Currently, I am an undergraduate student at MIT EECS, where I am advised by Vincent Sitzmann as part of the Scene Representation Group. My goal is to build AI models that can understand, generate, and interact with the world. Specifically, I work on generative models and video world models. Previously, I worked at the MIT-IBM Watson AI Lab with Arvind and Jie Chen on graph representation learning.
Classifier-free guidance (CFG) is a key technique for improving conditional generation in diffusion models, enabling more accurate control while enhancing sample quality. It is natural to extend this technique to video diffusion, which generates video conditioned on a variable number of context frames, collectively referred to as history. However, we find two key challenges to guiding with variable-length history: architectures that only support fixed-size conditioning, and the empirical observation that CFG-style history dropout performs poorly. To address this, we propose the Diffusion Forcing Transformer (DFoT), a video diffusion architecture and theoretically grounded training objective that jointly enable conditioning on a flexible number of history frames. We then introduce History Guidance, a family of guidance methods uniquely enabled by DFoT. We show that its simplest form, vanilla history guidance, already significantly improves video generation quality and temporal consistency. A more advanced method, history guidance across time and frequency further enhances motion dynamics, enables compositional generalization to out-of-distribution history, and can stably roll out extremely long videos.
@misc{song2025historyguidedvideodiffusion,title={History-Guided Video Diffusion},author={Song, Kiwhan and Chen, Boyuan and Simchowitz, Max and Du, Yilun and Tedrake, Russ and Sitzmann, Vincent},year={2025},eprint={2502.06764},archiveprefix={arXiv},primaryclass={cs.LG},url={https://arxiv.org/abs/2502.06764},}
