mlsanityData to 7 Oct 2026

Medical vision-language models

947 papers6 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: medical, clinical, vision-language, image, performance

Key facts. Medical vision-language models: 947 papers on arXiv since 2021 (data through 7 Oct 2026). 272 of its 947 mapped papers (29%) cite “LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day” (2023, arXiv 2306.00890). 74 of its 947 mapped papers (8%) cite “OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM” (2024, arXiv 2402.09181). 33 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

33 new papers, 17 Sep – 7 Oct; 6 this week.

  1. This week · 6
  2. DeltaRepresentation: Geometry Supervised Representation Learning of Phenotypes via Counterfactual Reasoning for Medical VLMs
  3. Geometry-Supervised Visual Representation Learning for Multi-Phenotype Lesion Interpretation in Medical VLMs
  4. HeiCo-FOCUS: A Clinically Grounded Dataset for Long-Context Video Understanding
  5. Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI
  6. Knee3DVLM: Dual-Sequence Full-Volume Vision-Language Modeling for Comprehensive Knee MRI Assessment
  7. MedPrune: Topology-Efficient Multimodal Multi-Agent Communication Evolution for Medical VQA Tasks
  8. Earlier · 27
  9. Localization Lens for Improving Medical Vision-Language Models
  10. Reliability Stress Tests and Decision-Time Routing for Chest X-ray Vision-Language Models
  11. Ranking-Aware Prompt Optimization for Multimodal Clinical Diagnosis
  12. Learning Where to Look: Anatomical Grounding and Guided Attention for Cardiac MRI Vision-Language Models
All 33
  1. CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models also fits: VLM benchmarks and visual reasoning
  2. SAM Meets VLM: Parameter-Decoupled Full-Parameter Training for Unified Medical Reasoning and Segmentation
  3. How Medical VLMs Underutilize Their Vision Encoders: A Dermatology Perspective
  4. Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity
  5. EyeVQA: Benchmarking Ophthalmic Vision-Language Models from Recognition to Spatial Grounding
  6. Medical Image Alignment Assessment as a Test of Generalist Visual Reasoning in Frontier Multimodal Models
  7. SentZero: An Enhanced Sentence-Centric Vision-Language Pretraining for Multi-Task Zero-Shot Chest X-Ray Analysis
  8. Clinical Trajectory Alignment for Medical Vision-Language Pre-training
  9. FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs
  10. Contamination, Prior, or Evidence? Decomposing and Training Evidence Use in Whole-Slide Vision-Language Models
  11. Does Vision-Language Pretraining Granularity Matter? A Controlled Evaluation of Vision-Language Objectives Across Chest X-Ray Interpretation Tasks
  12. Enhancing Visual Reasoning in Chest X-Ray Report Generation Using Reinforcement Learning
  13. From Reward Signal to Visual Utility: A Controlled Audit of Medical VLM Post-Training
  14. ViSTA: A Simple Bridge Extends Visual Alignment to Clinical Time-Series Understanding in Multimodal LLMs
  15. UltraG-Bench: A Multi-task Benchmark for assessing Large Vision-Language Models on Pixel-level Evidence Grounding in Ultrasound
  16. Med-AR: Autoregressive Vision-Language Pretraining for Long-Tailed Chest X-Ray Classification and Uncertainty-Aware Evaluation
  17. FFM-CP: Cross-Backbone Fusion of Vision-Language Foundation Models for Few-Shot Computational Pathology
  18. NV-Reason-CT: 3D Visual Language Model for CT Analysis
  19. SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models also fits: Visual token pruning and efficiency
  20. Representation-guided in-context learning for medical image interpretation with multimodal large language models
  21. QwenVLConnector: A Fast, Unified Medical VLM Chatbot for Fine-Grained Clinical Perception and Text Generation
  22. GPEC: Efficient Pre-LLM Gaussian Process Embedding Correction for Cardiac Video Caption Generation
  23. Beyond Benchmark Scores: Auditing Medical Vision-Language Models for Chest X-Ray Tuberculosis Screening

Foundations

Most cited by papers here

  1. LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day2023cited by 272 here
  2. OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM2024cited by 74 here
  3. HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale2024cited by 68 here
  4. Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning2025cited by 67 here
  5. MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning2025cited by 59 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 35 here
  2. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 73 here
  3. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 28 here
  4. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 30 here
  5. 2024CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Modelscited by 23 here
  6. 2024HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scalecited by 68 here
  7. 2025HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptationcited by 32 here
17 more it builds on, not in this chain
  1. 2021Learning to Prompt for Vision-Language Modelscited by 30 here
  2. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 26 here
  3. 2023BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Taskscited by 34 here
  4. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 272 here
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 68 here
  6. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 39 here
  7. 2024OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLMcited by 74 here
  8. 2024Vision-Language Models for Medical Report Generation and Visual Question Answering: A Reviewcited by 26 here
  9. 2024M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Modelscited by 44 here
  10. 2024MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicinecited by 35 here
  11. 2024GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AIcited by 31 here
  12. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 52 here
  13. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 23 here
  14. 2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learningcited by 59 here
  15. 2025Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Modelscited by 45 here
  16. 2025Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoningcited by 67 here
  17. 2025Qwen3-VL Technical Reportcited by 37 here

The 24 most cited of 1,104.

Browse

30 of 947, ranked 6–35

  1. 6Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models202545
  2. 7M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models202444
  3. 8MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine202435
  4. 9BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks202334
  5. 10HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation202532
  6. 11GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI202431
  7. 12Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review202426
  8. 13CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models202423
  9. 14XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models202322
  10. 15Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding202521
All 30
  1. 16Merlin: A Computed Tomography Vision-Language Foundation Model and Dataset202420
  2. 17VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge202419
  3. 18A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision202319
  4. 19PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology202418
  5. 20Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis202517
  6. 21MedBLIP: Bootstrapping Language-Image Pre-training from 3D Medical Images and Texts202316
  7. 22Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study202216
  8. 23MultiMedEval: A Benchmark and a Toolkit for Evaluating Medical Vision-Language Models202415
  9. 24PathAsst: A Generative Foundation AI Assistant Towards Artificial General Intelligence of Pathology202315
  10. 25M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimization202315
  11. 26CXR-CLIP: Toward Large Scale Chest X-ray Language-Image Pre-training202315
  12. 27MAIRA-1: A specialised large multimodal model for radiology report generation202315
  13. 28Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training202115
  14. 29MMedAgent: Learning to Use Medical Tools with Multi-modal Agent202414
  15. 30RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models202413
  16. 31Qilin-Med-VL: Towards Chinese Large Vision-Language Model for General Healthcare202313
  17. 32BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature202512
  18. 33EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery202512
  19. 34SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding202412
  20. 35Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine202412