# Semantic-Preserving Cross-Style Visual Reasoning for Robust Multi-Modal Understanding in Large Vision-Language Models

Source: [Semantic-Preserving Cross-Style Visual Reasoning for Robust Multi-Modal Understanding in Large Vision-Language Models](<https://www.sota2.com/research/paper/69004e1f3ef7ccd74e5e2f6b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-29T05:05:10.050Z

Authors: Aya Nakayama, Brian Wong, Yuji Nishimura, Kaito Tanaka

Published: 2025-10-26T21:11:46.000Z

## Abstract

The "style trap" poses a significant challenge for Large Vision-Language Models (LVLMs), hindering robust semantic understanding across diverse visual styles, especially in in-context learning (ICL). Existing methods often fail to effectively decouple style from content, hindering generalization. To address this, we propose the Semantic-Preserving Cross-Style Visual Reasoner (SP-CSVR), a novel framework for stable semantic understanding and adaptive cross-style visual reasoning. SP-CSVR integrates a Cross-Style Feature Encoder (CSFE) for style-content disentanglement, a Semantic-Aligned In-Context Decoder (SAICD) for efficient few-shot style adaptation, and an Adaptive Semantic Consistency Module (ASCM) employing multi-task contrastive learning to enforce cross-style semantic invariance. Extensive experiments on a challenging multi-style dataset demonstrate SP-CSVR's state-of-the-art performance across visual captioning, visual question answering, and in-context style adaptation. Comprehensive evaluations, including ablation studies and generalization analysis, confirm SP-CSVR's efficacy in enhancing robustness, generalization, and efficiency across diverse visual styles.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.22838>)

[PDF](<https://arxiv.org/pdf/2510.22838.pdf>)
