mlsanityData to 14 Oct 2026

MedUAG: Unified Understanding and Generation for Medical Multimodal Models

arXiv 2608.18937 ↗First posted 19 Aug 2026cs.CL cs.AIcited by 0

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

Abstract (arXiv)

Recent Multimodal Large Language Models (MLLMs) are rapidly evolving into unified understanding and generation (UAG) frameworks. However, extending these unified paradigms to the medical domain is hindered by: the absence of comprehensive training and evaluation benchmarks, and the lack of broadly validated unified medical model. To address these gaps, we present a comprehensive foundation for medical UAG. First, we construct MedUAGCorpus, the largest unified medical understanding and generation dataset to date, comprising over 6 million instances across 14 imaging modalities. Second, we introduce MedUAGBench, a systematic benchmark that expands medical generation evaluation to 12 diverse tasks under standardized protocols. Finally, leveraging these resources, we develop MedUAG, an end-to-end trained unified medical model. Extensive experiments demonstrate that MedUAG achieves strong performance across a wide array of understanding and generation tasks, establishing a competitive baseline and paving the way for next-generation medical multimodal systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 39 of its 56 references that are in the map. First posted on arXiv 19 Aug 2026.

Builds on

39 of 56 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation14 Feb
  2. 2024MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine6 Aug
  3. 2024OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM14 Feb
  4. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day1 Jun
  5. 2023BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks26 May

Other references · 34

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2022Flow Matching for Generative Modelingcited by 5,702
  6. 2025Qwen2.5-VL Technical Reportcited by 5,587
  7. 2013Auto-Encoding Variational Bayescited by 4,053
  8. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  9. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  10. 2025Qwen3-VL Technical Reportcited by 2,793
  11. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  12. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
22 more
  1. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 897
  2. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  3. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  4. 2023BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairscited by 520
  5. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 475
  6. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 470
  7. 2021SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answeringcited by 449
  8. 2025BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Datasetcited by 376
  9. 2024SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generationcited by 331
  10. 2020AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?cited by 224
  11. 2024CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formatscited by 106
  12. 2025Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understandingcited by 102
  13. 2025Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunitiescited by 85
  14. 2025UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generationcited by 66
  15. 2022BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pixcited by 61
  16. 2024ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image Datasetcited by 54
  17. 2023Adaptive Supervised PatchNCE Loss for Learning H&E-to-IHC Stain Translation with Inconsistent Groundtruth Image Pairscited by 38
  18. 2020OpenKBP: The open-access knowledge-based planning grand challengecited by 30
  19. 2025SynthRAD2025 Grand Challenge dataset: generating synthetic CTs for radiotherapycited by 28
  20. 2025UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysiscited by 12
  21. 2025Towards Interpretable Counterfactual Generation via Multimodal Autoregressioncited by 11
  22. 2025Automating RT Planning at Scale: High Quality Data For AI Trainingcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024MedViLaM: A multimodal large language model with advanced generalizability and explainability for medical data understanding and generation
  2. 2026MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Images
  3. 2025Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
  4. 2024Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks
  5. 2024PeFoMed: Parameter Efficient Fine-tuning of Multimodal Large Language Models for Medical Imaging
  6. 2025Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation
  7. 2025From large language models to multimodal AI: A scoping review on the potential of generative AI in medicine
  8. 2025MedGEN-Bench: A Contextually Entangled Benchmark for Open-ended Multimodal Medical Generation