SOURCE-LINKED INTELLIGENCE

BindCLIP: One Balanced Coupling For Compositional Vision Language Scoring

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Global vision--language similarities compress an image and a caption into one vector, preserving semantics but not which word corresponds to which region or how those regions are arranged; a model can recognize every word and object yet prefer a compositionally incorrect caption. We argue that a frozen encoder retains this association structure, so the problem is to read it rather than to rebuild it beside the pretrained similarity. We introduce BindCLIP, a pairwise scorer built on one latent object: a balanced token--patch--depth optimal-transport coupling that places both candidate captions

Read original source ↗ Open in workspace

recordType

paper

region

Global