Hao Lu

I am a third-year Ph.D. student at The Hong Kong University of Science and Technology (Guangzhou campus), supervised by Dr. Yingcong Chen. Before that, I received the joint M.S. degree with the University and Chinese Academy of Sciences (UCAS), and the Institute of Computing Technology (ICT), Chinese Academy of Sciences under the supervision of Prof. Dr. Hu Han and Dr. S. Kevin Zhou in 2022. I also had the privilege of working closely with Dr. Shiguang Shan and Dr. Xilin Chen.

I am generally interested in artificial intelligence and deep learning. My current research focuses on:

🦙 Multimodal Large Model
🛠️ 4D Reconstruction and Generation
🚗 Autonomous Driving
🔬 AI for Science

Email / Google Scholar

Internship Experience

ByteDance Seed June 2025 -- Present

Research Intern
Topic: Unified Generation, Understanding, and Action of Multimodal Large Models.

University of California, Berkeley May 2024 -- May 2025

Research Intern
Topic: 4D Scene Reconstruction and Dynamic Generation.
Advisors: Wenzhao Zheng, Wei Zhan, Kurt Keutzer and Masayoshi Tomizuka.

Phigent Robotics Dec. 2022 -- May 2024

Research Intern
Topic: Generalization and Scalability of BEV Perception.
Advisor: Dr. Yunpeng Zhang, Dr. Zheng Zhu, and Dr. Dalong Du.

Selected Papers [Full List]

UniUGP: Unifying Understanding, Generation, and Planning For End-to-end Autonomous Driving.
Hao Lu*, Ziyang Liu*, Guangfeng Jiang, Yuanfei Luo, et al.
arXiv:2512.09864
[Paper] [Homepage]

4D Driving Scene Generation With Stereo Forcing.
Hao Lu*, Zhuang Ma*, Guangfeng Jiang, Wenhang Ge, et al.
arXiv:2509.20251
[Paper] [Homepage]

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving.
Hao Lu, Tianshuo Xu, Wenzhao Zheng, Yunpeng Zhang, et al.
NeurIPS 2025
[Paper] [Code]

Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model.
Yuting Zhang*, Hao Lu*, Qingyong Hu, Yin Wang, et al.
CVPR 2025
[Paper] [Code]

Hawk: Learning to Understand Open-World Video Anomalies.
Jiaqi Tang*, Hao Lu*, Ruizheng Wu, Xiaogang Xu, et al.
NeurIPS 2024
[Paper] [Code]

Occ-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models.
Tianshuo Xu, Hao Lu, XU Yan, Yingjie Cai, et al.
ICRA 2025
[Paper] [Code]

Sage Deer: A Super-Aligned Driving Generalist Is Your Cockpit.
Hao Lu*, Jiaqi Tang*, Jiyao Wang, Yunfan Lu, et al.
Preprint

Towards Generalizable Multi-Camera 3D Object Detection via Perspective Debiasing.
Hao Lu, Yunpeng Zhang, Qing Lian, Dalong Du, et al.
AAAI 2024
[Paper] [Code]

Scaling Multi-Camera 3D Object Detection through Weak-to-Strong Eliciting.
Hao Lu, Jiaqi Tang, Xinli Xu, Xu Cao, et al.
Preprint
[Paper] [Code]

GPT as Psychologist? Preliminary Evaluations for GPT-4V on Visual Affective Computing.
Hao Lu*, Xuesong Niu*, Jiyao Wang*, Yin Wang*, Qingyong Hu* et al.
CVPR Workshops 2024
[Paper] [Code]

Neuron Structure Modeling for Generalizable Remote Physiological Measurement.
Hao Lu, Zitong Yu, Xuesong Niu, Yingcong Chen.
CVPR 2023
[Paper] [Code]

Dual-GAN: Joint BVP and Noise modelling for Remote Physiological Measurement.
Hao Lu, Hu Han, S. Kevin Zhou.
CVPR 2021
[Paper]

*Equal contribution.

Honors and Awards

The 1st Place in RoboDrive, IEEE Conference on Robotics and Automation (ICRA2024)
The first prize in China (0.2%), The Chinese Mathematics Competitions (CMC2016)

Website Template