About me

I am an incoming PhD student at The University of Hong Kong, advised by Prof Hongyang Li and Prof Bin Chen. Before joining HKU, I worked as as a Research Assistant at 4DVLab with Prof. Yuexin Ma, where I collaborated closely with Dr. Xinge Zhu. I earned my BSc with first-class honours from the dual-degree program between Beijing University of Posts and Telecommunications and Queen Mary University of London.

My work focuses on enabling AI to understand the 3D world like humans do, particularly in the field of autonomous driving, by developing algorithms with high generalizability, interpretability, and evolvability.

You can find my CV here: Yuhang Lu’s Curriculum Vitae

🔥 News

  • 2025.06: ReAL-AD is accepted by ICCV 2025!
  • 2025.06: Join OpenDriveLab as Research Intern.
  • 2024.12: IDKB is accepted by AAAI 2025!
  • 2024.09: OctreeOcc is accepted by NeurIPS 2024!
  • 2024.09: We introduce IDKB, the first large-scale vision-language dataset dedicated to professional driving knowledge and experience.

📝 Publications

* indicates equal contributions

ICCV 2025
ReAL-AD

ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving

Yuhang Lu, Jiadong Tu, Xinge Zhu, Yuexin Ma

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025

[Paper]

ICRA 2025
RenderWorld

RenderWorld: World Model with Self-Supervised 3D Label

Ziyang Yan, Wenzhen Dong, Yihua Shao, Yuhang Lu, Liu Haiyang, Jingwen Liu, Haozhe Wang, Zhe Wang, Yan Wang, Fabio Remondino, Yuexin Ma

2025 IEEE International Conference on Robotics and Automation (ICRA 2025)

[Paper]

AAAI 2025
IDKB

Can LVLMs Obtain a Driver’s License? A Benchmark Towards Reliable AGI for Autonomous Driving

Yuhang Lu*, Yichen Yao*, Jiadong Tu*, Jiangnan Shao*, Yuexin Ma, Xinge Zhu

Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25)

[Project Page] [Paper]

NeurIPS 2024
OctreeOcc

OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries

Yuhang Lu, Xinge Zhu, Tai Wang, Yuexin Ma

Conference on Neural Information Processing Systems (NeurIPS), 2024

[Paper] [Code]

ICCV 2023
SeeMore

See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data

Yuhang Lu*, Qi Jiang*, Runnan Chen, Yuenan Hou, Xinge Zhu, Yuexin Ma

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023

[Paper] [Code]

💻 Work Experience

Shanghai Artificial Intelligence Laboratory

June 2025 - Present

Position: Research Intern (Supervisor: Li Chen)

Location: Shanghai, China

ShanghaiTech University

August 2022 - April 2025

Position: Research Assistant (Supervisor: Yuexin Ma)

Location: Shanghai, China

📖 Education

  • The University of Hong Kong (HKU)
    • Ph.D., Musketeers Foundation Institute of Data Science
    • October 2025 – Present
  • Beijing University of Posts and Telecommunications (BUPT)
    • B.E., Internet of Things Engineering
    • September 2018 – July 2022
  • Queen Mary University of London (QMUL)
    • B.E., Internet of Things Engineering (First-class degree)
    • September 2018 – July 2022

🌟 Miscellaneous

Academic Services

I served as a reviewer for top-tier conference such as ICCV, NeurIPS, AAAI …

Hobbies

Love: 🎱Billiards (Chinese 8 ball and Snooker), 🏀basketball and 🏃jogging