Excited to share our ICLR 2021 paper on image composition in GAN latent space! joint with jswulff Phillip Isola paper+code+colab: chail.github.io/latent-composi… it's interactive and super fun to play with :)

Incredibly honored to receive the Koenderink Prize at #ECCV2022 for our work on transforming the #Sintel movie into a benchmark and dataset for Optical Flow (and more!), together with Daniel Butler, Garrett Stanley, and Michael Black . Some background: perceiving-systems.blog/en/news/sintel…

Falcon 9 launch from Vandenberg...

As language models get ever larger, is there still a place for smaller specialized models? In this work we find that there is, and that their performance is comparable to much larger general language models while requiring less data + computation.

This paper asks “Do We Still Need Clinical Language Models?” in the era of ChatGPT? Their analysis finds the answer, at least for now, is yes: arxiv.org/abs/2302.08091

Crazy...

Full article: openevidence.com/announcements/…