About Me

Hi! I am Jiazhe Wei (魏佳哲), an incoming master student majoring in Artificial Intelligence at Nanjing University and doing research at Pattern Recognition Lab @NJU, supervised by Prof. Chenyang Si and Prof. Tieniu Tan. I got my bachelor degree at Xi’an Jiaotong university.

I have completed several wonderful research internships at CERN, Westlake University, and Lovart.AI, and I have met many open and outstanding researchers during my experience. I’m currently interning in the Video Generation Group at WeChat Vision @ Tencent, where I work with Dr. Binxin Yang and Dr. Chen Li on video editing foundation training and world models.

My research explores a clear division of labor between understanding and generative models: each should focus on what it does best, while the understanding model explicitly guides the generative process. My goal is to make generative models function as instruction-driven, renderer-level systems and to unify understanding and generation through an agent harness. Specifically, my research interests include: 1) Agentic Generative Models; 2) Video World Models with Controllable Agent Harnesses; 3) Generative Models with Physical Intelligence.

✨ I’m always open to all kinds of cooperation and discussion. You can contact me via email or WeChat: wjz_void.