About me
I am currently a Research Assistant at 4DVLab of ShanghaiTech University, supervised by Prof. Yuexin Ma. I am also fortunate to work closely with Dr. Xinge Zhu. Prior to joining 4DVLab, I obtained my bachelor’s degree from the joint program between Beijing University of Posts and Telecommunications and Queen Mary University of London, graduating with first-class honors.
My research aims to empower AI to comprehend the 3D world with human-like perception, by developing 3D understanding algorithms that are annotation-efficient, highly generalizable, and interpretable. Recently, I focus on leveraging vision-language models (VLMs) to improve the performance and generalization of autonomous driving algorithms.
You can find my CV here: Yuhang Lu’s Curriculum Vitae
🔥 News
- 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.
- 2024.05: We propose OctreeOcc, a highly efficient, multi-granularity method for occupancy prediction.
- 2023.07: Excited to share that my first paper SeeMore, has been accepted by ICCV 2023!
- 2022.08: Thrilled to join 4DVLab as a Research Assistant.
📝 Publications
* indicates equal contributions
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
Arxiv preprint
📖 Educations
Beijing University of Posts and Telecommunications (BUPT)
September 2018 - July 2022
Major: B.E. in Internet of Things Engineering
Queen Mary University of London (QMUL)
September 2018 - July 2022
Major: B.E. in Internet of Things Engineering (first-class degree)
Miscellaneous
Hobbies
Love: 🏀Basketball, 🎱billiards and 🏃jogging