Zelei Cheng

Mudd 3303

Department of Computer Science

Northwestern University

Email: zelei.cheng@northwestern.edu

I am a PhD candidate in Computer Science at Northwestern University advised by Professor Xinyu Xing. I earned my master’s degree from Purdue University and my bachelor’s degree from Beijing University of Posts and Telecommunications (BUPT). If you are interested in my research, please do not hesitate to contact me via email!

My research interests include

• Reinforcement Learning (Explainable RL, In-context RL, RLHF)
• Large Language Model Safety (Toxicty, Jailbreak, Prompt Injection)
• AI for Software/System Security

Selected Publications

• Zelei Cheng, Xian Wu, Jiahao Yu, Xin-Qiang Cai, Shuo Han, Xinyu Xing

Soft-Label Integration for Robust Toxicity Classification

In Proc. of NeurIPS, 2024.

• Zelei Cheng, Xian Wu, Jiahao Yu, Sabrina Yang, Gang Wang, Xinyu Xing

RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation

In Proc. of ICML, 2024. (Spotlight)

• Zelei Cheng, Xian Wu, Jiahao Yu, Wenhai Sun, Wenbo Guo, Xinyu Xing

StateMask: Explainable Reinforcement Learning through State Mask

In Proc. of NeurIPS, 2023.