray Less Reinforcement Learning
  Lead developer, >1.1K GitHub stars

Selected Publications

• GEM: A Gym for Agentic LLMs
  Co-author, ICLR’26 and Outstanding in SEA Workshop of NeurIPS’25

• MALMEN: Massive Editing for Large Language Models via Meta Learning
  First author, >130 citations, top 10% cited in ICLR’24