Xi Xiong
 |
Xi Xiong, Ph.D. Research Professor 4800 Caoan Road, Tongda Hall, Rm 303 [CV] [Google Scholar] [ResearchGate] [LinkedIn] |
About Me
I am a Research Professor in Transportation Engineering at Tongji University and a Visiting Researcher in the Department of Engineering Science at the University of Oxford, hosted by Prof. Jakob Foerster. Previously, I am a Postdoctoral Fellow at the Harvard Kennedy School. I receive a Ph.D. in Transportation Engineering from New York University, an M.Sc. from Tsinghua University, and a B.Sc. from Jilin University. I am also a co-founder of LangRun.AI.
Research Interests
Intelligent Systems
Reinforcement Learning
Generative AI
Dynamic programming
Optimal Control
Network Optimization
What's New
(Dec 8, 2025) I give a talk at the Stanford Intelligent Systems Laboratory, hosted by Prof. Mykel Kochenderfer, titled “Optimizing Mixed-Autonomy Traffic with Reinforcement Learning and Large Language Models.”
(Nov 18, 2025) We present two papers at IEEE ITSC 2025 in Gold Coast, Australia:
“Multi-Armed Bandit for Stochastic Shortest Path in Mixed Autonomy.” arXiv
“A Large Language Model-Enhanced Q-learning for Capacitated Vehicle Routing Problem with Time Windows.” arXiv
(Nov 3, 2025) Our paper “iLLM-TSC: Integration Reinforcement Learning and Large Language Model for Traffic Signal Control Policy Improvement” receives conditional acceptance from IEEE Transactions on Vehicular Technology. arXiv
(Sep 1, 2025) We welcome Jiazhuo Li, who joins our lab as a master’s student.
(Jun 18, 2025) We present at the IFAC Workshop on Control of Systems Governed by Partial Differential Equations (CPDE 2025) in Beijing, China: “Dyna-Style Learning with a Macroscopic Model for Vehicle Platooning in Mixed-Autonomy Traffic.” link
(May 18, 2025) I begin my academic visit at the University of Oxford, hosted by Prof. Jakob Foerster in the Department of Engineering Science.
(Apr 22, 2025) I attend the 13th International Conference on Learning Representations (ICLR 2025) in Singapore.
(Jan 5, 2025) We present at the 104th TRB Annual Meeting in Washington, DC: “Reinforcement Learning from Human Feedback for Lane Changing of Autonomous Vehicles in Mixed Traffic.” arXiv
(Sep 24, 2024) We present at IEEE ITSC 2024 in Edmonton, Canada: “A Multi-Agent Rollout Approach for Highway Bottleneck Decongestion in Mixed Autonomy.” link
(Sep 2, 2024) Our paper “Traffic Signal Cycle Control with Centralized Critic and Decentralized Actors under Varying Intervention Frequencies” is accepted for publication in IEEE Transactions on Intelligent Transportation Systems. link
(Sep 1, 2024) We welcome Linjiang Cao, who joins our lab as a master’s student.
(Jul 15, 2024) I attend the 6th Annual Learning for Dynamics and Control Conference (L4DC 2024) at the University of Oxford.
(Jun 3, 2024) Our paper “An Approximate Dynamic Programming Approach to Vehicle Platooning Coordination in Networks” is accepted by IEEE Transactions on Intelligent Transportation Systems. link
(May 18, 2024) Our paper “UniTSA: A Universal Reinforcement Learning Framework for V2X Traffic Signal Control” is accepted by IEEE Transactions on Vehicular Technology. link
Visitor Flag Counter