mlsanityData to 7 Oct 2026

MedGemma 1.5 Technical Report

arXiv 2604.05081 ↗First posted 6 Apr 2026cs.AIcited by 43

Not on the map. Why?

Cited by 20 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce MedGemma 1.5 4B, the latest model in the MedGemma collection. MedGemma 1.5 expands on MedGemma 1 by integrating additional capabilities: high-dimensional medical imaging (CT/MRI volumes and histopathology whole slide images), anatomical localization via bounding boxes, multi-timepoint chest X-ray analysis, and improved medical document understanding (lab reports, electronic health records). We detail the innovations required to enable these modalities within a single architecture, including new training data, long-context 3D volume slicing, and whole-slide pathology sampling. Compared to MedGemma 1 4B, MedGemma 1.5 4B demonstrates significant gains in these new areas, improving 3D MRI condition classification accuracy by 11% and 3D CT condition classification by 3% (absolute improvements). In whole slide pathology imaging, MedGemma 1.5 4B achieves a 47% macro F1 gain. Additionally, it improves anatomical localization with a 35% increase in Intersection over Union on chest X-rays and achieves a 4% macro accuracy for longitudinal (multi-timepoint) chest x-ray analysis. Beyond its improved multimodal performance over MedGemma 1, MedGemma 1.5 improves on text-based clinical knowledge and reasoning, improving by 5% on MedQA accuracy and 22% on EHRQA accuracy. It also achieves an average of 18% macro F1 on 4 different lab report information extraction datasets (EHR Datasets 2, 3, 4, and Mendeley Clinical Laboratory Test Reports). Taken together, MedGemma 1.5 serves as a robust, open resource for the community, designed as an improved foundation on which developers can create the next generation of medical AI systems. Resources and tutorials for building upon MedGemma 1.5 can be found at https://goo.gle/medgemma.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). Builds on 23 of its 36 references that are in the map. First posted on arXiv 6 Apr 2026.

Builds on

23 of 36 references.

References · 23

  1. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  2. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  3. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  4. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  5. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,271
  6. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  7. 2022MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answeringcited by 525
  8. 2021SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answeringcited by 444
  9. 2025MedGemma Technical Reportcited by 398
  10. 2021RadGraph: Extracting Clinical Entities and Relations from Radiology Reportscited by 310
  11. 2025MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understandingcited by 212
  12. 2023Learning to Exploit Temporal Structure for Biomedical Vision-Language Processingcited by 210
11 more
  1. 2016Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)cited by 197
  2. 2024Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomographycited by 192
  3. 2019A deep learning system for differential diagnosis of skin diseasescited by 118
  4. 2024Advancing Multimodal Medical Capabilities of Geminicited by 88
  5. 2023MAIRA-1: A specialised large multimodal model for radiology report generationcited by 72
  6. 2018Development and Validation of a Deep Learning Algorithm for Improving Gleason Scoring of Prostate Cancercited by 34
  7. 2024EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summariescited by 33
  8. 2024AfriMed-QA: A Pan-African, Multi-Specialty, Medical Question-Answering Benchmark Datasetcited by 26
  9. 2023Consensus, dissensus and synergy between clinicians and specialist foundation models in radiology report generationcited by 12
  10. 2025CoCa-CXR: Contrastive Captioners Learn Strong Temporal Structures for Chest X-Ray Vision-Language Understandingcited by 11
  11. 2025PolyPath: Adapting a Large Multimodal Model for Multi-slide Pathology Report Generationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 43.

43 papers.

Sort:

By area:

  1. 2026Large Language Models Lack Temporal Awareness of Medical Knowledgecited by 2
  2. 2026PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?cited by 2
  3. 2026Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensemblescited by 1
  4. 2026Does Language Shift Break Medical Vision-Language Models? Indonesian Radiology Visual Question Answering Case Studycited by 1
  5. 2026Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiabilitycited by 1
  6. 2026ReportQA: QA-Based Radiology Report Evaluationcited by 1
  7. 2026CheXpercept: A Benchmark for Evaluating Expert-Level Lesion Perception in Chest X-rayscited by 1
  8. 2026RadSight: Towards Perceptually Reliable Multimodal Radiology Image Understandingcited by 1
  9. 2026Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generationcited by 1
  10. 2026RadMatch: Auditable Radiology Report Evaluation via Finding-Level Matchingcited by 1
  11. 2026The Cost of Language: Centroid Erasure Exposes and Exploits Modal Competition in Multimodal Language Modelscited by 0
  12. 2026Rethinking Patient Education as Multi-turn Multi-modal Interactioncited by 0
31 more
  1. 2026EHR-RAGp: Retrieval-Augmented Prototype-Guided Foundation Model for Electronic Health Recordscited by 0
  2. 2026How Seemingly Inconsequential Design Choices Dictate Performance of LLMs in Pathologycited by 0
  3. 2026Probing, Fusion, and Trustworthiness: A Systematic Evaluation of Foundation Model Representations for Multimodal Cancer Analysiscited by 0
  4. 2026TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimizationcited by 0
  5. 2026Towards Real-World Ultrasound Understanding: Large Vision-Language Models from Multi-Image Examinations with Long-Form Reportscited by 0
  6. 2026Auditing Evidence Use in Medical LLM Diagnosiscited by 0
  7. 2026Objective-Aligned Direct Answer SFT for Robust Multi-Frame Medical VQAcited by 0
  8. 2026MedSAM2-Anatomy: Training-Free Inference-Time Optimization for Musculoskeletal Segmentationcited by 0
  9. 2026A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generationcited by 0
  10. 2026Adaptive Arena-based Contestable Argumentative Network-of-Experts for Open-Ended Care Plan Coordinationcited by 0
  11. 2026ELICITED: EHR-grounded Longitudinal Interactive Conversations for Information-seeking Triage Evaluation and Decision-makingcited by 0
  12. 2026PathoArgus: Advancing Evidence-Grounded Long-Context Visual Reasoning across Gigapixel Whole-Slide and Multi-Slide Case Contextscited by 0
  13. 2026Volumetric Radiology AI in the Era of Multimodal Large Language Modelscited by 0
  14. 2026An end-to-end-trained vision-language model for native-language prostate pathology report generationcited by 0
  15. 2026CheXGround: Anatomical Region Tokens for Grounded Longitudinal Chest X-ray Interpretationcited by 0
  16. 2026MedQA-MM: Shortcuts Behind Medical Visual Reasoningcited by 0
  17. 2026Separating Capability from Confidence: Grounded Dual-State Calibration for GRPO-Trained Medical Vision-Language Modelscited by 0
  18. 2026Two-Stage Mixture-of-LoRA for Multi-Task Medical Vision-Language Learningcited by 0
  19. 2026MedTRACE: Tool-Augmented Multimodal Clinical Reasoning Agents for Evidence-Grounded Decision-Makingcited by 0
  20. 2026Rethinking Correctness for Uncertainty Estimation in Clinical Prediction with Vision-Language Modelscited by 0
  21. 2026ECG Mirage: Revealing and Mitigating the Underutilisation of ECGs in Vision-Language Models for Clinical Predictioncited by 0
  22. 2026Authority-Preserving Evaluation of Medical Vision-Language Assistantscited by 0
  23. 2026NV-Reason-CT: 3D Visual Language Model for CT Analysiscited by 0
  24. 2026EyeVQA: Benchmarking Ophthalmic Vision-Language Models from Recognition to Spatial Groundingcited by 0
  25. 2026FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMscited by 0
  26. 2026XFlow: A Workflow Model for Instruction-Guided Lesion Segmentation in Chest X-rayscited by 0
  27. 2026From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoningcited by 0
  28. 2026Learning Where to Look: Anatomical Grounding and Guided Attention for Cardiac MRI Vision-Language Modelscited by 0
  29. 2026CineMR: Tool-Integrated Vision-Language Reasoning for Quantitative Cardiac MRI Assessmentcited by 0
  30. 2026Geometry-Supervised Visual Representation Learning for Multi-Phenotype Lesion Interpretation in Medical VLMscited by 0
  31. 2026DeltaRepresentation: Geometry Supervised Representation Learning of Phenotypes via Counterfactual Reasoning for Medical VLMscited by 0