Diffusion models are powerful, but they require a lot of time and data to train. We propose Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training time costs while improving data efficiency, which thus helps democratize diffusion model training to broader users. At the core of our innovations is a new conditional score function at the patch level, where the patch location in the original image is included as additional coordinate channels, while the patch size is randomized and diversified throughout training to encode the cross-region dependency at multiple scales. Sampling with our method is as easy as in the original diffusion model.

Our method, V oxMol, generates molecules in a fundamentally different way than the current state of the art ( i.e.,

We propose a method called clustered conformal prediction that clusters together classes having "similar" conformal

We explore the methodology and theory of reward-directed generation via conditional diffusion models.

We explore the methodology and theory of reward-directed generation via conditional diffusion models.

B.5 Langevin dynamics Under mild assumptions on r log p