Yuhang Lu 陆宇航

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

Physical AI, especially humanoid robotics and autonomous driving.
Humanoid robot foundation models with transferability, compositionality, and contact awareness.
3D understanding under distribution shift, limited supervision, and long-tail scenarios.

Email CV Google Scholar GitHub

News

Feb 2026
DriveCombo was accepted by CVPR 2026.
Oct 2025
Started my Ph.D. at HKU MMLab.
Jun 2025
ReAL-AD was accepted by ICCV 2025.
Dec 2024
IDKB was accepted by AAAI 2025.
Sep 2024
OctreeOcc was accepted by NeurIPS 2024.
Sep 2024
Introduced IDKB, a large-scale vision-language benchmark for professional driving knowledge.

Selected Publications

* indicates equal contribution.

arXiv 2026 · Co-author

World Engine: Towards the Era of Post-Training for Physical AI

Tianyu Li*, Li Chen*, Caojun Wang*, Haochen Liu*, Kashyap Chitta, Yuhang Lu, Naisheng Ye, Yufei Wang, Jiaxin Peng, Jin Pan, Zhaoyu Su, Andrei Bursuc, Shengbo Eben Li, Andreas Geiger, Honglin Bian, Hongyang Li*, Peng Su

arXiv preprint, 2026

Project Page Code

CVPR 2026 · Co-author

DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving

Enhui Ma*, Jiahuan Zhang*, Guantian Zheng, Tao Tang, Shengbo Eben Li, Yuhang Lu, Xia Zhou, Xueyang Zhang, Yifei Zhan, Kun Zhan, Zhihui Hao, Xianpeng Lang, Kaicheng Yu

Conference on Computer Vision and Pattern Recognition 2026

Paper

ICCV 2025 · First author

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

Project Page

ICRA 2025 · Co-author

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 · Co-first author

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 Dataset

NeurIPS 2024 · First author

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 · Co-first author

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

Experience

April 2026 - Present

Booster Robotics · Beijing, China

Research Intern · Supervised by Chaoyi Li.

January 2026 - April 2026

Huawei Technologies Co., Ltd. · Shenzhen, China

Research Intern · Supervised by Peng Su.

June 2025 - September 2025

Shanghai Artificial Intelligence Laboratory · Shanghai, China

Research Intern · Supervised by Li Chen.

August 2022 - April 2025

ShanghaiTech University · Shanghai, China

Research Assistant · Supervised by Yuexin Ma.

Education

October 2025 - Present

The University of Hong Kong

Ph.D., School of Computing and Data Science

September 2018 - July 2022

Beijing University of Posts and Telecommunications & Queen Mary University of London

Joint B.E. Program in Internet of Things Engineering (First-class honours)

Miscellaneous

Academic Service

I serve as a reviewer for CVPR, ICCV, ECCV, NeurIPS, AAAI, ICRA, and related venues.

Beyond Research

Outside research, I enjoy billiards and jogging.

Contact

I am always happy to connect about Physical AI, humanoid robot, 3D vision, and related research collaborations. Feel free to reach out to me via email.

lu.yuhang@connect.hku.hk