集成记忆的可重构适配器：一种统一框架，适用于多任务设置
Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks
AI总结：
MIRA通过整合联想记忆与适配器调节，实现多任务设置中的快速任务切换和持久知识保留。
摘要：
生物体不断在逃避捕食者、觅食、穿越崎岖地形和社会化等任务之间切换，通常在毫秒内完成。令人惊叹的是，它们能够保留已学习环境的知识，而不会发生灾难性遗忘，这一现象神经科学家推测，是由于单一的神经回路动态叠加了如多巴胺和乙酰胆碱等神经调节剂。与此同时，深度学习研究通过领域泛化（DG）和持续学习（CL）解决类似挑战，但这些方法仍然孤立，尽管大脑可以无缝执行这些任务。特别是，先前的工作尚未探索涉及联想记忆（AMs）的架构，而这些是生物系统的重要组成部分，用于共同解决这些任务。我们提出Memory-Integrated Reconfigurable Adapters（MIRA），一种统一框架，它在共享骨干上集成了Hopfield风格的联想记忆模块。联想记忆键是在事后学习的，用于索引和检索任何给定任务或领域上的存储适配器更新的仿射组合，按样本进行。通过仅改变任务特定的目标，我们证明MIRA能够无缝适应领域转移和连续任务暴露。在标准基准上的实证评估证实，我们的AM增强架构显著提高了适应性和保留性：在DG中，MIRA实现了最先进的分布外准确性，在增量学习设置中，它优于专门设计处理灾难性遗忘的架构，使用通用CL算法。通过将基于适配器的调节与生物启发的联想记忆统一起来，MIRA在单一可扩展架构中实现了快速的任务切换和持久的知识保留，为更灵活和记忆增强的AI系统铺平了道路。
英文摘要：
Organisms constantly pivot between tasks such as evading predators, foraging, traversing rugged terrain, and socializing, often within milliseconds. Remarkably, they preserve knowledge of once-learned environments sans catastrophic forgetting, a phenomenon neuroscientists hypothesize, is due to a singular neural circuitry dynamically overlayed by neuromodulatory agents such as dopamine and acetylcholine. In parallel, deep learning research addresses analogous challenges via domain generalization (DG) and continual learning (CL), yet these methods remain siloed, despite the brains ability to perform them seamlessly. In particular, prior work has not explored architectures involving associative memories (AMs), which are an integral part of biological systems, to jointly address these tasks. We propose Memory-Integrated Reconfigurable Adapters (MIRA), a unified framework that integrates Hopfield-style associative memory modules atop a shared backbone. Associative memory keys are learned post-hoc to index and retrieve an affine combination of stored adapter updates for any given task or domain on a per-sample basis. By varying only the task-specific objectives, we demonstrate that MIRA seamlessly accommodates domain shifts and sequential task exposures under one roof. Empirical evaluations on standard benchmarks confirm that our AM-augmented architecture significantly enhances adaptability and retention: in DG, MIRA achieves SoTA out-of-distribution accuracy, and in incremental learning settings, it outperforms architectures explicitly designed to handle catastrophic forgetting using generic CL algorithms. By unifying adapter-based modulation with biologically inspired associative memory, MIRA delivers rapid task switching and enduring knowledge retention in a single extensible architecture, charting a path toward more versatile and memory-augmented AI systems.
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。
