Selected as an Outstanding Reviewer of ICCV 2025 (Top 3%); InfGen accepted to ICCV 2025; RIPT-VLA released; SceneDiffuser++ accepted to CVPR 2025; ProSim accepted to CoRL 2024; Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation published at ICCV 2025; A unified next-token prediction model that performs interleaved closed-loop motion simulation and scene generation for stable long-term traffic simulation; RIPT-VLA: Interactive Post-Training for Vision-Language-Action Models preprint; Promptable Closed-loop Traffic Simulation published at CoRL 2024; Language Conditioned Traffic Generation published at CoRL 2023; EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding published at NeurIPS 2023.
Research Experience
Waymo Research: Research Intern, Jun. 2024 - Nov. 2024, with Chiyu 'Max' Jiang; NVIDIA Research Autonomous Vehicle Research Group: Research Intern, Aug. 2023 - Jun. 2024 & Jun. 2025 - Present, with Boris Ivanovic, Xinshuo Weng, Yuxiao Chen, Boyi Li, Yulong Cao, Marco Pavone; The University of Texas at Austin: Research Assistant, Jan. 2023 - Present, PhD Advisor: Philipp Krähenbühl; Research Assistant, Aug. 2021 - Dec. 2022, with Kristen Grauman; The Chinese University of Hong Kong: Research Assistant, Sep. 2020 - Mar. 2021, with Bolei Zhou; Uber ATG Toronto: Research Intern, Sep. 2019 - Aug. 2020, with Raquel Urtasun, Shenlong Wang; Boston University: Research Assistant, July 2019 - Sep. 2019, with Kate Saenko, Xingchao Peng; Sun Yat-Sen University: Undergraduate Researcher, Sep. 2017 - June 2019, with Wei-Shi Zheng.
Education
The University of Texas at Austin: PhD in Computer Science, Aug. 2021 - Present; Sun Yat-Sen University: B.E. in Computer Science, Sep. 2016 - Jun. 2021, Ranking: 2/189.
Background
Currently a PhD student at The University of Texas at Austin, advised by Philipp Krähenbühl. My research focuses on simulating realistic human behavior and environment evolution. Specifically, my current research focuses on content generation for autonomous driving simulation systems, aiming to make autonomous driving safe and easily accessible for everyone. My long-term goal is to develop realistic world modeling and simulation systems that can be used to train and test intelligent agents in a variety of domains.
Miscellany
Actively looking for full-time research opportunities in the industry. Feel free to reach out if you think I'd be a good match!