GeoStack: 一种用于视觉语言模型中近阿贝尔知识组合的框架
GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs
AI总结：
GeoStack通过几何约束和结构约束确保基础模型知识保留，实现常数时间推理，有效缓解灾难性遗忘。
摘要：
我们解决了视觉语言模型（VLMs）中知识组合的挑战，其中在多个领域或任务中积累专业知识通常会导致灾难性遗忘。我们引入GeoStack（几何堆叠），一种模块化框架，允许独立训练的领域专家被组合成一个统一模型。通过在适配器流形上施加几何和结构约束，GeoStack确保基础模型的基础知识得以保留。此外，我们数学上证明了权重折叠性质，实现了无论集成专家数量如何均保持常数时间推理复杂度（O(1)）。在多领域适应和类增量学习中的实验结果表明，GeoStack提供了一种高效的长期知识组合机制，同时显著减轻了灾难性遗忘。代码可在https://github.com/QuantitativeImagingLaboratory/GeoStack获取。
英文摘要：
We address the challenge of knowledge composition in Vision-Language Models (VLMs), where accumulating expertise across multiple domains or tasks typically leads to catastrophic forgetting. We introduce GeoStack (Geometric Stacking), a modular framework that allows independently trained domain experts to be composed into a unified model. By imposing geometric and structural constraints on the adapter manifold, GeoStack ensures the foundational knowledge of the base model is preserved. Furthermore, we mathematically demonstrate a weight-folding property that achieves constant-time inference complexity ($O(1)$), regardless of the number of integrated experts. Experimental results across multi-domain adaptation and class-incremental learning show that GeoStack provides an efficient mechanism for long-term knowledge composition while significantly mitigating catastrophic forgetting. Code is available at https://github.com/QuantitativeImagingLaboratory/GeoStack.
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。
