Mingdong Wu | 吴铭东

A third-year Ph.D. student in Peking University (PKU).

wmd_23_10.jpg

I am a final year Ph.D. student in the School of Computer Science at PKU, advised by Prof. Hao Dong. I received my bachelor degree in 2021, from Turing Class in PKU. Currently, I am excited to be working with Jianlan Luo at AgiBot on some challenging problems. My recent research focuses on real world reinforcement learning algorithms and robotic systems with tactile sensing, building future data-flying-wheel applications.

news

Jul 8, 2024 One paper gets accepted to RAL 2024 🎉
Jul 1, 2024 One paper gets accepted to ECCV 2024 🎉
Sep 11, 2023 One paper gets accepted to SIGGRAPH Asia 2023 🎉
Sep 12, 2023 One paper gets accepted to BMVC 2023 (Oral) 🎉
Sep 22, 2023 Three paper gets accepted to NeurIPS 2023 🎉
Apr 18, 2023 One paper gets accepted to RAL 2023 🎉
Feb 28, 2023 One paper gets accepted to CVPR 2023 🎉
Sep 16, 2022 One paper gets accepted to NeurIPS 2022 🎉

Selected Publications

(*) indicates equal contribution [Full List]

2025

  1. IROS 2025
    SimLauncher: Launching Sample-Efficient Real-world Robotic Reinforcement Learning via Simulation Pre-training
    Mingdong Wu*, Lehong Wu*, Yizhuo Wu*, Weiyao Huang, Hongwei Fan, Zheyuan Hu, Haoran Geng, Jinzhou Li, Jiahe Ying, Long Yang, and  others
    IEEE/RSJ International Conference on Intelligent Robots and Systems, 2025
  2. CoRL 2025
    UniTac2Pose: A Unified Approach Learned in Simulation for Generalizable Visuotactile In-hand Pose Estimation
    Mingdong Wu*, Long Yan*, Jin Liu*, Weiyao Huang, Lehong Wu, Zelin Chen, Daolin Ma, and Hao Dong
    Conference on Robot Learning, 2025
  3. IROS 2025
    Adaptive Visuo-Tactile Fusion with Predictive Force Attention for Dexterous Manipulation
    Jinzhou Li*, Tianhao Wu*Jiyao Zhang, Zeyuan Chen, Haotian Jin, Mingdong Wu, Yujun Shen, Yaodong Yang, and Hao Dong
    IEEE/RSJ International Conference on Intelligent Robots and Systems, 2025
  4. ICRA 2025
    Canonical representation and force-based pretraining of 3d tactile for dexterous visuo-tactile policy learning
    Tianhao Wu, Jinzhou Li*, Jiyao Zhang*Mingdong Wu, and Hao Dong
    IEEE International Conference on Robotics and Automation, 2025

2024

  1. ECCV 2024
    Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking
    Jiyao Zhang*, Weiyao Huang*, Bo Peng*, Mingdong Wu, Fei Hu, Zijian Chen, Bo Zhao, and Hao Dong
    European Conference on Computer Vision, 2024
  2. RAL 2024
    Distilling Functional Rearrangement Priors from Large Models
    Yiming Zeng*, Mingdong Wu*, Long Yang, Jiyao Zhang, Hao Ding, Hui Cheng, and Hao Dong
    IEEE Robotics and Automation Letters, 2024

2023

  1. NeurIPS 2023
    GenPose: Generative Category-level Object Pose Estimation via Diffusion Models
    Jiyao Zhang*Mingdong Wu*, and Hao Dong
    Thirty-seventh Conference on Neural Information Processing Systems, 2023
  2. NeurIPS 2023
    Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping
    Tianhao Wu*Mingdong Wu*Jiyao ZhangYunchong Gan, and Hao Dong
    Thirty-seventh Conference on Neural Information Processing Systems, 2023

2022

  1. NeurIPS 2022
    TarGF: Learning Target Gradient Field to Rearrange Objects without Explicit Goal Specification
    Mingdong Wu*Fangwei Zhong*, Yulong Xia, and Hao Dong
    Advances in Neural Information Processing Systems, 2022