Can we match vision and language representations without any supervision or paired data?

Surprisingly, yes! 

Our #CVPR2025 paper with @neekans.bsky.social and @dcremers.bsky.social shows that the pairwise distances in both modalities are often enough to find correspondences.

⬇️ 1/4

Join us this Friday (Feb. 28), 4 pm CET, for a talk by Kevin Chen (MIT) on insect-scale aerial robots driven by soft artificial muscles as a part of our MaP Robotics, Vision, and Control Talks!
Zoom link: t.co/XuhrDNfw73
Details & Full Schedule: t.co/B6W4GJrpGc

I am honored to give a keynote talk at the upcoming GenEAI (geneai.edu.sot.tum.de) workshop at ETRA (etra.acm.org/2025/index.h...) in Toyko. Looking forward to it!

We are organizing the third version of the Rhobin workshop at this year's CVPR, and have an outstanding lineup of speakers! Join us at #CVPR in June. More details on the workshop page rhobin-challenge.github.io

I am going to give a talk at ZurichCV#8 event tonight at 18:00!
You are more than welcome to join us!

lnkd.in/ewrJirNg