I’m a graduate student at MIT, pursuing an M.S. in Computational Science and Engineering (CSE) and an M.S. in Technology and Policy (TPP). I received my B.S. in Mathematics and Physics from Tsinghua University in 2025. Click here to view my up-to-date CV, updated in 2026/7/17.

Research Interests

• LLM Alignment
• Dynamic Control
• Traffic Prediction

News

• Jan, 2026: Our paper “RE-PO: Robust Enhanced Policy Optimization as a General Framework for LLM Alignment” was accepted at ICLR 2026.

• Apr, 2025: I am excited to join MIT IDSS as a master student in Fall 2025.

• Jan, 2025: Our new paper “Pareto Control Barrier Function for Inner Safe Set Maximization Under Input Constraints” was accepted for presentation at American Control Conference (ACC) 2025.

• Oct, 2024: Our new paper “Virtual Nodes Improve Long-term Traffic Prediction “ was accepted for presentation at TRB Annual Meeting 2025.

Publication

• Xiaoyang Cao, Zelai Xu, Mo Guang, Kaiwen Long, Michiel Bakker, Yu Wang, Chao Yu, RE-PO: Robust Enhanced Policy Optimization as a General Framework for LLM Alignment, International Conference on Learning Representations, 2026. arXiv

• Xiaoyang Cao, Zhe Fu, Alexandre M. Bayen, Pareto Control Barrier Function for Inner Safe Set Maximization Under Input Constraints, American Control Conference, 2025. arXiv slide

• Xiaoyang Cao, Dingyi Zhuang, Shenhao Wang, Jinhua Zhao, Virtual Nodes Improve Long-term Traffic Prediction, Transportation Research Board, 2025. arXiv slide