HANCLIP: A Family of Hyperbolic Angular Negation Vision Language Models

arXiv:2606.23843v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are typically pre-trained on large-scale image-text datasets to capture semantic correspondences between visual content and natural language. However, they remain surprisingly brittle to negation: models often rely on shallow word co-occurrence and are easily distracted by misleading or irrelevant textual cues, even when their overall retrieval or classification performance is strong. Moreover, directly finetuning on n...