Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains

ACL ARR 2025 February Submission4470 Authors

Abstract:

Vision-language models (VLMs) achieve remarkable success in single-image tasks. However, real-world scenarios often involve intricate multi-image inputs, leading to a notable performance decline as models struggle to disentangle critical information scattered across complex visual features.
In this work, we propose Focus-Centric Visual Chain, a novel paradigm that enhances VLMs’ perception, comprehension, and reasoning abilities in multi-image scenarios. To facilitate this paradigm, we propose Focus-Centric Data Synthesis, a scalable bottom-up approach for synthesizing high-quality data with elaborate reasoning paths. Through this approach, We
construct VISC-150K, a large-scale dataset with reasoning data in the form of Focus-Centric Visual Chain, specifically designed for multi-image tasks. Experimental results on seven multi-image benchmarks demonstrate that our method achieves average performance gains of 3.16% and 2.24% across two distinct model architectures, without compromising the general vision-language capabilities.
our study represents a significant step toward more robust and capable vision-language systems that can handle complex visual scenarios.

Paper Type: Long

Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond

Research Area Keywords: vision question answering, multimodality

Contribution Types: NLP engineering experiment, Data resources

Languages Studied: English

Submission Number: 4470