Papers
arxiv:2508.00945

Optimizing Vision-Language Consistency via Cross-Layer Regional Attention Alignment

Published on Jul 31, 2025
Authors:
,
,
,
,
,
,
,
,
,

Abstract

Consistent Cross-layer Regional Alignment enhances vision-language models by introducing layered patch-wise cross attention and progressive attention integration to improve cross-modal embedding learning and model interpretability.

AI-generated summary

Vision Language Models (VLMs) face challenges in effectively coordinating diverse attention mechanisms for cross-modal embedding learning, leading to mismatched attention and suboptimal performance. We propose Consistent Cross-layer Regional Alignment (CCRA), which introduces Layer-Patch-wise Cross Attention (LPWCA) to capture fine-grained regional-semantic correlations by jointly weighting patch and layer-wise embedding, and Progressive Attention Integration (PAI) that systematically coordinates LPWCA, layer-wise, and patch-wise attention mechanisms in sequence. This progressive design ensures consistency from semantic to regional levels while preventing attention drift and maximizing individual attention benefits. Experimental results on ten diverse vision-language benchmarks demonstrate that our CCRA-enhanced LLaVA-v1.5-7B model achieves state-of-the-art performance, outperforming all baseline methods with only 3.55M additional parameters, while providing enhanced interpretability through more regionally focused and semantically aligned attention patterns.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2508.00945 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2508.00945 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2508.00945 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.