Post

Jonathan Stray
@jonathanstray.com

Another nail in the coffin of the Octopus Thought Experiment. You *can* learn the structure of the physical world from text alone.

Dominik Schnaus@schnaus.bsky.social

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 ⬇️

No replies yet.