AI RESEARCH
More Than Meets the Eye: Measuring the Semiotic Gap in Vision-Language Models via Semantic Anchorage
arXiv CS.CL
•
ArXi:2604.17354v1 Announce Type: new Vision-Language Models (VLMs) excel at photorealistic generation, yet often struggle to represent abstract meaning such as idiomatic interpretations of noun compounds. To study whether high visual fidelity interferes with idiomatic compositionality under visual abstraction, we