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.

翻译：生物体能够在毫秒级时间内灵活切换任务，如躲避捕食者、觅食、穿越崎岖地形及社交活动，同时能保持对已学习环境的记忆而避免灾难性遗忘。神经科学家推测，这一现象源于单一神经回路在神经调节物质（如多巴胺和乙酰胆碱）作用下动态叠加调控。与此同时，深度学习研究通过领域泛化（DG）与持续学习（CL）应对类似挑战，但这些方法仍相互隔离，未能复现大脑无缝整合的能力。值得注意的是，现有研究尚未探索利用生物系统中不可或缺的联想记忆（AM）架构来协同处理这些任务。本文提出记忆集成可重构适配器（MIRA），这是一个在共享主干网络上集成霍普菲尔德式联想记忆模块的统一框架。联想记忆键通过后验学习实现按样本索引，并检索存储适配器更新的仿射组合，以适配任意任务或领域。仅通过调整任务特定目标，我们证明MIRA能在一个架构内无缝适应领域偏移与序列化任务暴露。在标准基准测试中的实证评估表明，增强联想记忆的架构显著提升了适应性与记忆保持能力：在领域泛化中，MIRA取得了最先进的分布外准确率；在增量学习场景中，其性能优于采用通用持续学习算法、专门设计用于缓解灾难性遗忘的架构。通过将基于适配器的调制机制与受生物启发的联想记忆相融合，MIRA在单一可扩展架构中实现了快速任务切换与持久知识保持，为开发更具通用性与记忆增强能力的人工智能系统开辟了新路径。