About me
Jiawei Wang is an incoming tenure-track Assistant Professor of Intelligent Transportation at the Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), where he will begin in May 2026. He is currently a postdoctoral researcher at the Graduate School of Interdisciplinary Information Studies at The University of Tokyo and a Visiting Scholar at the Center for Spatial Information Science.
Professional Snapshot
- Current appointments: Postdoctoral Researcher at The University of Tokyo; Visiting Scholar at CSIS
- Upcoming role: Assistant Professor, Intelligent Transportation, HKUST(GZ)
- Education: Ph.D. in Civil Engineering, McGill University (advisor: Prof. Lijun Sun); B.Eng. & M.Eng., Transportation Engineering, Sun Yat-sen University
- Research impact: 1100+ citations; publications in Transportation Research Part C, IEEE T-ITS, NeurIPS, ICLR, and related venues
Research Vision
I build integrated AI-driven transportation systems that connect traffic generation, traffic cognition, and traffic control. My long-term goal is to develop deployable, behaviorally grounded tools that use multimodal mobility data, generative modeling, behavioral intelligence, and system optimization to support resilient, equitable, and efficient urban mobility.
Research Pillars
Traffic Generation & Cognition with Foundation Models
I study how large language models and other foundation models can encode, explain, and predict human mobility behaviors. This work enables behaviorally faithful agents for urban planning scenarios and creates new ways to interrogate travel decision-making.
- Large language models as urban residents: An LLM agent framework for personal mobility generation. NeurIPS, 2024.
- ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM Framework. ICLR, 2026.
Generative Modeling for Traffic Simulation
I design generative AI methods (flow matching, diffusion, and language-based models) to simulate mobility trajectories and system states at scale, producing realistic, controllable environments for policy evaluation.
- TrajFlow: Nation-wide Pseudo GPS Trajectory Generation with Flow Matching Models. ICLR, 2026.
Reinforcement Learning for Public Transportation Control
My research in reinforcement learning, especially multi-agent RL, addresses real operational challenges such as bus bunching, service reliability, and resource allocation.
- Dynamic holding control to avoid bus bunching: A multi-agent deep reinforcement learning framework. Transportation Research Part C, 2020.
- Reducing bus bunching with asynchronous multi-agent reinforcement learning. IJCAI, 2021.
- Robust dynamic bus control: A distributional multi-agent reinforcement learning approach. IEEE Transactions on Intelligent Transportation Systems, 2022.
- Multi-objective multi-agent deep reinforcement learning to reduce bus bunching for multi-line services with a shared corridor. Transportation Research Part C, 2023.
Collaborations & Initiatives
At HKUST(GZ), I am establishing the Generative Intelligent Transportation Lab, focusing on end-to-end mobility intelligence, from synthetic demand generation to adaptive control policies. I collaborate closely with transit agencies and urban data partners to ensure that foundational research translates into deployable technology.
For a complete list of publications, please visit my Google Scholar.
Contact
jiawei-dot-wang4-at-mail-dot-mcgill-dot-ca