About Me

I am currently an M.Res. student in EdinburghNLP under the supervision of prof. Shay Cohen. Prior to that, I interned at Hong Kong University of Science and Technology under the supervision of Dr. Jie Fu and Shanghai Jiao Tong University under the supervision of prof. Paul Weng. My current research interest lies in eliciting Reasoning capability of Large Language Models via Reinforcement Learning.

CV ｜ Google Scholar ｜ GitHub ｜ Kaggle ｜ X ｜ Zhihu

I will join WestlakeNLP as research assistant under the supervision of prof. Yue Zhang and UIUCNLP as intern under the supervision of prof. Heng Ji. I am looking for PhD position starting from 2025 fall.

Publications

• 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%

Services

• Reviewer: ICML’24 (6 papers)
• TA: NLU+ 23-24 (44 hours), MLP 23-24 (62 hours)

Fun Facts

• I am the 14th academic generation descendant of Gauss, the 14th of Laplace, the 18th of Bernoulli, the 20th of Leibniz, and the 26th of Copernicus.

• My high school has a history over 2,160 years. This is not a typo. It was founded in 143-141 B.C.

Acknowledgement

I am lucky to meet many enthusiastic, intelligent, and hardworking peers, such as Yijun Yang@Edinburgh, Weipeng Zhang@NEU, Jiahong Xie@SJTU, Xun Zhao@UCAS, Shengda Fan@Beihang, Ge Zhang@Waterloo, Hanxu Hu@UZH, Simon Yu@NEU, and Yangyi Chen@UIUC. I learnt a lot when working with them.