I am an M.S. student in Computer Science at ShanghaiTech University, advised by Ying Cao and Quan Li. My research focuses on generative modeling for graphic design, particularly the joint understanding and generation of multimodal design content.

I develop generative models that jointly reason about visual content, spatial layout, typography, and semantic intent. My recent work explores multimodal priors for data-efficient design generation, interactions between image and layout generation, and coordinated image editing and layout synthesis. More broadly, I am interested in controllable generation, multimodal learning, and diffusion- and flow-based generative modeling.

Beyond research, I enjoy drawing and long-distance running.