Skip to contentSkip to filters

We use cookies for analytics.

Distributional Diffusion Models

Valentin de Bortoli

Google DeepMind

Recording

49 min

Abstract

Standard diffusion training estimates the mean of clean data conditioned on a noisy sample. This talk instead learns the entire conditional distribution using a scoring-rule objective. Sampling that richer posterior permits larger reverse-process steps and fewer inference iterations. Experiments with images and robot trajectories assess the resulting speed–quality trade-off and compare it with conventional diffusion models.

Topics