About Me

I am an engineer in Alibaba Group. I obtained M.Res. in Informatics at the University of Edinburgh under the supervision of prof. Shay Cohen. Prior to that, I interned at the Hong Kong University of Science and Technology under the supervision of Dr. Jie Fu. My interest lies in training agentic large language models (LLMs) by reinforcement learning (RL).

Google Scholar ｜ GitHub ｜ Hugging Face ｜ Kaggle ｜ X ｜ Zhihu

Publications

• CHARM: Calibrating Reward Models with Chatbot Arena Scores
  Xiao Zhu, Chenmien Tan, Pinzhen Chen, Rico Sennrich, Yanlin Zhang, and Hanxu Hu
  Under Review

• Massive Editing for Large Language Models via Meta Learning
  Chenmien Tan, Ge Zhang, and Jie Fu
  ICLR’24

• Learning Rewards to Optimise Global Performance Metrics in Deep Reinforcement Learning
  Junqi Qian, Paul Weng, and Chenmien Tan
  AAMAS’23

• CVaR-Regret Bounds for Multi-Armed Bandits
  Chenmien Tan and Paul Weng
  ACML’22

Competitions

• Learning Equality – Curriculum Recommendations
  Ranking: 17/1057 = 1.6%
• Google AI4Code – Understand Code in Python Notebooks
  Ranking: 25/1135 = 2.2%
• H&M Personalized Fashion Recommendations
  Ranking: 45/2952 = 1.5%

Academic Services

• Reviewer: ICLR’25, ICML’24-25
• TA: NLU+ 23-24, MLP 23-24

Acknowledgement

I am lucky to work with many enthusiastic, intelligent, and hardworking peers, such as Yijun Yang@Edinburgh, Weipeng Zhang@Huawei, Jiahong Xie@SJTU, Xun Zhao@UCAS, Shengda Fan@RUC, Ge Zhang@ByteDance, Hanxu Hu@UZH, and Simon Yu@NEU. I learnt a lot from them. Foremost, I thank Chenxi Chen for her companionship. She is my greatest fortunate.