Jason Gan

About Me

I am a final-year undergraduate student at The Hong Kong University of Science and Technology, studying Computer Engineering with a minor in Robotics. My research is in embodied AI — building models that let robots understand the world well enough to act in it.

I am currently a Research Intern at Sangfor Technologies, supervised by Prof. Xiaobo Wang. I have spent three years with HKUST RoboMaster Team ENTERPRIZE, where I now serve as Senior Advisor.

I am looking for PhD opportunities. If you are interested in my research, please feel free to reach out.

Research Interests

Embodied AI Vision-Language-Action Models World Models Robot Manipulation Embedded Systems

News

  • Sep 2026

    Our preprint AR-WAM: A Visual-Conditioned Agent-Ready World Action Model for Robotic Manipulation is now available on arXiv.

  • May 2026

    Our paper MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation was accepted to ICML 2026.

  • Jan 2026

    Our paper Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation was accepted to ICRA 2026.

Selected Publications

All publications →

* Equal contribution.

Experience

Selected Awards

  • 2025/26, 2024/25
    Talent Development Scholarship

    HKSAR Government Scholarship Fund

  • 2025
    Champion, RoboMaster University League

    Zhejiang Regional Competition, 3V3 · Results ↗

  • 2025
    Outstanding Captain, RoboMaster 2025

    Results ↗ · Invited share (CN) ↗