William (Bill) Peebles

William Peebles
I'm a fourth-year PhD student at Berkeley AI Research advised by Alyosha Efros. Previously, I did my undergrad at MIT where I worked with Antonio Torralba. I've interned at FAIR, Adobe Research and NVIDIA. I'm supported by the National Science Foundation's Graduate Research Fellowship Program.

My research focuses on deep learning and artificial intelligence, with a strong emphasis on deep generative models. I am especially interested in large-scale generative AI for synthesizing and manipulating visual content.

twitter · github · google scholar · email


[Jan 2023] DiT is now natively usable in Hugging Face diffusers here.
[Dec 2022] We released a DiT Hugging Face Space here.
[Dec 2022] DiT code has been released in PyTorch here.
[Sep 2022] G.pt code has been released in PyTorch here.
[Jun 2022] GANgealing is a best paper finalist at CVPR'22.
[Apr 2022] Check out Two Minute Papers' video covering GANgealing!


Scalable Diffusion Models with Transformers
William Peebles, Saining Xie
project page · hugging face space · colab · paper · github

Learning to Learn with Generative Models of Neural Network Checkpoints
William Peebles*, Ilija Radosavovic*, Tim Brooks, Alexei Efros, Jitendra Malik
project page · paper · github

GAN-Supervised Dense Visual Alignment
William Peebles, Jun-Yan Zhu, Richard Zhang, Antonio Torralba, Alexei Efros, Eli Shechtman
CVPR 2022 (Oral) · Best Paper Finalist
two minute papers · mixed reality demo · video · project page · paper · github

The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
William Peebles, John Peebles, Jun-Yan Zhu, Alexei Efros, Antonio Torralba
ECCV 2020 (Spotlight)
video · overview in 90 seconds · project page · paper · github

GAN reconstructions of images versus the original images. Seeing What a GAN Cannot Generate
David Bau, Jun-Yan Zhu, Jonas Wulff, William Peebles, Hendrik Strobelt, Bolei Zhou, Antonio Torralba
ICCV 2019 (Oral)
demo · project page · paper · github

A natural image of a building is modified by adding trees and domes. Semantic Photo Manipulation with a Generative Image Prior
David Bau, Hendrik Strobelt, William Peebles, Jonas Wulff, Bolei Zhou, Jun-Yan Zhu, Antonio Torralba
demo · project page · paper