{"type":"ScholarlyArticle","title":"CoDA: Co-adaptive Dual-path Alignment for Vision-Language Models","authors":[{"name":"Yi Zhang","slug":"yi-zhang","given":"Yi","family":"Zhang","affiliation":""},{"name":"Rui Zhu","slug":"rui-zhu","given":"Rui","family":"Zhu","affiliation":""},{"name":"Channi Li","slug":"channi-li","given":"Channi","family":"Li","affiliation":""},{"name":"Xiaoxu Li","slug":"xiaoxu-li","given":"Xiaoxu","family":"Li","affiliation":""},{"name":"Zhanyu Ma","slug":"zhanyu-ma","given":"Zhanyu","family":"Ma","affiliation":""},{"name":"Jing-Hao Xue","slug":"jing-hao-xue","given":"Jing-Hao","family":"Xue","affiliation":""}],"abstract":"Parameter-efficient adaptation methods, such as adapters and prompt learning, have become popular for transferring pre-trained vision-language models (VLMs) to downstream tasks. However, under limited supervision during adaptation, overly aggressive cross-modal alignment can distort the intrinsic structure of modality-specific representations, leading to degraded generalization. In this paper, we propose Co-adaptive Dual-path Alignment (CoDA), a new adaptation framework that explicitly disentangles and coordinates cross-modal semantic alignment and intra-modal structural consistency. In CoDA, we also propose a parent class labeling strategy that injects hierarchical semantic priors into textual prompts, further stabilizing alignment under limited supervision. Extensive experiments on eleven benchmark datasets show that CoDA outperforms state-of-the-art parameter-efficient methods, particularly under few-shot learning and distribution-shift scenarios. Our code is available at https://github.com/yizhang-ac/CoDA.","doi":"10.24963/ijcai.2026/234","url":"https://ijcai.org/proceedings/2026/234","pdf":"https://ijcai.org/proceedings/2026/0234.pdf","markdown":"https://ijcai.org/proceedings/2026/234.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/234","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":234,"pages":{"first":2100,"last":2108},"keywords":["Machine Learning: Few-shot learning","Computer Vision: Transfer, low-shot, semi- and un- supervised learning","Computer Vision: Multimodal learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}