About Me
I am a 4th-year Ph.D. candidate at Huazhong University of Science and Technology, where I am fortunate to be advised by Prof. Xinggang Wang and Prof. Wenyu Liu. Currently, I am an intern at ByteDance Seed, working on VLA models for physical AI. I also interned at Horizon Robotics, where I was advised by Dr. Qian Zhang, and at Applied Intuition, where I worked under the guidance of Chief Scientist Dr. Wei Zhan.
My research focuses on visual representation learning for physical AI. I am especially interested in end-to-end driving systems, large vision-language-action models, video-based world models, and spatial intelligence that can connect perception, reasoning, and action.
News
- 2026.05, We released LaMo, a self-supervised latent motion prior for physically realistic video generation.
- 2026.01, VADv2 was accepted by ICLR 2026 🎉.
- 2025.09, RAD was accepted by NeurIPS 2025 🎉.
- 2025.02, DiffusionDrive was accepted by CVPR 2025 Highlight 🎉.
- 2023.07, VAD was accepted by ICCV 2023 🎉.
Publications
Recent Highlights
LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation
Bo Jiang, Depu Meng, Yihan Hu, Yichen Xie, Tianshuo Xu, Wei Zhan
arXiv preprint, 2026
- A self-supervised latent motion prior for improving the physical realism of video generation models across physical and general video benchmarks.
VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning
Bo Jiang*, Shaoyu Chen*, Hao Gao, Bencheng Liao, Qian Zhang, Wenyu Liu, Xinggang Wang
International Conference on Learning Representations (ICLR), 2026
- An multi-modal end-to-end driving framework that introduces probabilistic planning to handle uncertainty problem in autonomous driving.
DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving
Bencheng Liao, Shaoyu Chen, Haoran Yin, Bo Jiang, Cheng Wang, Siyu Yan, Xinbang Zhang, Xiangyu Li, Ying Zhang, Qian Zhang, Xinggang Wang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
- A diffusion-based formulation for end-to-end autonomous driving that uses truncated denoising to improve planning quality and inference practicality.
Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving
Bo Jiang, Shaoyu Chen, Bencheng Liao, Xingyu Zhang, Wei Yin, Qian Zhang, Chang Huang, Wenyu Liu, Xinggang Wang
arXiv preprint, 2024
- A dual-system autonomous driving VLA model that connects high-level decision-making with low-level end-to-end planning.
VAD: Vectorized Scene Representation for Efficient Autonomous Driving
Bo Jiang*, Shaoyu Chen*, Qing Xu, Botian Liao, Jiacheng Chen, Hao Zhou, Qian Zhang, Wenyu Liu, Chang Huang, Xinggang Wang
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
- A vectorized scene representation for end-to-end autonomous driving, enhancing inference efficiency without compromising planning accuracy.
Other Publications
-
RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning, Hao Gao, Shaoyu Chen, Bo Jiang, Bencheng Liao, Yiang Shi, Xiaoyang Guo, Yuechuan Pu, Haoran Yin, Xiangyu Li, Xinbang Zhang, Ying Zhang, Wenyu Liu, Qian Zhang, Xinggang Wang, Advances in Neural Information Processing Systems (NeurIPS), 2025
-
AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning, Bo Jiang, Shaoyu Chen, Qian Zhang, Wenyu Liu, Xinggang Wang
-
MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction, Bencheng Liao, Shaoyu Chen, Yunchi Zhang, Bo Jiang, Qian Zhang, Wenyu Liu, Chang Huang, Xinggang Wang, International Journal of Computer Vision (IJCV), 2024
-
Lane Graph as Path: Continuity-Preserving Path-Wise Modeling for Online Lane Graph Construction, Bencheng Liao*, Shaoyu Chen*, Bo Jiang, Tianheng Cheng, Qian Zhang, Wenyu Liu, Chang Huang, Xinggang Wang, European Conference on Computer Vision (ECCV), 2024
-
HOPE: Hierarchical Spatial-Temporal Network for Occupancy Flow Prediction, Yihan Hu, Wenxin Shao, Bo Jiang, Jiajie Chen, Siqi Chai, Zhening Yang, Jingyu Qian, Helong Zhou, Qiang Liu, CVPR 2022 Workshop on Autonomous Driving
Invited Talks
- 2025.10, Advancing E2E-AD via Multimodal Planning, Reinforced Fine-Tuning, and Language Modality Integration, IROS 2026 Autonomous Driving Workshop, Hangzhou, China.
- 2025.04, Closed-Loop Reinforcement Learning for On-Policy Autonomous Driving, China Generative AI Conference, Beijing, China.
- 2025.01, Rethinking Vision-Language-Action Models for End-to-end Autonomous Driving, the 4th Global Autonomous Driving Summit, Beijing, China.
Honors and Awards
- 2023, National First Prize, the 8th China International “Internet+” College Students Innovation and Entrepreneurship Competition
- 2023, First-Class Ph.D. Scholarship, Huazhong University of Science and Technology
- 2023, Outstanding Student, Huazhong University of Science and Technology
- 2022, 1st Place Winner, Google Waymo Open Dataset Challenge, Occupancy Flow Prediction Track
- 2021, Outstanding Graduate, Central South University
Educations
- 2023.09 - 2027.06, Ph.D. in Information and Communication Engineering, Huazhong University of Science and Technology, Wuhan, China
- 2021.09 - 2023.06, M.S. in Information and Communication Engineering, Huazhong University of Science and Technology, Wuhan, China
- 2017.09 - 2021.06, B.Sc. in Data Science and Big Data Technology, Central South University, Changsha, China
Internships
- 2026.06 - Present, Multimodal Interaction Research Intern, ByteDance Seed, Beijing, China.
- 2026.01 - 2026.06, World Model Research Intern, Applied Intuition, Sunnyvale, CA, U.S.
- 2021.05 - 2026.01, Autonomous Driving Algorithm Research Intern, Horizon Robotics, Beijing, China.