ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025
I am a first-year Ph.D. student at HKU MMLab, co-advised by Prof. Hongyang Li and Prof. Bin Chen. Before joining HKU, I worked as a Research Assistant at 4DVLab with Prof. Yuexin Ma, collaborating closely with Dr. Xinge Zhu. I received my B.Sc. with first-class honours from the dual-degree program between Beijing University of Posts and Telecommunications and Queen Mary University of London.
Research Interests. My current research focuses on Physical AI, especially embodied intelligence and video generation. More broadly, I am interested in how machines can build reliable world understanding from visual and 3D observations, with strong generalization, interpretability, and evolvability.
Started my Ph.D. at HKU MMLab.
ReAL-AD was accepted by ICCV 2025.
IDKB was accepted by AAAI 2025.
OctreeOcc was accepted by NeurIPS 2024.
Introduced IDKB, a large-scale vision-language benchmark for professional driving knowledge.
* indicates equal contribution.
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025
2025 IEEE International Conference on Robotics and Automation (ICRA 2025)
June 2025 - September 2025
Shanghai Artificial Intelligence Laboratory ·
Research Intern · Supervised by Li Chen.
August 2022 - April 2025
ShanghaiTech University ·
Research Assistant · Supervised by Yuexin Ma.
October 2025 - Present
Ph.D., School of Computing and Data Science
September 2018 - July 2022
Joint B.E. Program in Internet of Things Engineering (First-class honours)
I serve as a reviewer for CVPR, ICCV, NeurIPS, AAAI, ICRA, and related venues.
Outside research, I enjoy billiards and jogging.
I am always happy to connect about Physical AI, video generation, 3D vision, and related research collaborations.