Subspace Alignment for Vision-Language Model Test-time Adaptation

[2601.08139] Subspace Alignment for Vision-Language Model Test-time Adaptation Skip to main content Search Submit Donate Log in Computer Science > Computer Vision and Pattern Recognition arXiv:2601.08139 (cs) [Submitted on 13 Jan 2026 ( v1 ), last revised 27 Aug 2026 (this version, v2)] Title: Subspace Alignment for Vision-Language Model Test-time Adaptation Authors: Zhichen Zeng , Wenxuan Bao , Xiao Lin , Ruizhong Qiu , Tianxin Wei , Xuying Ning , Yuchen Yan , Chen Luo , Monica Xiao Cheng , Jingrui He , Hanghang Tong View PDF HTML (experimental) Abstract: Vision-language models (VLMs), despite their extraordinary zero-shot capabilities, are vulnerable to distribution shifts. Test-time adaptation (TTA) emerges as a predominant strategy to adapt VLMs to unlabeled test data on the fly. However, existing TTA methods heavily rely on zero-shot predictions as pseudo-labels for self-training, which can be unreliable under distribution shifts and misguide adaptation due to two fundamental this http URL (Modality Gap), distribution shifts induce gaps between visual and textual modalities, making cross-modal relations inaccurate. Second (Visual Nuisance), visual embeddings encode rich but task-irrelevant noise that often overwhelms task-specific semantics under distribution shifts. To address these limitations, we propose SubTTA, which aligns the semantic subspaces of both modalities to enhance zero-shot predictions to better guide the TTA process. To bridge the modality gap, SubTTA extracts the principal subspaces of both modalities and aligns the visual manifold to the textual semantic anchor by minimizing their chordal distance. To eliminate visual nuisance, SubTTA projects the aligned visual features onto the task-specific textual subspace, which filters out task-irrelevant noise by constraining visual embeddings within the valid semantic span, and standard TTA is further performed on the purified space to refine the decision boundaries. Extensive experiments on various benchmarks and VLM architectures demonstrate the effectiveness of SubTTA, yielding an average improvement of 2.24% over state-of-the-art TTA methods. Our code is available at this https URL . Comments: 23 pages, 11 figures Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2601.08139 [cs.CV] (or arXiv:2601.08139v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2601.08139 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zhichen Zeng [ view email ] [v1] Tue, 13 Jan 2026 02:02:41 UTC (7,097 KB) [v2] Thu, 27 Aug 2026 05:55:39 UTC (7,235 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2026-01 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark 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? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Subspace Alignment for Vision-Language Model Test-time Adaptation#674279
• Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models#173254
• From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model#343456
• Domain Recentering and Confidence-Weighted Prior Calibration for Vision-Language Models#1077287
• BindCLIP: One Balanced Coupling For Compositional Vision Language Scoring#1049453