作者位次 #3/3ACL 2026Findings· Findings of ACL
Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLM s
Israfel Salazar · Desmond Elliott · Yova Kementchedjhieva
摘要
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...