---
title: "BMIP: Bi-directional Modality Interaction Prompt Learning for VLM"
authors:
  - "Song-Lin Lv"
  - "Yu-Yang Chen"
  - "Zhi Zhou"
  - "Ming Yang"
  - "Lan-Zhe Guo"
doi: "10.24963/ijcai.2025/655"
url: "https://ijcai.org/proceedings/2025/655"
pdf: "https://ijcai.org/proceedings/2025/0655.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "5887-5895"
track: "Main Track"
keywords:
  - "Computer Vision: CV: Multimodal learning"
  - "Machine Learning: ML: Multi-modal learning"
  - "Machine Learning: ML: Few-shot learning"
  - "Machine Learning: ML: Open-World/Open-Set/OOD Learning"
---

# BMIP: Bi-directional Modality Interaction Prompt Learning for VLM

Song-Lin Lv, Yu-Yang Chen, Zhi Zhou, Ming Yang, Lan-Zhe Guo

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 5887-5895. DOI: [10.24963/ijcai.2025/655](https://doi.org/10.24963/ijcai.2025/655)

## Abstract

Vision-language models (VLMs) have exhibited remarkable generalization capabilities, and prompt learning for VLMs has attracted great attention for the ability to adapt pre-trained VLMs to specific downstream tasks. However, existing studies mainly focus on single-modal prompts or uni-directional modality interaction, overlooking the powerful alignment effects resulting from the interaction between the vision and language modalities. To this end, we propose a novel prompt learning method called Bi-directional Modality Interaction Prompt (BMIP), which dynamically weights bi-modal information through learning the information of the attention layer, enhancing trainability and inter-modal consistency compared to simple information aggregation methods. To evaluate the effectiveness of prompt learning methods, we propose a more realistic evaluation paradigm called open-world generalization complementing the widely adopted cross-dataset transfer and domain generalization tasks. Comprehensive experiments on various datasets reveal that BMIP not only outperforms current state-of-the-art methods across all three evaluation paradigms but is also flexible enough to be combined with other prompt-based methods for consistent performance enhancement.