mlsanityData to 14 Oct 2026

The Impact of Image Resolution on Biomedical Multimodal Large Language Models

arXiv 2510.18304 ↗First posted 21 Oct 2025cs.CV cs.CLcited by 1

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 23 of its 35 references that are in the map. First posted on arXiv 21 Oct 2025.

Builds on

23 of 35 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature13 Jan
  2. 2024MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine6 Aug
  3. 2024Advancing High Resolution Vision-Language Models in Biomedicine12 Jun
  4. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day1 Jun

Other references · 19

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  3. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  4. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  6. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  7. 2023Otter: A Multi-Modal Model with In-Context Instruction Tuningcited by 550
  8. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 475
  9. 2021SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answeringcited by 449
  10. 2023PaLI-X: On Scaling up a Multilingual Vision and Language Modelcited by 255
  11. 2024Rotary Position Embedding for Vision Transformercited by 236
  12. 2019Fixing the train-test resolution discrepancycited by 209
7 more
  1. 2024LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Imagescited by 195
  2. 2024Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Modelscited by 66
  3. 2024WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answeringcited by 34
  4. 2025MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Researchcited by 32
  5. 2024μ-Bench: A Vision-Language Benchmark for Microscopy Understandingcited by 15
  6. 2022RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learningcited by 8
  7. 2022Understanding the Impact of Image Quality and Distance of Objects to Object Detection Performancecited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification
  2. 2025Res-Bench: Benchmarking the Robustness of Multimodal Large Language Models to Dynamic Resolution Input
  3. 2025A Training-Free, Task-Agnostic Framework for Enhancing MLLM Performance on High-Resolution Images
  4. 2025Perceive and Calibrate: Analyzing and Enhancing Robustness of Medical Multi-Modal Large Language Models
  5. 2024On Large Visual Language Models for Medical Imaging Analysis: An Empirical Study
  6. 2025Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation
  7. 2024Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models
  8. 2024Multimodal Large Language Models for Bioimage Analysis