Han Yang (杨涵)

I am a second-year PhD student at University of Massachusetts Amherst (UMass Amherst), advised by Prof. Chuang Gan. I received my bachelor’s degree in Computer Science with first-class honors from The Chinese University of Hong Kong (CUHK). Before starting my PhD, I worked on embodied AI, multimodal learning, and generative models with Prof. Chuang Gan and Prof. Yilun Du, and on low-level vision and self/semi-supervised learning with Prof. Chi-Wing Fu at CUHK.

My current research focuses on dexterous robotic manipulation. I am particularly interested in how reinforcement learning, tactile sensing, and human guidance can enable robotic hands to perform challenging manipulation tasks such as grasping, in-hand reorientation, and tool use. My recent work explores tactile-guided reinforcement learning for dexterous manipulation and shared autonomy for dexterous-hand teleoperation, where learned policies assist human operators in executing difficult object-level motions. More broadly, my goal is to build robotic systems that can interact with the physical world with the adaptability, responsiveness, and dexterity required for real-world tasks.