How can we identify what are the invariances that biological neurons encode for? Check out my work with Mo Bashiri. @AntolikLab and sinzlab "Learning invariance manifolds of visual sensory neurons" openreview.net/pdf?id=2dQyENi… It's also at Symmetry and Geometry in Neural Representations, poster session at 3:30pm!

I made a small website: thissynthdoesnotexist.com

Introducing – Paragraphica! 📡📷 A camera that takes photos using location data. It describes the place you are at and then converts it into an AI-generated "photo". See more here: bjoernkarmann.dk/project/paragr… or try to take your own photo here: paragraphica.bjoernkarmann.dk

So excited to share our work got an oral at ICLR! Huge thanks to Mo Bashiri—your vision and drive made this possible; collaborating with you as co-first authors has been truly amazing. Also deeply grateful to @AntolikLab & sinzlab for their invaluable support and guidance!🚀

We visualized the features of 16 SAEs trained on CLIP in collaboration between Fraunhofer HHI and Mila - Institut québécois d'IA! Search thousands of interpretable CLIP features in our vision atlas, with autointerp labels, & scores like clarity and polysemanticity. Some fun features in thread: