稀疏光谱LoRA：用于医学VLMs的路由专家
Sparse Spectral LoRA: Routed Experts for Medical VLMs
AI总结：
本文提出MedQwen，一种参数高效的医学VLM，结合了光谱路由的专家混合（MoE）与理论支持的缩放规则，通过非重叠SVD段初始化专家，减少序列遗忘并提升医疗图像任务性能。
摘要：
大型视觉-语言模型（VLMs）在通用基准上表现优异，但在医学影像中常缺乏鲁棒性，异构监督导致跨数据集干扰和对数据制度（即监督信号混合方式）的敏感性。在真实临床工作流程中，数据和任务是按顺序到来的，因此朴素的持续训练进一步导致灾难性遗忘。为解决这些问题，我们提出了MedQwen，一种参数高效的医学VLM，将光谱路由的MoE与理论支持的缩放规则结合，使低秩更新与全秩、完全微调的MoE对齐，而无需改变基础架构。具体而言，我们从预训练权重的非重叠奇异值分解（SVD）段初始化每个专家，并引入残差补偿和缩放方案，以实现稳定的专家专业化和在分布偏移下的一致路由。在23个涵盖视觉问答、报告生成、放射学分类和幻觉缓解的医学数据集中，MedQwen实现了强大的、可靠的性能：它在零样本分类中以339倍更少的可训练参数接近完全微调，并将序列遗忘减少到约5%，而强大的基线在降级中减少超过20-50%。
英文摘要：
Large vision-language models (VLMs) excel on general benchmarks but often lack robustness in medical imaging, where heterogeneous supervision induces cross-dataset interference and sensitivity to data regime (i.e., how the supervisory signals are mixed). In realistic clinical workflows, data and tasks arrive sequentially, so naive continual training further leads to catastrophic forgetting. To address these challenges, we propose MedQwen, a parameter-efficient medical VLM that couples a spectrally routed Mixture-of-Experts (MoE) with a theoretically grounded scaling rule that aligns low-rank updates with a full-rank, fully fine-tuned MoE, without changing the base architecture. Concretely, we initialize each expert from non-overlapping singular value decomposition (SVD) segments of the pretrained weight and introduce a residual compensation and scaling scheme to enable stable expert specialization and consistent routing under distribution shift. Across 23 medical datasets covering visual question answering, report generation, radiology classification, and hallucination mitigation, MedQwen achieves strong, reliable performance: it approaches full fine-tuning on zero-shot classification with 339$\times$ fewer trainable parameters, and reduces sequential forgetting to $\sim$5\% where strong baselines degrade by $>$20-50\%.
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。
