Jingbo Wang/ 王靖博
wangjingbo@pjlab.org.cn

Jingbo Wang

I lead the research team on humanoid robot learning at the Embodied AI Center of Shanghai AI Lab. Our research aims to empower humanoid robots with the ability to acquire versatile skills and autonomously adapt to complex environments, leveraging prior knowledge demonstrated by humans in their daily lives. Previously, I conducted research in areas including character animation and simulation, efficient perception models—such as BiSeNet V1 and V2—and 3D reconstruction.

News
  • Our team is hiring! We are looking for talented full time researchers, reserch engineers and self-motivated interns to join us. If you have a strong background in following topics, please feel free to reach out to me.
    • Humanoid Locomotion, Whole Body Control, Motion Tracking, Humanoid-Scene Interactions, Loco-Manipulation
    • Behavior Foundation Model on Manipulation and Whole Body Control
    • Character Animation, Motion Generation and Planning, Motion Retargeting
    • Reinforcement learning, Efficient Generative Model, MLLM
    • Real-time Perception and its Deployment

Recent Research Interests ( Full List in Google Scholar)

Liang Pan, Zeshi Yang, Zhiyang Dou, Wenjia Wang, Buzhen Huang, Bo Dai, Taku Komura, Jingbo Wang TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025
[Project] [Paper]
Shunlin Lu, Jingbo Wang, Zeyu Lu, Ling-Hao Chen, Wenxun Dai, Junting Dong, Zhiyang Dou, Bo Dai, Ruimao Zhang
ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025
[Project] [Paper]
Jiawei Gao*, Ziqin Wang*, Zeqi Xiao, Jingbo Wang, Tai Wang, Jinkun Cao, Xiaolin Hu†, Si Liu, Jifeng Dai, Jiangmiao Pang ('*' donats equal contribution.)
CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics
Conference on Neural Information Processing Systems (NeurIPS), 2024
[Project] [Paper]
Jingbo Wang*, Zhengyi Luo*, Ye Yuan, Yixuan Li, Bo Dai ('*' donats equal contribution.)
PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[Project] [Paper] [Video]
Yi Shi, Jingbo Wang, Xuekun Jiang, Bingkun Lin, Bo Dai, Xue Bin Peng
Interactive Character Control with Auto-Regressive Motion Diffusion Models
ACM Transactions on Graphics (Proc. SIGGRAPH 2024), 2024
[Paper] [Project]
Zeqi Xiao, Tai Wang, Jingbo Wang, Jinkun Cao, Wenwei Zhang, Bo Dai, Dahua Lin, Jiangmiao Pang
Unified Human-Scene Interaction via Prompted Chain-of-Contacts
The International Conference on Learning Representations (ICLR), 2024
[Paper] [Project]
Jingbo Wang, Ye Yuan, Zhengyi Luo, Kevin Xie, Dahua Lin, Umar Iqbal, Sanja Fidler, Sameh Khamis
Learning Human Dynamics in Autonomous Driving Scenarios
IEEE International Conference on Computer Vision (ICCV), 2023
[Paper] [Video]

Education

  • [2020.08-2023.08]   Ph.D student at MMLab, IE Department, The Chinese University of Hong Kong.
  • [2016.09-2019.07]   Key Laboratory of Machine Perception (MOE), School of EECS, Peking University.
  • [2012.09-2016.07]   Beijing Institute of Technology, School of Mathematics and Statistics.

Experiences

  • [2022.05-2023.06]   Research Intern at Nvidia Toronto AI Lab. Supervised by Dr Ye Yuan, Dr Sameh Khamis, and Prof. Sanja Filder.
  • [2022.01-2022.05]   Research Intern at Shanghai AI Lab. Supervised by Dr. Bo Dai.
  • [2020.01-2021.12]   Research Intern at SenseTime Research. Supervised by Dr. Ding Liang.
  • [2019.08-2020.07]   Research Assistant at MMLAB, CUHK. Supervised by Prof. Dahua Lin.
  • [2017.06-2018.12]   Research Intern at Megvii Research. Supervise by Dr, Gang Yu.

Academic Competition

  • Winner of COCO 2018 Challenge in Panoptic Segmentation Track
  • Winner of Mapillary 2018 Challenge in Panoptic Segmentation Track