Lehong Wu

EECS, Peking University

my_photo1.jpg

I am a 4th-year undergraduate from EECS, Peking University.

I am a visiting research student at CMU AIRe Lab, advised by Prof. Aviral Kumar. At Peking University, I conduct research at PKU-Agibot Lab, advised by Prof. Hao Dong. Before that, I was fortunate to work at STRUCT, advised by Prof. Jiaying Liu.

My research interest lies in robot learning, with a focus on robotic reinforcement learning and manipulation currently. I aim to build autonomous and scalable robot learning systems in the real world.

Contact me: Email / Github / WeChat

News

Aug 09, 2025 🎉 One paper gets accepted by CoRL 2025.
Jun 16, 2025 🎉 One paper gets accepted by IROS 2025 as oral presentation.
Jul 01, 2024 🎉 Two papers get accepted by ECCV 2024.

Selected Publications

  1. IROS 2025
    simlauncher-preview-v3.png
    SimLauncher: Launching Sample-Efficient Real-world Robotic Reinforcement Learning via Simulation Pre-training
    Mingdong Wu*Lehong Wu*, Yizhuo Wu*, and 9 more authors
    In International Conference on Intelligent Robots and Systems (IROS), Oral Presentation, 2025
  2. CoRL 2025
    unitac2pose-preview.png
    UniTac2Pose: A Unified Approach Learned in Simulation for Generalizable Visuotactile In-hand Pose Estimation
    Mingdong Wu*, Long Yang*, Jin Liu, and 5 more authors
    In Conference on Robot Learning (CoRL), 2025
  3. ECCV 2024
    macdiff-preview.jpg
    MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion
    Lehong Wu, Lilang Lin, Jiahang Zhang, and 2 more authors
    In European Conference on Computer Vision (ECCV), 2024
  4. ECCV 2024
    igm-preview.png
    Idempotent Unsupervised Representation Learning for Skeleton-Based Action Recognition
    Lilang Lin, Lehong Wu, Jiahang Zhang, and 1 more author
    In European Conference on Computer Vision (ECCV), 2024