Department of Mathematics, Columbia UniversityI do theoretical-grounded LLM post training, via optimization theory and reinforcement learning to advance LLM reasoning and alignment. Apart from that, I enjoy doing optimal transport and geometry processing.
I am an undergradute student from Columbia, advised by Prof. Andrew Blumberg and Prof. Tianyi Lin. I am now working closely with Prof. Mengdi Wang and her group in Princeton.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Columbia College, Columbia UniversityB.A. in Mathematics, Computer ScienceMay. 2026
Experience
-
Princeton UniversityResearch Intern; Hosted by Mengdi WangFeb. 2025 -
HKU Musketeers Foundation Institute of Data ScienceResearch Intern; Hosted by Yue Xie, Qingpeng ZhangMay. 2024
Teaching & Service
-
TA for Analysis & Optimization (Sp 24/Fa 24/Sp 25/Fa 25/Sp 26)
-
Reviewer for NeurIPS, ICLR, ICML, AAAI
Selected Publications (view all )
ComPO: Preference Alignment via Comparison Oracles
Peter Chen, Xi Chen, Wotao Yin, Tianyi Lin
Advances in Neural Information Processing Systems 38 (NeurIPS 2025)
ComPO: Preference Alignment via Comparison Oracles
Peter Chen, Xi Chen, Wotao Yin, Tianyi Lin
Advances in Neural Information Processing Systems 38 (NeurIPS 2025)
Beyong Contamination: Rethinking RLVR Learning Dynamics through Clipping, Entropy, and Random Rewards
Peter Chen, Xiaopeng Li, Ziniu Li, Wotao Yin, Xi Chen, Tianyi Lin
ICLR 2026, under review
Beyong Contamination: Rethinking RLVR Learning Dynamics through Clipping, Entropy, and Random Rewards
Peter Chen, Xiaopeng Li, Ziniu Li, Wotao Yin, Xi Chen, Tianyi Lin
ICLR 2026, under review
Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
Peter Chen, Xiaopeng Li, Ziniu Li, Xi Chen, Tianyi Lin
ICLR 2026, under review
Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
Peter Chen, Xiaopeng Li, Ziniu Li, Xi Chen, Tianyi Lin
ICLR 2026, under review