Jonathan Ho
First author of Denoising Diffusion Probabilistic Models (DDPM) and of Classifier-Free Diffusion Guidance
Jonathan Ho is first author of "Denoising Diffusion Probabilistic Models" (DDPM, NeurIPS 2020), written with Ajay Jain and Pieter Abbeel, all three listed with UC Berkeley on the paper's project page. With Tim Salimans, Ho wrote "Classifier-Free Diffusion Guidance" (2022). Ho is a co-first author of Imagen Video, a text-to-video system of cascaded video diffusion models presented by Google Research's Brain Team, and a co-author of Imagen and of "Variational Diffusion Models" with Diederik P. Kingma, Tim Salimans, and Ben Poole.1273456
Work
Denoising Diffusion Probabilistic Models (DDPM) (external site: hojonathanho.github.io)Published research
First author, with Ajay Jain and Pieter Abbeel (all listed with UC Berkeley on the project page), of the NeurIPS 2020 paper on high-quality image synthesis with diffusion probabilistic models; the project page links the paper and the authors' code repository.217
Classifier-Free Diffusion Guidance (external site: arxiv.org)Published research
First author, with Tim Salimans, of the 2022 paper introducing classifier-free guidance for diffusion models.3
Imagen Video (external site: imagen.research.google)Published research
Listed first among the equal-contribution authors of Imagen Video on Google Research's project page, which describes a text-conditional video generation system built from a cascade of video diffusion models.4
Other documented roles
Roles the sources document but that are not confirmed as current.
- Listed with Google Research, Brain Team on Classifier-Free Diffusion Guidance and as co-first author of Imagen Video (2022), Google Research, Brain Team48
- Listed with UC Berkeley as first author of DDPM (2020), UC Berkeley1
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.