Multimodal Agents · Visual Generation

Building Generative Intelligence for Open-Ended Multimodal Creation

I am an undergraduate student at South China University of Technology. My research focuses on multimodal agent systems that turn human intent into controllable visual and interactive content. I am broadly interested in agents for image generation, video generation, 3D/4D generation, visual reasoning, and iterative editing: systems that can decompose creative tasks, coordinate specialized models or tools, and improve outputs through planning, feedback, and self-reflection. I work closely with Jinxiu Liu.