Haojun Qiu

Hi! I am a researcher on the World Models team at Waabi, working on world modeling and simulation for autonomous driving. I received my B.Sc. in Computer Science from the University of Toronto, advised by Prof. David B. Lindell and Prof. Kyros Kutulakos, and worked on score-based generative modeling and patch-based methods, focusing on efficient and training-free single-image generative modeling via closed-form diffusion models.

In Summer 2024, I worked with Prof. Jiajun Wu and Dr. Elliott Wu at Stanford University on video score distillation and motion modeling. In Summer 2025, I participated in the Summer Geometry Initiative (SGI) at MIT, where I explored some topics in geometry processing (Monte Carlo geometry processing, logarithmic heat diffusion, and fluid simulation with Gaussian velocity fields).

My current research interests broadly span generative models (diffusion/flow models), video world models, and 3D/4D scene representations.