{"ID":2853210,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.16926","arxiv_id":"2510.16926","title":"Res-Bench: Benchmarking the Robustness of Multimodal Large Language Models to Dynamic Resolution Input","abstract":"Multimodal Large Language Models (MLLMs) increasingly support dynamic image resolutions. However, current evaluation paradigms primarily assess semantic performance, overlooking the critical question of resolution robustness - whether performance remains stable across varying input resolutions. To address this gap, we introduce \\textbf{Res-Bench}, a comprehensive benchmark comprising 14,400 samples across 12 resolution levels and six core capability dimensions. We designed a novel evaluation framework that goes beyond traditional accuracy metrics to capture performance stability. This framework introduces multiple robustness metrics: Spearman's correlation for assessing resolution-performance trends, and Absolute/Relative Continuous Error (ACE/RCE) for measuring performance volatility. Using these metrics, we conducted a large-scale evaluation of leading MLLMs. Our analysis encompasses: (1) model-centric and task-centric robustness examination, (2) investigation of preprocessing strategies including padding and super-resolution, and (3) exploration of fine-tuning for stability enhancement.","short_abstract":"Multimodal Large Language Models (MLLMs) increasingly support dynamic image resolutions. However, current evaluation paradigms primarily assess semantic performance, overlooking the critical question of resolution robustness - whether performance remains stable across varying input resolutions. To address this gap, we...","url_abs":"https://arxiv.org/abs/2510.16926","url_pdf":"https://arxiv.org/pdf/2510.16926v3","authors":"[\"Chenxu Li\",\"Zhicai Wang\",\"Yuan Sheng\",\"Xingyu Zhu\",\"Yanbin Hao\",\"Xiang Wang\"]","published":"2025-10-19T16:53:01Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}