Over the past three years, diffusion models have established themselves as a new generative modelling paradigm.
Their empirical successes have broadened the applications of generative modelling to image, video, audio, 3D
synthesis and science applications. As diffusion models become more and more popular and are applied to extremely
diverse problems, it also becomes harder to track the key contributions in the field. This workshop aims to keep
track of the recent advances and set guidelines for future research. By bringing together practice, methodology and
theory actors we aim at identifying unexplored areas and pushing the frontier of diffusion model research.
The workshop will be held on Friday 15th December 2023 in Hall B1 (ground floor) - we look forward to seeing you in New Orleans!
Ask questions to our panelists here
We would like to thank Apple and NVIDIA for sponsoring the workshop (and providing prizes - to be announced!)
Weizmann Institute of Science, Google
John Hopkins University
University of Maryland
Valentin De Bortoli
Contact us at