- Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models (arXiv)
- Awards:
- First Place in End-to-End Driving at Scale, Second Place in Driving with Language, CVPR 2024 Autonomous Driving Grand Challenge
- Projects:
- StreamPETR (ICCV’23), a streaming paradigm for camera-based 3D perception that reached #1 among online methods on nuScenes and has been widely adopted in both academia and industry
Research Experience
- Work Experience:
- Joined NVIDIA AV Applied Research Group as a Research Intern in October 2023
- Joined MEGVII Technology Foundation Model Group as a Research Intern in October 2022
- OmniDrive and Hydra-MDP, connecting 3D perception with multimodal reasoning for end-to-end autonomous driving
Education
- Degree: Ph.D. Student
- School: The Hong Kong Polytechnic University
- Advisor: Prof. Lei Zhang
- Time: Currently enrolled
- Major: Computing
Background
- Research Interests: 3D perception and planning, multimodal foundation models, streaming video understanding, test-time adaptation, etc.
- Professional Field: Department of Computing, particularly in autonomous driving and robotics
- Introduction: A second-year Ph.D. student in the Department of Computing at The Hong Kong Polytechnic University, advised by Prof. Lei Zhang. Closely collaborates with NVIDIA Research.