mlsanityData to 14 Oct 2026

MedGemma Technical Report

arXiv 2507.05201 ↗First posted 7 Jul 2025cs.AI cs.CL cs.CVcited by 436

Not on the map. Why?

Cited by 132 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Artificial intelligence (AI) has significant potential in healthcare applications, but its training and deployment faces challenges due to healthcare's diverse data, complex tasks, and the need to preserve privacy. Foundation models that perform well on medical tasks and require less task-specific tuning data are critical to accelerate the development of healthcare AI applications. We introduce MedGemma, a collection of medical vision-language foundation models based on Gemma 3 4B and 27B. MedGemma demonstrates advanced medical understanding and reasoning on images and text, significantly exceeding the performance of similar-sized generative models and approaching the performance of task-specific models, while maintaining the general capabilities of the Gemma 3 base models. For out-of-distribution tasks, MedGemma achieves 2.6-10% improvement on medical multimodal question answering, 15.5-18.1% improvement on chest X-ray finding classification, and 10.8% improvement on agentic evaluations compared to the base models. Fine-tuning MedGemma further improves performance in subdomains, reducing errors in electronic health record information retrieval by 50% and reaching comparable performance to existing specialized state-of-the-art methods for pneumothorax classification and histopathology patch classification. We additionally introduce MedSigLIP, a medically-tuned vision encoder derived from SigLIP. MedSigLIP powers the visual understanding capabilities of MedGemma and as an encoder achieves comparable or better performance than specialized medical image encoders. Taken together, the MedGemma collection provides a strong foundation of medical image and text capabilities, with potential to significantly accelerate medical research and development of downstream applications. The MedGemma collection, including tutorials and model weights, can be found at https://goo.gle/medgemma.

Key facts. Cited by 436 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Jul 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 93; 2026: 343.

436 papers.

Sort:

By area:

  1. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  2. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 77
  3. 2026MIRAGE: The Illusion of Visual Understandingcited by 65
  4. 2026MedGemma 1.5 Technical Reportcited by 45
  5. 2025A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontierscited by 37
  6. 2025MedVLThinker: Simple Baselines for Multimodal Medical Reasoningcited by 27
  7. 2025Pillar-0: A New Frontier for Radiology Foundation Modelscited by 25
  8. 2025Automating Expert-Level Medical Reasoning Evaluation of Large Language Modelscited by 22
  9. 2025EHR-R1: A Reasoning-Enhanced Foundational Language Model for Electronic Health Record Analysiscited by 18
  10. 2025Med-CMR: A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic for Medical Complex Multimodal Reasoningcited by 14
  11. 2025UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysiscited by 12
  12. 2026MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolutioncited by 12
38 more
  1. 2025HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Researchcited by 11
  2. 2025S-Chain: Structured Visual Chain-of-Thought For Medicinecited by 11
  3. 2025OralGPT-Omni: A Versatile Dental Multimodal Large Language Modelcited by 11
  4. 2026Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Makingcited by 11
  5. 2025MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precisioncited by 10
  6. 2025End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoningcited by 10
  7. 2025OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoningcited by 10
  8. 2025Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMscited by 10
  9. 2026IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentationcited by 10
  10. 2026OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysiscited by 10
  11. 2025Improving Generative Ad Text on Facebook using Reinforcement Learningcited by 9
  12. 2025Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbationscited by 9
  13. 2025Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Maskscited by 9
  14. 2025Evolving Interactive Diagnostic Agents in a Virtual Clinical Environmentcited by 9
  15. 2025Revisiting 2D Foundation Models for Scalable 3D Medical Image Classificationcited by 9
  16. 2026ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretationcited by 9
  17. 2026CRIMSON: A Clinically-Grounded LLM-Based Metric for Generative Radiology Report Evaluationcited by 9
  18. 2025Agentic AI framework for End-to-End Medical Data Inferencecited by 8
  19. 2025Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoningcited by 8
  20. 2025RadAgents: Multimodal Agentic Reasoning for Chest X-ray Interpretation with Radiologist-like Workflowscited by 8
  21. 2025Shallow Robustness, Deep Vulnerabilities: Multi-Turn Evaluation of Medical LLMscited by 8
  22. 2025Reasoning Visual Language Model for Chest X-Ray Analysiscited by 8
  23. 2025OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Taskscited by 8
  24. 2026EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learningcited by 8
  25. 2026MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learningcited by 8
  26. 2026ATPO: Adaptive Tree Policy Optimization for Multi-Turn Medical Dialoguecited by 8
  27. 2025Multi-step retrieval and reasoning improves radiology question answering with large language modelscited by 7
  28. 2025Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AIcited by 7
  29. 2025Grounding Large Language Models in Clinical Evidence: A Retrieval-Augmented Generation System for Querying UK NICE Clinical Guidelinescited by 7
  30. 2025CXRAgent: Director-Orchestrated Multi-Stage Reasoning for Chest X-Ray Interpretationcited by 7
  31. 2025SurgViVQA: Temporally-Grounded Video Question Answering for Surgical Scene Understandingcited by 7
  32. 2026PathReasoner-R1: Instilling Structured Reasoning into Pathology Vision-Language Model via Knowledge-Guided Policy Optimizationcited by 7
  33. 2026MediX-R1: Open Ended Medical Reinforcement Learningcited by 7
  34. 2026BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidencecited by 7
  35. 2026PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide Image VQAcited by 7
  36. 2025Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoningcited by 6
  37. 2025CLARITY: Medical World Model for Guiding Treatment Decisions by Simulating Context-Aware Disease Trajectoriescited by 6
  38. 2025RadImageNet-VQA: A Large-Scale CT and MRI Dataset for Radiologic Visual Question Answeringcited by 6

50 most cited of 436 All 436 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025MedGemma vs GPT-4: Open-Source and Proprietary Zero-shot Medical Disease Classification from Images
  2. 2025MedBLINK: Probing Basic Perception in Multimodal Language Models for Medicine
  3. 2024MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models
  4. 2025MedAtlas: Evaluating LLMs for Multi-Round, Multi-Task Medical Reasoning Across Diverse Imaging Modalities and Clinical Text
  5. 2026PSF-Med: Measuring and Explaining Paraphrase Sensitivity in Medical Vision Language Models
  6. 2025MedBookVQA: A Systematic and Comprehensive Medical Benchmark Derived from Open-Access Book
  7. 2024MedViLaM: A multimodal large language model with advanced generalizability and explainability for medical data understanding and generation
  8. 2024MedPix 2.0: A Comprehensive Multimodal Biomedical Data set for Advanced AI Applications with Retrieval Augmented Generation and Knowledge Graphs