paper-with-me

Papers

Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics

2026-05-06 · Andreas Pattichis, Constantine Dovrolis arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.05097

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning

2026-04-14 · Jagadeesh Rachapudi, Ritali Vatsi, Praful Hambarde, Amit Shukla arxiv

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underscore the need for systems that can not only acquire new knowledge through Continual Learning (CL) but also remove outdated, sensitive, or private information through Machine Unlearn…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 Recognition

Meta-Learning Representations for Continual Learning

2019-05-29 · NeurIPS 2019 12 · Khurram Javed, Martha White

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-Learning

Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams

2026-03-08 · Jiyeon Kim, Hyunji Lee, Dylan Zhou, Sue Hyun Park 외 arxiv

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

2022-04-28 · Yang Yang, Zhiying Cui, Junjie Xu, Changhong Zhong 외

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+2

Multi-Scale Global-Instance Prompt Tuning for Continual Test-time Adaptation in Medical Image Segmentation

2026-02-05 · Lingrui Li, Yanfeng Zhou, Nan Pu, Xin Chen 외 arxiv

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