University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > Sampling with diffusion models

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

Sampling with diffusion models

Download to your calendar using vCal

If you have a question about this talk, please contact .

Teams link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.

In this talk, Shreyas and Jiajun will discuss sampling with diffusion models. We cover two cases, one is to do posterior (or conditioning) sampling of diffusion models, for applications in inverse imaging, class-conditional sampling, text-to-image guidance and finetuning, and another is to learn a diffusion models to draw samples from unnormalized density. For the former, we cover inference-only corrections to existing diffusion models that fall under the umbrella of “reconstruction guidance” (DPS, Red-diff etc), as well as training methods such as classifier and classifier-free guidance. Finally, we discuss some recent work for efficient finetuning (ControlNet, DEFT etc), as well as an introduction to stochastic control techniques (DEFT, Adjoint Matching). For the latter, we will introduce some recently developed diffusion-based neural samplers, including diffusion denoising samplers (DDS, iDEM, etc) , escorted samplers (CMCD, etc.), or other variations.

This talk is part of the Machine Learning Reading Group @ CUED series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

test Winstanley Lecture Theatre Old Library at Pembroke College

Other talks

Why people with schizophrenia die earlier? Mortality and accelerated ageing Director's Briefing Title tbc Decoding genomic chaos - a pancancer compendium of chromosomal instability TBC Group Presentation 5
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity