Vision-Language Models (VLMs) face significant challenges when dealing with the diverse resolutions and aspect ratios of real-world images, as most existing models rely on fixed, low-resolution inputs. While recent studies have explored integrating native resolution visual encoding to improve model performance, such efforts remain fragmented and lack a systematic framework within the open-source community. Moreover, existing benchmarks fall short in evaluating VLMs under varied visual conditions, often neglecting resolution as a critical factor. To address the "Resolution Dilemma" stemming from both model design and benchmark limitations, we introduce RC-Bench, a novel benchmark specifically designed to systematically evaluate VLM capabilities under extreme visual conditions, with an emphasis on resolution and aspect ratio variations. In conjunction, we propose NativeRes-LLaVA, an open-source training framework that empowers VLMs to effectively process images at their native resolutions and aspect ratios. Based on RC-Bench and NativeRes-LLaVA, we conduct comprehensive experiments on existing visual encoding strategies. The results show that Native Resolution Visual Encoding significantly improves the performance of VLMs on RC-Bench as well as other resolution-centric benchmarks. Code is available at https://github.com/Niujunbo2002/NativeRes-LLaVA.
@article{arxiv.2506.12776,
title = {Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models},
author = {Junbo Niu and Yuanhong Zheng and Ziyang Miao and Hejun Dong and Chunjiang Ge and Hao Liang and Ma Lu and Bohan Zeng and Qiahao Zheng and Conghui He and Wentao Zhang},
journal= {arXiv preprint arXiv:2506.12776},
year = {2025}
}