One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models
Contrastive vision-language models learn shared embedding spaces by aligning matched image-text pairs, yet their representations remain separated by a modality gap.
By Aditya Sharma, Divya SaxenaarXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Sep 30, 2026.
Comments
Sign in to join the discussion.