Paper Detail

MedUAG: Unified Understanding and Generation for Medical Multimodal Models

Zijie Meng, Yuncheng Zhang, Hualiang Wang, Yitian Tang, Xiaotang Gai, Chen Shen, Songtao Jiang, Shaosheng Cao, Jian Wu, Xian Wu, Zuozhu Liu

arxiv Score 18.3

Published 2026-08-19 · First seen 2026-08-20

General AI

Abstract

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{meng2026meduag,
  title = {MedUAG: Unified Understanding and Generation for Medical Multimodal Models},
  author = {Zijie Meng and Yuncheng Zhang and Hualiang Wang and Yitian Tang and Xiaotang Gai and Chen Shen and Songtao Jiang and Shaosheng Cao and Jian Wu and Xian Wu and Zuozhu Liu},
  year = {2026},
  abstract = {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},
  url = {https://arxiv.org/abs/2608.18937},
  keywords = {cs.CL, cs.AI},
  eprint = {2608.18937},
  archiveprefix = {arXiv},
}

Metadata

{}