About me
I am a Ph.D. candidate at The Chinese University of Hong Kong, advised by Prof. Kam-Fai Wong. I was a visiting researcher at LMU Munich, working with Prof. Hinrich Schütze. I received my M.S. from Peking University and B.S. from Northwestern Polytechnical University.
My research focuses on training large language models effectively and using them reliably, organized around three questions:
- How can RL incentivize reasoning? [BRIDGE ICML’26, EEPO ICLR’26]
- How do we make alignment robust? [PEARL ICLR’25, VAA ICML’25]
- How do we monitor what LLMs generate? [WatME ACL’24, CONNER EMNLP’23]
News
- [05/2026] One paper on LLM reasoning accepted at ICML 2026.
- [01/2026] One paper on RL exploration accepted at ICLR 2026.
- [05/2025] One paper on safety alignment accepted at ICML 2025.
- [02/2025] One paper on instruction tuning accepted at ICLR 2025.
- [05/2024] One paper on watermarking accepted at ACL 2024.
- [10/2023] One paper on LLM evaluation accepted at EMNLP 2023.
Selected publications (Full list)
Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning
Liang Chen, Xueting Han, Li Shen, Jing Bai, Kam-Fai Wong
ICML 2026EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget
Liang Chen, Xueting Han, Qizhou Wang, Bo Han, Jing Bai, Hinrich Schütze, Kam-Fai Wong
ICLR 2026Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
Liang Chen, Xueting Han, Li Shen, Jing Bai, Kam-Fai Wong
ICML 2025PEARL: Towards Permutation-Resilient LLMs
Liang Chen, Li Shen, Yang Deng, Xiaoyan Zhao, Bin Liang, Kam-Fai Wong
ICLR 2025WatME: Towards Lossless Watermarking Through Lexical Redundancy
Liang Chen, Yatao Bian, Yang Deng, Deng Cai, Shuaiyi Li, Peilin Zhao, Kam-Fai Wong
ACL 2024Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators
Liang Chen, Yang Deng, Yatao Bian, Zeyu Qin, Bingzhe Wu, Tat-Seng Chua, Kam-Fai Wong
EMNLP 2023
Talks
Beyond Two-Stage Training: Cooperative SFT and RL for Improved LLM Reasoning
PhD Seminar, LMU Munich – August 2025
Host: Prof. Hinrich SchützeVulnerability-Aware Alignment: Protect Open-Source LLMs against Unsafe Fine-tuning
AI Time, Online Live – June 2025Towards Trustworthy LLMs: Improving Robustness via Post-Training Optimization
PhD Seminar, LMU Munich – May 2025
Host: Prof. Hinrich Schütze
Teaching
I have served as a teaching assistant for the following courses:
- Operations Research II (SEEM3440) – Covers advanced optimization techniques, including non-linear, integer, and dynamic programming.
- Engineering Innovation and Entrepreneurship (SEEM3450) – A hands-on course focused on identifying engineering opportunities and developing business plans.
Internships
- Microsoft Research, Systems Research Group
- Tencent AI Lab, Machine Learning Center
Community service
- Reviewer for ICML, ICLR, NeurIPS, AISTATS, ACL, EMNLP, and NAACL.
Honors & scholarships
- Postgraduate Studentship, The Chinese University of Hong Kong
- School Scholarship, Peking University
- First-Class Scholarship, Northwestern Polytechnical University
Miscellaneous
Outside of research, I enjoy walking in parks, as well as swimming, hiking, and table tennis.
During my undergrad, I was the runner-up in the Freshmen Cup table tennis singles match and won the team championship three times.
Live long enough to live forever.