Research
My recent research focuses on understanding and improving multi-step inference processes in neural networks. I am interested in how internal representations evolve across iterative steps, and how these dynamics can be exploited to improve efficiency, controllability, and generalization.
Diffusion Models
I study how diffusion models allocate computation across layers and time steps, with an emphasis on dynamic routing, token/state selection, and accelerated inference.
Video Generation
I work on planning-generation decomposition for video models, scalable spatio-temporal architectures, and methods that improve controllability while maintaining generation quality.
Multimodal Foundation Models
More broadly, I am interested in multimodal generative modeling, visual reasoning, and efficient neural architectures that reveal and exploit internal dynamics during inference.