It’s clear this is a new experience; he’s an assistant professor and coauthor. A whole bunch of big name BSky folks are poking at his study, which seems like a good study. I’m really surprised everyone is “giving him career advice”

Show Post

DINOv2 has never seen a caption, and Qwen3 has never seen an image. We still aligned their embedding spaces without a single image-caption pair. It even works when the images and the captions come from different datasets. Project page: dominik-schnaus.github.io/unpaired-rosetta ⬇️

Show Post

This is a result I’ve dreamt about for many years: *unpaired translation between images and text* I thought it might be only slightly possible, the kind of thing you have to really squint at. But Dominik proved this wrong. You don’t have to squint. Worth looking for yourself:

Show Post

Our reward function compression work is now out in Nature Communications! 🎉 In it, we present and empirically test a computational framework that formalizes the trade-offs between goal flexibility and learning efficiency. @annecollins.bsky.social @natureportfolio.nature.com doi.org/10.1038/s414...

Show Post

Really excited about this paper with @gaiamolinaro.bsky.social - check it out! We have a few other projects coming out soon, which further support the theory we put forward.

Show Post