Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics
LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled multi-timescale dynamics make new associations immediately usable, strengthen what repetition confirms, and let the rest fade. We argue that external memory should follow a similar principle. In Memini, this view takes the form of an associative memory that organizes knowledge as a directed graph. Each edge carries two coupled internal variables, one fast and one slow, following the Benna-Fusi model of synaptic consolidation. From this coupling, episodic sensitivity, gradual consolidation, and selective forgetting are expected to emerge as facets of a single mechanism, reframing external memory as a learning substrate that reorganizes through its own dynamics. This workshop article describes an early-stage conceptual design without experimental evaluation.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning
Recent advances in deep learning underscore the need for systems that can not only acquire new knowledge through Continual Learning (CL) but also remove outdated, sensitive, or private information through Machine Unlearn…
Continual LearningFace RecognitionMeta-Learning Representations for Continual Learning
A continual learning agent should be able to build on top of existing knowledge to learn on new data quickly while minimizing forgetting. Current intelligent systems based on neural network function approximators arguabl…
Continual LearningMeta-LearningCan Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams
LLMs operating in dynamic real-world contexts often encounter knowledge that evolves continuously or emerges incrementally. To remain accurate and effective, models must adapt to newly arriving information on the fly. We…
Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor
Deep learning has shown its human-level performance in various applications. However, current deep learning models are characterised by catastrophic forgetting of old knowledge when learning new classes. This poses a cha…
class-incremental learningClass Incremental LearningContinual Learningimage-classification+2Multi-Scale Global-Instance Prompt Tuning for Continual Test-time Adaptation in Medical Image Segmentation
Distribution shift is a common challenge in medical images obtained from different clinical centers, significantly hindering the deployment of pre-trained semantic segmentation models in real-world applications across mu…
Medical Image SegmentationSemantic SegmentationTest-time Adaptation