锻造动态记忆：基于检索的持续学习用于通用医学基础模型
Forging a Dynamic Memory: Retrieval-Guided Continual Learning for Generalist Medical Foundation Models
AI总结：
本文提出基于检索的持续学习方法，通过动态知识蒸馏和RAG技术，解决多模态医学模型在领域迁移和细粒度特征保留中的核心难题。
摘要：
多模态生物医学视觉-语言模型（VLMs）在持续学习（CL）领域展现出巨大潜力。然而，它们面临一个核心困境：如何在保持细粒度模态内特征的同时，弥合不同模态之间的显著领域差距。为解决这一挑战，我们提出了一种综合框架。利用我们从PubMed科学论文中提取的1800万个多模态和全面的医学检索数据库，我们首次将检索增强生成（RAG）整合到持续学习中。具体而言，我们采用一个多模态、多层RAG系统，通过动态、按需的知识检索为模型微调提供实时指导。在此基础上，我们引入了一个动态知识蒸馏框架。该框架通过动态调节参数空间的重要性、蒸馏知识的粒度以及参考数据集的数据分布，精确解决上述核心困境。为了彻底验证我们策略的临床价值，我们设计了一个更严格的医学通用任务增量学习（MGTIL）基准。该基准旨在同时评估模型适应显著领域变化、保留细微领域特征以及实时学习新复杂医学任务的能力。广泛的实验结果表明，我们提出的方法在所有指标上均达到最先进的（SOTA）性能。代码见补充材料。
英文摘要：
Multimodal biomedical Vision-Language Models (VLMs) exhibit immense potential in the field of Continual Learning (CL). However, they confront a core dilemma: how to preserve fine-grained intra-modality features while bridging the significant domain gap across different modalities. To address this challenge, we propose a comprehensive framework. Leveraging our 18-million multimodal and comprehensive medical retrieval database derived from PubMed scientific papers, we pioneer the integration of Retrieval-Augmented Generation (RAG) into CL. Specifically, we employ a multi-modal, multi-layer RAG system that provides real-time guidance for model fine-tuning through dynamic, on-demand knowledge retrieval. Building upon this, we introduce a dynamic knowledge distillation framework. This framework precisely resolves the aforementioned core dilemma by dynamically modulating the importance of the parameter space, the granularity of the distilled knowledge, and the data distribution of the reference dataset in accordance with the required level of detail. To thoroughly validate the clinical value of our strategy, we have designed a more rigorous \textbf{M}edical Generalist Task Incremental Learning (MGTIL) benchmark. This benchmark is engineered to simultaneously evaluate the model's capacity for adaptation to significant domain shifts, retention of subtle intra-domain features, and real-time learning of novel and complex medical tasks. Extensive experimental results demonstrate that our proposed method achieves state-of-the-art (SOTA) performance across all metrics. The code is provided in the supplementary materials.
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。
