# On the Robustness of Medical Vision-Language Models: Are they Truly Generalizable?

arXiv: https://arxiv.org/abs/2505.15425 · HTML: https://mlsanity.com/paper/2505.15425/

## Key facts

- Cited by 10 papers 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 39 references that are in the map.
- First posted on arXiv 21 May 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents](https://mlsanity.com/paper/2303.07240/) (2023)
- [A Comprehensive Survey of Foundation Models in Medicine](https://mlsanity.com/paper/2406.10729/) (2024)
- [MedFuse: Multi-modal fusion with clinical time-series data and chest X-ray images](https://mlsanity.com/paper/2207.07027/) (2022)
- [ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image Dataset](https://mlsanity.com/paper/2405.10004/) (2024)
- [UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities](https://mlsanity.com/paper/2412.10372/) (2024)
- [CLIP in Medical Imaging: A Survey](https://mlsanity.com/paper/2312.07353/) (2023)
- [DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation](https://mlsanity.com/paper/2011.09876/) (2020)
- [MedMNIST-C: Comprehensive benchmark and improved classifier robustness by simulating realistic image corruptions](https://mlsanity.com/paper/2406.17536/) (2024)
- [Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models](https://mlsanity.com/paper/2407.15913/) (2024)
- [BAPLe: Backdoor Attacks on Medical Foundational Models using Prompt Learning](https://mlsanity.com/paper/2408.07440/) (2024)
- [A comprehensive and easy-to-use multi-domain multi-task medical imaging meta-dataset](https://mlsanity.com/paper/2404.16000/) (2024)
- [A Survey of Medical Vision-and-Language Applications and Their Techniques](https://mlsanity.com/paper/2411.12195/) (2024)
- [Pre and Post-hoc Diagnosis and Interpretation of Malignancy from Breast DCE-MRI](https://mlsanity.com/paper/1809.09404/) (2018)
- [Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentation](https://mlsanity.com/paper/2307.07269/) (2023)
- [Noise is an Efficient Learner for Zero-Shot Vision-Language Models](https://mlsanity.com/paper/2502.06019/) (2025)
- [On Evaluating Adversarial Robustness of Volumetric Medical Segmentation Models](https://mlsanity.com/paper/2406.08486/) (2024)
- [Benchmarking Robustness of Contrastive Learning Models for Medical Image-Report Retrieval](https://mlsanity.com/paper/2501.09134/) (2025)

## Built on by (most cited first, 10 of 10)

- [Reasoning Visual Language Model for Chest X-Ray Analysis](https://mlsanity.com/paper/2510.23968/) (2025)
- [Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift](https://mlsanity.com/paper/2509.09397/) (2025)
- [T3: Test-Time Model Merging in VLMs for Zero-Shot Medical Imaging Analysis](https://mlsanity.com/paper/2510.27265/) (2025)
- [The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy](https://mlsanity.com/paper/2607.11175/) (2026)
- [Stride-Net: Fairness-Aware Disentangled Representation Learning for Chest X-Ray Diagnosis](https://mlsanity.com/paper/2602.10875/) (2026)
- [Can Experts Adapt Without Training? On Test-Time Modality Generalization in MVLMs](https://mlsanity.com/paper/2607.16726/) (2026)
- [MedQ-Deg: A Multidimensional Benchmark for Evaluating MLLMs Across Medical Image Quality Degradations](https://mlsanity.com/paper/2603.07769/) (2026)
- [Assessing VLM Reliability for Medical Image Quality Evaluation Under Corruption and Bias](https://mlsanity.com/paper/2607.01973/) (2026)
- [Vertical Fusion: Condensing Internal Representations for Robust ViT Classification](https://mlsanity.com/paper/2607.10391/) (2026)
- [On the Robustness of Temporal Vision-Language Models for Surgical Endoscopy Videos](https://mlsanity.com/paper/2608.14262/) (2026)

## Abstract (arXiv)

Medical Vision-Language Models (MVLMs) have achieved par excellence generalization in medical image analysis, yet their performance under noisy, corrupted conditions remains largely untested. Clinical imaging is inherently susceptible to acquisition artifacts and noise; however, existing evaluations predominantly assess generally clean datasets, overlooking robustness -- i.e., the model's ability to perform under real-world distortions. To address this gap, we first introduce MediMeta-C, a corruption benchmark that systematically applies several perturbations across multiple medical imaging datasets. Combined with MedMNIST-C, this establishes a comprehensive robustness evaluation framework for MVLMs. We further propose RobustMedCLIP, a visual encoder adaptation of a pretrained MVLM that incorporates few-shot tuning to enhance resilience against corruptions. Through extensive experiments, we benchmark 5 major MVLMs across 5 medical imaging modalities, revealing that existing models exhibit severe degradation under corruption and struggle with domain-modality tradeoffs. Our findings highlight the necessity of diverse training and robust adaptation strategies, demonstrating that efficient low-rank adaptation when paired with few-shot tuning, improves robustness while preserving generalization across modalities.