AI 服务暂时不可用，以下为来源正文，待恢复后补全翻译。
[Submitted on 28 Sep 2026] Title:One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models View a PDF of the paper titled One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models, by Aditya Sharma and 1 other authors View PDF HTML (experimental) Abstract:Contrastive vision-language models learn shared embedding spaces by aligning matched image-text pairs, yet their representations remain separated by a modality gap. Prior work reports divergent effects of modifying this gap: reducing it can improve zero-shot classification and cross-modal alignment, whereas removing gap-related structure can degrade image-text retrieval. In this paper, we provide a unified geometric explanation for these task-dependent effects. Across CLIP and SigLIP encoders, we find that a single dominant direction captures 94.4-99.9% of the squared norm of the image-text mean separation, revealing that the mean-separation component is approximately rank-one. A decomposition of the similarity score then identifies three task-specific roles. In zero-shot classification, query-side fixed gap-offset subtraction is exactly equivalent to an additive class bias. In standard cross-modal retrieval, projecting out the gap direction and renormalising residuals discards candidate-specific norm information, inducing a multiplicative ranking distortion; a geometry-derived exponent tracks the grid-search optimum (Spearman rho = 0.93) and restores performance in some settings, although the gains transfer unevenly. In mixed-modal retrieval, the gap direction sorts candidates by modality; its removal can improve cross-modal ranking, unlike random or non-gap controls. Residual semantic structure after removal defines the limits of the rank-one account. Together, these results explain why gap modification can improve, degrade, or restore performance across downstream settings. By clarifying when and why gap modification changes model behavior, this account provides a principled basis for selecting gap interventions in similarity-based vision-language systems across evaluated downstream tasks. Comments: 9 pages, 3 figures, 3 tables Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2609.36101 [cs.CV] (or arXiv:2609.36101v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2609.36101 arXiv-issued DOI via DataCite (pending registration) Submission history From: Aditya Sharma [view email] [v1] Mon, 28 Sep 2026 18:40:27 UTC (312 KB) Full-text links: Access Paper: View a PDF of the paper titled One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models, by Aditya Sharma and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV new | recent | 2026-09 Change to browse by: cs cs.AI cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)