mlsanityData to 7 Oct 2026

MAIRA-1: A specialised large multimodal model for radiology report generation

arXiv 2311.13668 ↗First posted 22 Nov 2023cs.CL cs.AI cs.CVcited by 72

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

Abstract (arXiv)

We present a radiology-specific multimodal model for the task for generating radiological reports from chest X-rays (CXRs). Our work builds on the idea that large language model(s) can be equipped with multimodal capabilities through alignment with pre-trained vision encoders. On natural images, this has been shown to allow multimodal models to gain image understanding and description capabilities. Our proposed model (MAIRA-1) leverages a CXR-specific image encoder in conjunction with a fine-tuned large language model based on Vicuna-7B, and text-based data augmentation, to produce reports with state-of-the-art quality. In particular, MAIRA-1 significantly improves on the radiologist-aligned RadCliQ metric and across all lexical metrics considered. Manual review of model outputs demonstrates promising fluency and accuracy of generated reports while uncovering failure modes not captured by existing evaluation practices. More information and resources can be found on the project website: https://aka.ms/maira.

Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 29 of its 48 references that are in the map. First posted on arXiv 22 Nov 2023.

Builds on

29 of 48 references.

References · 29

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  4. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  5. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  6. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  7. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  8. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 590
  9. 2023OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Modelscited by 560
  10. 2013Generating Sequences With Recurrent Neural Networkscited by 549
  11. 2023Med-Flamingo: a Multimodal Medical Few-shot Learnercited by 387
  12. 2020Generating Radiology Reports via Memory-driven Transformercited by 363
17 more
  1. 2022Making the Most of Text Semantics to Improve Biomedical Vision--Language Processingcited by 336
  2. 2020CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERTcited by 329
  3. 2021RadGraph: Extracting Clinical Entities and Relations from Radiology Reportscited by 310
  4. 2023Learning to Exploit Temporal Structure for Biomedical Vision-Language Processingcited by 210
  5. 2018TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rayscited by 139
  6. 2020Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generationcited by 139
  7. 2023Interactive and Explainable Region-guided Radiology Report Generationcited by 139
  8. 2019Clinically Accurate Chest X-Ray Report Generationcited by 138
  9. 2022Improving Chest X-Ray Report Generation by Leveraging Warm Startingcited by 93
  10. 2023PromptMRG: Diagnosis-Driven Prompts for Medical Report Generationcited by 92
  11. 2021Chest ImaGenome Dataset for Clinical Reasoningcited by 89
  12. 2022Improving the Factual Correctness of Radiology Report Generation with Semantic Rewardscited by 82
  13. 2023ELIXR: Towards a general purpose X-ray artificial intelligence system through alignment of large language models and radiology vision encoderscited by 49
  14. 2022Improving Radiology Report Generation Systems by Removing Hallucinated References to Non-existent Priorscited by 48
  15. 2023Radiology-GPT: A Large Language Model for Radiologycited by 44
  16. 2023Multimodal Image-Text Matching Improves Retrieval-based Chest X-Ray Report Generationcited by 37
  17. 2023Style-Aware Radiology Report Generation with RadGraph and Few-Shot Promptingcited by 28

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 30; 2025: 27; 2026: 14.

72 papers.

Sort:

By area:

  1. 2024Capabilities of Gemini Models in Medicinecited by 231
  2. 2025Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoningcited by 217
  3. 2024MAIRA-2: Grounded Radiology Report Generationcited by 140
  4. 2024CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formatscited by 100
  5. 2024Advancing Multimodal Medical Capabilities of Geminicited by 88
  6. 2024Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancementcited by 66
  7. 2025Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Keycited by 64
  8. 2024Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluationcited by 51
  9. 2024MedImageInsight: An Open-Source Embedding Model for General Domain Medical Imagingcited by 45
  10. 2026MedGemma 1.5 Technical Reportcited by 43
  11. 2025RadGPT: Constructing 3D Image-Text Tumor Datasetscited by 34
  12. 2025A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontierscited by 34
38 more
  1. 2024Dia-LLaMA: Towards Large Language Model-driven CT Report Generationcited by 32
  2. 2024Libra: Leveraging Temporal Images for Biomedical Radiology Analysiscited by 29
  3. 2024Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Taskscited by 24
  4. 2025RadVLM: A Multitask Conversational Vision-Language Model for Radiologycited by 24
  5. 2024An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generationcited by 23
  6. 2024Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Surveycited by 20
  7. 2025CT-Agent: A Multimodal-LLM Agent for 3D CT Radiology Question Answeringcited by 20
  8. 2024Overview of the First Shared Task on Clinical Text Generation: RRG24 and "Discharge Me!"cited by 19
  9. 2024ChEX: Interactive Localization and Region Description in Chest X-rayscited by 18
  10. 2024FineRadScore: A Radiology Report Line-by-Line Evaluation Technique Generating Corrections with Severity Scorescited by 18
  11. 2024A Survey on Trustworthiness in Foundation Models for Medical Image Analysiscited by 16
  12. 2024M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretationcited by 16
  13. 2025Multimodal Large Language Models for Medicine: A Comprehensive Surveycited by 16
  14. 2024LLM-RadJudge: Achieving Radiologist-Level Evaluation for X-Ray Report Generationcited by 14
  15. 2026MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Imagescited by 12
  16. 2024CXR-Agent: Vision-language models for chest X-ray interpretation with uncertainty aware radiology reportingcited by 11
  17. 2024FactCheXcker: Mitigating Measurement Hallucinations in Chest X-ray Report Generation Modelscited by 11
  18. 2024LLM-RG4: Flexible and Factual Radiology Report Generation across Diverse Input Contextscited by 11
  19. 2024DeViDe: Faceted medical knowledge for improved medical vision-language pre-trainingcited by 10
  20. 2024ReXErr: Synthesizing Clinically Meaningful Errors in Diagnostic Radiology Reportscited by 9
  21. 2024SERPENT-VLM : Self-Refining Radiology Report Generation Using Vision Language Modelscited by 8
  22. 2025A Multimodal Multi-Agent Framework for Radiology Report Generationcited by 8
  23. 2025Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoningcited by 8
  24. 2024Pre-training on High Definition X-ray Images: An Experimental Studycited by 7
  25. 2024GPT-4V Cannot Generate Radiology Reports Yetcited by 7
  26. 2025Foundation Models in Medical Imaging: A Review and Outlookcited by 7
  27. 2024A Survey of Deep Learning-based Radiology Report Generation Using Multimodal Datacited by 6
  28. 2024ReXamine-Global: A Framework for Uncovering Inconsistencies in Radiology Report Generation Metricscited by 5
  29. 2025SilVar-Med: A Speech-Driven Visual Language Model for Explainable Abnormality Detection in Medical Imagingcited by 5
  30. 2025Data Scaling Laws for Radiology Foundation Modelscited by 4
  31. 2025A Review of Longitudinal Radiology Report Generation: Dataset Composition, Methods, and Performance Evaluationcited by 3
  32. 2025PETAR: Localized Findings Generation with Mask-Aware Vision-Language Modeling for PET Automated Reportingcited by 3
  33. 2026CWCD: Category-Wise Contrastive Decoding for Structured Medical Report Generationcited by 3
  34. 2025Insights into a radiology-specialised multimodal large language model with sparse autoencoderscited by 2
  35. 2025Clinically Grounded Agent-based Report Evaluation: An Interpretable Metric for Radiology Report Generationcited by 2
  36. 2025Automated Structured Radiology Report Generation with Rich Clinical Contextcited by 2
  37. 2025Vision-Language Models for Automated 3D PET/CT Report Generationcited by 2
  38. 2025Reflective Preference Optimization (RPO): Enhancing On-Policy Alignment via Hint-Guided Reflectioncited by 2

50 most cited of 72 All 72 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024MAIRA-Seg: Enhancing Radiology Report Generation with Segmentation-Aware Multimodal Large Language Models
  2. 2025A Generative Framework for Bidirectional Image-Report Understanding in Chest Radiography
  3. 2024Gla-AI4BioMed at RRG24: Visual Instruction-tuned Adaptation for Radiology Report Generation
  4. 2023MedXChat: A Unified Multimodal Large Language Model Framework towards CXRs Understanding and Generation
  5. 2025Any-to-Any Vision-Language Model for Multimodal X-ray Imaging and Radiological Report Generation
  6. 2025Exploring the Capabilities of Large Language Model Encoders for Image-Text Retrieval in Chest X-rays
  7. 2024Multimodal Large Language Model driven Radiology Report Generation with Clinical Knowledge Enhancement
  8. 2026Harrison.Rad 1.5 Technical Report: A radiology foundation model that can draft reports from images, priors and clinical context