Metraipolis › archive › dc_b6220da89ea4
MedUAG: Unified Understanding and Generation for Medical Multimodal Models — arXiv:2608.18937
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.18937
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T13:45:27.422Z
- SHA-256 of the archived text
4e2f28024111ba4bae73f18c4554d6bdcd8c75abb1d59afec6e9e91e0350a688- Stable URL of this page
https://metraipolis.com/documento/dc_b6220da89ea4
How to cite
MedUAG: Unified Understanding and Generation for Medical Multimodal Models — arXiv:2608.18937 — arXiv (en), https://arxiv.org/abs/2608.18937 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b6220da89ea4 (Metraipolis archive dc_b6220da89ea4, sha256 4e2f28024111ba4bae73f18c4554d6bdcd8c75abb1d59afec6e9e91e0350a688)
BibTeX
@misc{dcb6220da89ea4,
title = {MedUAG: Unified Understanding and Generation for Medical Multimodal Models — arXiv:2608.18937},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.18937},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b6220da89ea4; sha256 4e2f28024111ba4bae73f18c4554d6bdcd8c75abb1d59afec6e9e91e0350a688},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18937. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.18937 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T13:41:17.986Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).