YiTao ZHU

About

I am currently a Ph.D. student at The Hong Kong Polytechnic University, supervised by Prof. Anqi Qiu (仇安琪). I received my M.S. in Computer Science from ShanghaiTech University in 2025, advised by Prof. Qian Wang (王乾), and my B.S. in Computer Science from the same institution in 2022.

Research

My current research focuses on multimodal large language models (MLLMs) for medical image analysis, leveraging MLLMs to enable more reliable and naturally interactive computer-aided diagnosis (CAD), report generation, and medical image synthesis. Previously, I have also worked extensively in natural image processing, including multi-view object tracking and 3D human reconstruction. I have published serveral papers about medical image and computer vision with total .