Mo Xu

Ph.D. Student in Computer Sciences, University of Wisconsin–Madison

prof_pic.jpg

I am a Ph.D. student in Computer Sciences at the University of Wisconsin–Madison, co-advised by Bilge Mutlu and Josiah Hanna. I received my Master’s degree in Electrical and Computer Engineering from the University of Michigan–Ann Arbor (2022–2023), advised by Christoforos Mavrogiannis.

My research focuses on Embodied AI and Robot Learning, with an emphasis on dexterous manipulation, sim-to-real transfer, vision-language-action and world models. I am particularly interested in enabling robots to perform complex physical tasks in unstructured real-world environments.

I am currently open to research internship opportunities. My resume is available here.

news

September 2026 Grasp2Twist accepted to the IROS 2026 Workshop on Enhancing Dexterous Manipulation Through Haptic Feedback.
May 2026 Paper accepted by RA-L.

selected publications

  1. arXiv
    Grasp2Twist: Learning Bimanual Dexterous Jar Opening by Reinforcement Learning
    Mo Xu, Yunfu Deng, Jianuo Wang, and 2 more authors
    arXiv preprint arXiv:2609.32064, 2026
  2. RA-L
    Toward Real-time High-fidelity Immersive Robotic Telepresence via Online 3D Gaussian Splatting
    Jingxin Du, Mo Xu, Yaxin Hu, and 3 more authors
    IEEE Robotics and Automation Letters, 2026