Jiayang Li
I am a Tenured-Track Assistant Professor in the Department of Data and Systems Engineering at the University of Hong Kong. I obtained my Ph.D. degree in transportation systems analysis from Northwestern University in 2024 and my B.S. degree in mathematics from Tsinghua University in 2019.
My research aims to bring together optimization, game theory, and machine learning to address operations research challenges, particular within transportation and mobility systems. Looking ahead, I am looking forward to expanding my research to other complex systems, including infrastructure, energy, environmental systems and beyond. The ultimate goal of my research is to enhance the quality of life across diverse human habitats.
Openings
I am looking for self-motivated Ph.D. students and postdoctoral researchers with a strong mathematical and/or programming background for 2026 Spring and 2026 Fall. I am also happy to host remote undergraduate research interns. If you have interests, please reach me directly by email at jiayangl@hku.hk.
Selected publications
- Working Paper
LLM-guided reinforcement learning with representative agents for traffic modeling2025Working Paper - OR
An efficient algorithm for continuous bi-criteria traffic assignmentAccepted to Operations Research (subject to a voluntary data and code review), 2025 - ISTTT
- OR Under Revision
Differentiable bilevel programming for Stackelberg congestion games2024Under Revision at Operations Research - TS
A day-to-day dynamical approach to the most likely user equilibrium problemTransportation Science, 2024 - TS
Wardrop equilibrium can be boundedly rational: A new behavioral theory of route choiceTransportation Science, 2024 - TR-B
Accessibility-based ethics-aware transit designTransportation Research Part B: Methodological, 2023 - ICML
Achieving hierarchy-free approximation for bilevel programs with equilibrium constraintsProceeding of the 40th International Conference on Machine Learning, 2023 - NeurIPS
Inducing equilibria via incentives: Simultaneous design-and-play ensures global convergenceAdvances in Neural Information Processing Systems 35, 2022 - NeurIPS
End-to-end learning and intervention in gamesAdvances in Neural Information Processing Systems 33, 2020