Attended ICRA 2026 on-site.
Hong Kong SAR / Shanghai, China
BangjunWang
CS PhD student at The University of Hong Kong working on embodied AI, robotic manipulation, and foundation models.
01About
About
Hi, I am a first-year Ph.D. student at HKU MMLab, co-advised by Prof. Hongyang Li and Prof. Yi Ma. I received my Bachelor's degree from AI (Guozhi) Class (held by Prof. Xiaoou Tang and Prof. Cewu Lu), Shanghai Jiao Tong University (SJTU). Previously, I was a visiting scholar at the University of Southern California (USC), advised by Prof. Yue Wang, and the National University of Singapore (NUS), advised by Prof. Lin Shao. I also worked with Prof. Hao Dong and Prof. Junchi Yan before during my undergraduate years. My research focuses on Embodied AI, Robotic Manipulation, and Foundation Models. Feel free to contact me if you are interested in my research or would like to collaborate on any related topics!02Latest
Latest
Starting my PhD at HKU MMLab, co-advised by Prof. Hongyang Li and Prof. Yi Ma.
RoboVerse was accepted by RSS 2025, and the code has been released.
Actively applying for a 2025/2026 PhD position.
Serving as a reviewer for CVPR 2025 and ICML 2025.
Visiting student at USC, supervised by Prof. Yue Wang.
03Focus
Research with an eye on physical generalization.
01
Embodied AI
Learning systems that connect perception, action, and world understanding for physical agents.
02
Robotic manipulation
Generalizable manipulation policies, benchmarks, and datasets for scalable robot learning.
03
Foundation models
Vision-language-action and generative world action models for zero-shot physical reasoning.
04Publications
Selected work
01
Goal-VLA: Image-Generative VLMs as Object-Centric World Models Enable Zero-Shot Robot Manipulation
Haonan Chen*, Jingxiang Guo* , Bangjun Wang, Tianrui Zhang , Xuchuan Huang , Boren Zheng , Yiwen Hou , Chenrui Tie , Jiajun Deng , Lin Shao
IEEE International Conference on Robotics & Automation (ICRA) 2026
.jpg&w=3840&q=75)
02
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
Haoran Geng*, Feishi Wang*, Songlin Wei*, Yuyang Li*, Bangjun Wang*, Boshi An*, Charlie Tianyue Cheng*, Haozhe Lou, Peihao Li, Yen-Jen Wang, Yutong Liang, Dylan Goetting, Chaoyi Xu, Haozhe Chen, Yuxi Qian, Yiran Geng, Jiageng Mao, Weikang Wan, Mingtong Zhang, Jiangran Lyu, Siheng Zhao, Jiazhao Zhang, Jialiang Zhang, Chengyang Zhao, Haoran Lu, Yufei Ding, Ran Gong, Yuran Wang, Yuxuan Kuang, Ruihai Wu, Baoxiong Jia, Carlo Sferrazza, Hao Dong, Siyuan Huang, Koushil Sreenath, Yue Wang†, Jitendra Malik†, Pieter Abbeel† (Co-first author among 38 authors)
Robotics: Science and Systems (RSS) 2025
Oral PresentationEditor's Pick
03
Learning Manipulation by Predicting Interaction
Jia Zeng*, Qingwen Bu*, Bangjun Wang*, Wenke Xia*, Li Chen, Hao Dong, Haoming Song, Dong Wang, Di Hu, Ping Luo, Heming Cui, Bin Zhao, Xuelong Li, Yu Qiao, Hongyang Li
Robotics: Science and Systems (RSS) 2024
Oral PresentationEditor's Pick
04
LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving
Tianyu Li*, Peijin Jia*, Bangjun Wang*, Li Chen, Kun Jiang, Junchi Yan, Hongyang Li
Internationl Conference on Learning Representation (ICLR) 2024
05
OpenLane-V2: A Topology Reasoning Benchmark for Scene Understanding in Autonomous Driving
Huijie Wang, Tianyu Li, Yang Li, Li Chen, Chonghao Sima, Zhenbo Liu, Bangjun Wang, Peijin Jia, Yuting Wang, Shengyin Jiang, Feng Wen, Hang Xu, Ping Luo, Junchi Yan, Wei Zhang, Hongyang Li
Conference on Neural Information Processing Systems (NeurIPS) 2023
06
World4Omni: A Zero-Shot Framework from Image Generation World Model to Robotic Manipulation
Haonan Chen*, Bangjun Wang*, Jingxiang Guo*, Tianrui Zhang, Yiwen Hou, Xuchuan Huang, Chenrui Tie, Lin Shao
ICML 2025 Physical World Modeling Workshop
05Timeline
Visiting experience
2025.04 - 2025.09
National University of Singapore (NUS)
Visiting Scholar; Advisor/Supervisor: Prof. Lin Shao
- A Zero-Shot Framework from Image Generation World Model to Robotic Manipulation
2024.08 - 2025.07
University of Southern California (USC)
Visiting Scholar; Advisor/Supervisor: Prof. Yue Wang
- A Unified Benchmark for Scalable and Generalizable Vision-Language Robotic Manipulation
2024.03 - 2024.08
PKU-AGIBOT Lab, Peking University (PKU) & AGIBOT
Research Intern; Advisor/Supervisor: Prof. Hao Dong and Dr. Maoqing Yao
- Vision-Language-Action(VLA) Framework, Humanoid Bimanual Manipulation
2023.03 - 2024.06
OpenDriveLab, Shanghai AI Lab & The University of Hong Kong (HKU)
Research Intern; Advisor/Supervisor: Prof. Hongyang Li
- Embodied AI, Representation Learning for Robotic Manipulation
- Structural Understanding for Driving Scenes
2022.09 - 2023.03
ReThinkLab, Shanghai Jiao Tong University (SJTU)
Research Undergraduate; Advisor/Supervisor: Prof. Junchi Yan
- Image Retrieval, Image Matching
06Education
Education
2025 - Present
2021 - 2025
B.Eng. in Artificial Intelligence
Shanghai Jiao Tong University
Summa Cum Laude, Guozhi Class. Advisor: Prof. Cewu Lu and Prof. Xiaoou Tang
2024 - 2025
07Service
Academic service
Reviewer
- Robotics: Science and Systems (RSS), 2026
- Conference on Computer Vision and Pattern Recognition (CVPR), 2024, 2025, 2026
- International Conference on Computer Vision (ICCV), 2025
- Conference on Neural Information Processing Systems (NeurIPS), 2024, 2025, 2026
- International Conference on Machine Learning (ICML), 2025, 2026
- International Conference on Learning Representations (ICLR), 2025, 2026
- Conference on Robot Learning (CoRL), 2026
- International Conference on Robotics and Automation (ICRA), 2026
- AAAI Conference on Artificial Intelligence (AAAI), 2025, 2026
- ACM Multimedia (ACMMM), 2024
- International Conference on Artificial Intelligence and Statistics (AISTATS), 2025, 2026
Workshop Co-organizer
School Roles
- Class Leader of Guozhi Class, 2021 - 2025
08Misc
Outside the lab
Music
Classical, jazz, blues, and R&B; especially Mahler, Rachmaninoff, Wagner, and the late Romantic repertoire.
Sports
Tennis and Golf. I enjoy the blend of physicality, strategy, and mental focus in these sports.
Art and design
Learning graphic design and digital art systematically alongside research work.