I’m a final-year Ph.D. candidate at McGill University under the supervision of Prof. Lijun Sun. I was a visiting student researcher at the Robotics Institute, Carnegie Mellon University in 2023 under the supervision of Prof. Changliu Liu, and at the Department of Mechanical Engineering in 2018 under the supervision of Prof. Ding Zhao. Additionally, I conducted research at the Department of Mechanical Engineering, UC Berkeley from 2019 to 2020 under the supervision of Prof. Masayoshi Tomizuka. I earned my Bachelor degree in Vehicle Engineering from Chongqing University, in 2019.

My research is dedicated to establishing the foundations of Trustworthy AI/ML within complex, multi-agent dynamical systems. I bridge the gap between Traffic Flow Theory and Embodied AI by developing advanced frameworks for interpretable spatiotemporal reasoning and robust uncertainty quantification. By integrating Bayesian Statistics with Generative Models, my work transforms high-dimensional, evolving urban traffic data into high-fidelity Driver World Models. These models explicitly account for the inherent stochasticity of human-centric behaviors, providing a statistically rigorous pathway toward the safe and efficient deployment of autonomous systems in real-world, information-rich environments.

👋 Please feel free to contact me to schedule a quick discussion if you are interested in collaborating with me.

📢 I am actively seeking a postdoctoral position focused on stochastic modeling and simulation of human social behaviors in complex and interactive scenarios, dynamic interaction modeling (including both drivers and pedestrians), and Bayesian inference for human social behaviors. If my research interests align with your group, I would be excited to connect!

Featured Research

• Traffic Flow Theory & Traffic Simulations
  • Bayesian calibration of car-following models (IEEE T-ITS)
  • Calibrating Car-Following Models via Bayesian Dynamic Regression (ISTTT25 & TR Part C)
• Multi-Agent Social Interactions & Driver World Model
  • Social interactions for autonomous driving: A review and perspectives (Foundations and Trends® in Robotics)
  • Spatiotemporal learning of multivehicle interaction patterns in lane-change scenarios (IEEE T-ITS)
  • Interactive Car-Following: Matters but NOT Always (IEEE ITSC23)
• Spatiotemporal Data Modeling & Interpretable Pattern Discovery
  • Markov Regime-Switching Intelligent Driver Model for Interpretable Car-Following Behavior (arXiv: 2506.14762)
  • Discovering dynamic patterns from spatiotemporal data with time-varying low-rank autoregression (IEEE TKDE)
  • Forecasting sparse movement speed of urban road networks with nonstationary temporal matrix factorization (Transportation Science)
• Robust Uncertainty Quantification with Trustworthy AI
  • When Context Is Not Enough: Modeling Unexplained Variability in Car-Following Behavior (ISTTT26)
  • Active Simulation-Based Inference for Scalable Car-Following Model Calibration (arXiv: 2602.05246)

My Ph.D. Research Summary

News

• New! New preprint alert! Our paper “Active Simulation-Based Inference for Scalable Car-Following Model Calibration” is now available on arXiv: 2602.05246. Please check it out!
• New! Two papers “Online Calibration of Context-Driven Car-Following Models” and “AutoTune: A Unified Benchmark for Highway Traffic Microsimulation Calibration” are accepted at IEEE IV 2026.
• New! Our paper “When Context Is Not Enough: Modeling Unexplained Variability in Car-Following Behavior” is accepted at the 26th International Symposium on Transportation and Traffic Theory (ISTTT26). See you in Munich! [arXiv]
• New! New preprint alert! Our paper “Markov Regime-Switching Intelligent Driver Model for Interpretable Car-Following Behavior” is now available on arXiv: 2506.14762. Please check it out!

Read more