arxiv
PublishedJuly 28, 2026 at 4:00 AM
What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features
Publisher summary· verbatim
arXiv:2607.23271v1 Announce Type: cross Abstract: Contrastive vision-language models such as CLIP map semantically opposite phrases (e.g., "a dog" vs. "not a dog") to nearly identical embeddings, rendering them insensitive to negation. We attribute this failure to a phenomenon we call Representation
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
The Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗