AI RESEARCH
Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMs
arXiv CS.CV
•
ArXi:2509.19207v2 Announce Type: replace Contrastive vision-language models (VLMs) have made significant progress in binding visual and textual information, yet understanding long, compositional captions remains an open challenge. While these capabilities are often assumed to be closely related, the conditions under which they reinforce each other remain unclear. In this paper, we empirically analyze when compositional reasoning and long-caption understanding transfer across tasks, and when this relationship fails. Through controlled experiments across diverse.