{"ID":2852053,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.18304","arxiv_id":"2510.18304","title":"The Impact of Image Resolution on Biomedical Multimodal Large Language Models","abstract":"Imaging technologies are fundamental to biomedical research and modern medicine, requiring analysis of high-resolution images across various modalities. While multimodal large language models (MLLMs) show promise for biomedical image analysis, most are designed for low-resolution images from general-purpose datasets, risking critical information loss. We investigate how image resolution affects MLLM performance in biomedical applications and demonstrate that: (1) native-resolution training and inference significantly improve performance across multiple tasks, (2) misalignment between training and inference resolutions severely degrades performance, and (3) mixed-resolution training effectively mitigates misalignment and balances computational constraints with performance requirements. Based on these findings, we recommend prioritizing native-resolution inference and mixed-resolution datasets to optimize biomedical MLLMs for transformative impact in scientific research and clinical applications.","short_abstract":"Imaging technologies are fundamental to biomedical research and modern medicine, requiring analysis of high-resolution images across various modalities. While multimodal large language models (MLLMs) show promise for biomedical image analysis, most are designed for low-resolution images from general-purpose datasets, r...","url_abs":"https://arxiv.org/abs/2510.18304","url_pdf":"https://arxiv.org/pdf/2510.18304v1","authors":"[\"Liangyu Chen\",\"James Burgess\",\"Jeffrey J Nirschl\",\"Orr Zohar\",\"Serena Yeung-Levy\"]","published":"2025-10-21T05:19:43Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}