arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.00842cs.CL
收藏

MedGPT-oss: 为生物医学训练一个通用的视觉-语言模型

MedGPT-oss: Training a General-Purpose Vision-Language Model for Biomedicine

Department of Computer Science and Engineering, Lehigh University(莱斯大学计算机科学与工程系);Department of Computer Science and Engineering, University of Notre Dame(圣母大学计算机科学与工程系);Department of Health Outcomes & Biomedical Informatics, University of Florida(佛罗里达大学健康结果与生物医学信息学系);Department of Radiation Oncology, Mayo Clinic(梅奥诊所放射肿瘤科);Research Computing, University of Florida(佛罗里达大学研究计算中心);AI Technology Center, NVIDIA(NVIDIA人工智能技术中心)

Kai Zhang, Zhengqing Yuan, Cheng Peng, Songlin Zhao, Mengxian Lyu, Ziyi Chen, Yanfang Ye, Wei Liu, Ying Zhang, Kaleb E Smith, Lifang He, Lichao Sun, Yonghui Wu

AI总结:

MEDGPT-oss是一款开放式权重的200亿参数视觉-语言模型,通过优化训练课程实现多模态和文本推理能力,适用于隐私保护的临床AI研究。

摘要:

生物医学多模态助手有望统一放射学、病理学和临床文本推理,但仍然存在关键的部署缺口:表现最佳的系统要么是闭源的,要么计算上不可行,这阻止了在患者隐私和PHI合规性要求下所需的本地部署。我们介绍了MEDGPT-OSS,一个开放式权重、200亿参数的通用视觉-语言模型,旨在促进临床AI的开放研究。而不是依赖架构复杂性,MEDGPT-OSS通过优化的三阶段训练课程将GPT-oss语言骨干与视觉前端配对。通过严格的数据整理和长上下文多模态对齐,逐步域适应这些模块,我们证明一个200亿参数的模型可以弥补能力缺口。它在分布外(OOD)多模态推理和复杂的纯文本临床任务上均优于更大的开放医疗模型。通过在单一指令遵循接口下统一各种模态,MEDGPT-OSS保持了参数高效的足迹,完全兼容商用GPU。我们发布了完整的训练配方、开放式权重检查点和严谨的评估工具,以作为隐私保护、机构特定临床AI研究的可验证基础。

英文摘要:

Biomedical multimodal assistants have the potential to unify radiology, pathology, and clinical-text reasoning, yet a critical deployment gap remains: top-performing systems are either closed-source or computationally prohibitive, precluding the on-premises deployment required for patient privacy and PHI compliance. We introduce MEDGPT-OSS, an open-weight, 20B-parameter generalist vision-language model designed to facilitate open research in clinical AI. Rather than relying on architectural complexity, MEDGPT-OSS pairs the GPT-oss language backbone with a visual front-end via a optimized, three-stage training curriculum. By progressively domain-adapting these modules through rigorous data curation and long-context multimodal alignment, we demonstrate that a 20B model can bridge the capacity gap. It successfully outperforms larger open medical models on out-of-distribution (OOD) multimodal reasoning and complex text-only clinical tasks. By unifying diverse modalities under a single instruction-following interface, MEDGPT-OSS maintains a parameter-efficient footprint fully compatible with commodity GPUs. We release the complete training recipe, open-weight checkpoints, and a rigorous evaluation harness to serve as a verifiable foundation for privacy-preserving, institution-specific clinical AI research.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑