Tianming Liu's Homepage

tianmliu_photo.png

1233 G.G.Brown Laboratory

University of Michigan

Ann Arbor, MI 48105

I am an Eric and Wendy Schmidt AI in Science Fellow at Michigan Institute of Data Science & AI in Society. I obtained my Ph.D. degree in transportation engineering (advised by Dr. Yafeng Yin) and M.S. degree in Industrial and Operations Engineering from University of Michigan in 2025, and have obtained my B.S. degree in control science and engineering from Tsinghua University in 2020.

My research operates at the intersection of behavioral science, artificial intelligence, and network theory to craft next-generation models and management strategies for smart transportation and logistics systems. Methodologically, my research integrates behavior economics, statistical learning, network modeling, queueing theory, and generative artificial intelligence. Currently, my research work features:

  • Agentic-LLM-powered models of transportation systems
  • Generative-AI-driven data synthesis and LLM alignment
  • Structural and AI-augmented behavior modeling
  • Behavior-informed operations management of mobility and logistics systems

I am currently on the academic job market and is seeking a tenure-track assistant professor position related to transportation engineering, industrial and systems engineering and urban artificial intelligence.

news

Jul 05, 2026 I am honored to have been invited to join the Early Career Editorial Board of the Journal of Intelligent Transportation Systems.
Jul 01, 2026 Three new papers accepted! Our paper on LLM agentic modeling of learning behavior is accepted by Transportation Research Part C. Another two papers on urban mass transit and logistics systems are accepted by Transportation Research Part E.
Jun 16, 2026 Our paper on LLM alignment of travel choice is accepted by Transportation Science.
Sep 30, 2025 Excited to share all of my 4 papers (2 first author, 2 corresponding author) have been accepted by TRB! Looking forward to presenting them at DC.
Sep 15, 2025 I give a talk at 2025 Modeling Mobility conference on integrating activity-based transportation models with Large Language Model agents.
Aug 21, 2025 I give a talk at MIT LIDs on my agentic-LLM-based travel demand modeling research.

selected publications

  1. TS
    LLM_alignment.png
    Aligning LLM with human travel choices: a persona-based embedding learning approach
    Tianming Liu, Manzi Li, and Yafeng Yin
    Transportation Science, 2026
  2. TRC
    Calibration_agent.png
    Aligning LLM agents with human learning and adjustment behavior: a dual agent approach
    Tianming Liu, Jirong Yang, Yafeng Yin, and 3 more authors
    Transportation Research Part C: Emerging Technologies, 2026
  3. OR Under Revision
    Xi_OR.png
    Fenchel-Young Estimators of Perturbed Utility Models
    Xi Lin, Yafeng Yin, and Tianming Liu
    arXiv preprint arXiv:2602.21376, 2026
  4. TS Under Revision
    queue_lottery.png
    Managing ride-sourcing drivers at transportation terminals: a lottery-based queueing approach
    Tianming Liu, Yafeng Yin, and Vijay Subramanian
    arXiv preprint arXiv:2509.25071, Accepted by the 105th TRB Annual Meeting, 2025
  5. TBS
    LLM_VOT.png
    Valuing time in silicon: Can large language models replicate human value of travel time
    Yingnan Yan, Tianming Liu, and Yafeng Yin
    Travel Behaviour and Society, 2026
  6. AI4T
    AI4T.png
    Toward llm-agent-based modeling of transportation systems: A conceptual framework
    Tianming Liu, Jirong Yang, and Yafeng Yin
    Artificial Intelligence for Transportation, 2025
  7. TRC
    Incentive_model.jpg
    Threshold-based incentives for ride-sourcing drivers: Implications on supply management and welfare effects
    Tianming Liu, Zhengtian Xu, Daniel Vignon, and 3 more authors
    Transportation Research Part C: Emerging Technologies, 2023
  8. TRC
    Incentive_data.png
    Effects of threshold-based incentives on drivers’ labor supply behavior
    Tianming Liu, Zhengtian Xu, Daniel Vignon, and 3 more authors
    Transportation Research Part C: Emerging Technologies, 2023