{"ID":2841403,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.12331","arxiv_id":"2511.12331","title":"SpaceVLM: Sub-Space Modeling of Negation in Vision-Language Models","abstract":"Vision-Language Models (VLMs) struggle with negation. Given a prompt like \"retrieve (or generate) a street scene without pedestrians,\" they often fail to respect the \"not.\" Existing methods address this limitation by fine-tuning on large negation datasets, but such retraining often compromises the model's zero-shot performance on affirmative prompts. We show that the embedding space of VLMs, such as CLIP, can be divided into semantically consistent subspaces. Based on this property, we propose a training-free framework that models negation as a subspace in the joint embedding space rather than a single point (Figure 1). To find the matching image for a caption such as \"A but not N,\" we construct two spherical caps around the embeddings of A and N, and we score images by the central direction of the region that is close to A and far from N. Across retrieval, MCQ, and text-to-image tasks, our method improves negation understanding by about 30% on average over prior methods. It closes the gap between affirmative and negated prompts while preserving the zero-shot performance that fine-tuned models fail to maintain. Code will be released upon publication.","short_abstract":"Vision-Language Models (VLMs) struggle with negation. Given a prompt like \"retrieve (or generate) a street scene without pedestrians,\" they often fail to respect the \"not.\" Existing methods address this limitation by fine-tuning on large negation datasets, but such retraining often compromises the model's zero-shot per...","url_abs":"https://arxiv.org/abs/2511.12331","url_pdf":"https://arxiv.org/pdf/2511.12331v1","authors":"[\"Sepehr Kazemi Ranjbar\",\"Kumail Alhamoud\",\"Marzyeh Ghassemi\"]","published":"2025-11-15T19:18:40Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}