About Me
Ph.D. candidate at McGill University — Bayesian learning, trustworthy AI, and driver world models for multi-agent traffic systems.
I’m a final-year Ph.D. candidate at McGill University, advised by Prof. Lijun Sun. I have also been a visiting researcher at CMU (with Prof. Changliu Liu, 2023; Prof. Ding Zhao, 2018) and UC Berkeley (with Prof. Masayoshi Tomizuka, 2019–2020). I received my B.Eng. in Vehicle Engineering from Chongqing University in 2019.
My research builds trustworthy AI for multi-agent traffic systems, combining Bayesian statistics with generative models to create interpretable driver world models that capture the stochasticity of human behavior — a statistically grounded path toward safe, reliable autonomous systems.
Open to postdoc positions. I’m actively seeking a postdoctoral role focused on stochastic modeling of human social behaviors, dynamic interaction modeling (drivers and pedestrians), and Bayesian approaches to trustworthy, cognitively grounded world models. If this aligns with your group’s interests, I’d be glad to connect.
Featured Research
Traffic Flow Theory & Simulation
- 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 & Interpretable Patterns
- 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 & 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)
Selected Publications
News
- 02/2026 New preprint: "Active Simulation-Based Inference for Scalable Car-Following Model Calibration" — arXiv: 2602.05246.
- 01/2026 Two papers accepted at IEEE IV 2026: "Online Calibration of Context-Driven Car-Following Models" and "AutoTune: A Unified Benchmark for Highway Traffic Microsimulation Calibration."
- 11/2025 Paper accepted at ISTTT26: "When Context Is Not Enough: Modeling Unexplained Variability in Car-Following Behavior" [arXiv]. See you in Munich!
- 06/2025 New preprint: "Markov Regime-Switching Intelligent Driver Model for Interpretable Car-Following Behavior" — arXiv: 2506.14762.
