---
title: "CoDA: Co-adaptive Dual-path Alignment for Vision-Language Models"
authors:
  - "Yi Zhang"
  - "Rui Zhu"
  - "Channi Li"
  - "Xiaoxu Li"
  - "Zhanyu Ma"
  - "Jing-Hao Xue"
doi: "10.24963/ijcai.2026/234"
url: "https://ijcai.org/proceedings/2026/234"
pdf: "https://ijcai.org/proceedings/2026/0234.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "2100-2108"
track: "Main Track"
keywords:
  - "Machine Learning: Few-shot learning"
  - "Computer Vision: Transfer, low-shot, semi- and un- supervised learning"
  - "Computer Vision: Multimodal learning"
---

# CoDA: Co-adaptive Dual-path Alignment for Vision-Language Models

Yi Zhang, Rui Zhu, Channi Li, Xiaoxu Li, Zhanyu Ma, Jing-Hao Xue

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 2100-2108. DOI: [10.24963/ijcai.2026/234](https://doi.org/10.24963/ijcai.2026/234)

## 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.