Feiyang Wu(邬飞扬) ☕️
Feiyang Wu(邬飞扬)

Master’s Student in Computational Science & Engineering

About Me

Feiyang Wu is a Master’s student in Computational Science and Engineering at Harvard University. He received his undergraduate degrees through the dual-degree program of the ZJU-UIUC Institute, holding a B.S. in Computer Engineering from the University of Illinois Urbana-Champaign (High Honors) and a B.Eng. in Electronic and Computer Engineering from Zhejiang University.

His research focuses on embodied artificial intelligence — vision-language-action models, world models and imitation learning — and how these methods transfer to real robotic manipulation, particularly in contact-rich settings.

Download CV
Interests
  • Vision-Language-Action Models
  • Large Language Models
  • World Models & Generative Models
  • Imitation & Reinforcement Learning
  • Robotics & Control
  • Embedded Systems
Education
  • ME Computational Science and Engineering

    Harvard University

  • BS Computer Engineering

    University of Illinois Urbana-Champaign

  • BEng Electronic and Computer Engineering

    Zhejiang University

📚 My Research

I’m a master’s student in Computational Science and Engineering at Harvard University. My research focuses on embodied artificial intelligence — vision-language-action models, world models and imitation learning — and how these methods transfer to real robotic manipulation, especially in contact-rich settings.

I received my undergraduate degrees through the dual-degree program of the ZJU-UIUC Institute: a B.S. in Computer Engineering from the University of Illinois Urbana-Champaign (High Honors) and a B.Eng. in Electronic and Computer Engineering from Zhejiang University.

Please reach out to collaborate! 😃

Featured Publications
Recent Publications
(2026). Robot Learning with Visual Predicted Force. Under review, ICRA 2027.
(2026). CoStream: Composing Simple Behaviors for Generalizable Complex Manipulation. arXiv:2606.26423.
(2024). MovieChat: From Dense Token to Sparse Memory for Long Video Understanding. In CVPR 2024.