I am a PhD student at Fudan University, co-advised by Prof. Tao Xie and Prof. Wei Yang.
My research interests include multimodal large language models, diffusion models, and intelligent agents, including GUI agents and agent operating systems.
I received my MSc in Professional Computer Science from Simon Fraser University and my BSc in Computer Science from the University of Alberta.
Turning images into interactive object layers for precise, action-based editing with a vision-language-action agent.
Layered diffusion for precise human removal in complex scenes, reducing semantic leakage between people, objects, and backgrounds.