Working Memory

Latest papers

8 papers0 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

A neural network that maintains and retrieves memories based on context
Sep 29, 2026Hayoung Song, JeongJun Park, Qihong Lu +4Working Memory Episodic Memory
Department of Psychology, University of Texas at Austin · Center for Theoretical and Computational Neuroscience, Washington University in St. Louis · Department of Neuroscience, University of Texas at Austin +6
Oscillatory Phase Coding Emerges in Adaptive RNNs for Flexible Working Memory
Sep 28, 2026Kehan Lu, Tianhao Chu, Aiersi Tuerhong +4Working Memory Neural Encoding
Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China. · School of Psychological and Cognitive Sciences, Peking University, Beijing, China. · Peking University, Beijing, China.
Nested Episodic State Topology (NEST): A Graph-Theoretic Architecture of Cognitive States
Jul 7, 2026IshantCognitive Architectures for AI Agents Computational Cognitive Modeling
SCM: Sleep-Consolidated Memory with Algorithmic Forgetting for Large Language Models
Apr 22, 2026Saish Sachin ShindeMemory-Augmented Language Models Memorization in Language Models
Clyrai IP Studio
A Miniature Brain Transformer: Thalamic Gating, Hippocampal Lateralization, Amygdaloid Salience, and Prefrontal Working Memory in Attention-Coupled Latent Memory
Mar 7, 2026Hong JeongWorking Memory Memory-Augmented Neural Networks
Department of Computer Information Engineering, Inha University in Tashkent, Uzbekistan
Random matrix theory of sparse neuronal networks with heterogeneous timescales
Dec 14, 2025Thiparat Chotibut, Oleg Evnin, Weerawit HorinouchiRandom Matrix Theory Working Memory
Chula Intelligent and Complex Systems, Department of Physics, Faculty of Science, Chulalongkorn University, Bangkok, Thailand · High Energy Physics Research Unit, Faculty of Science, Chulalongkorn University, Bangkok, Thailand · Theoretische Natuurkunde, Vrije Universiteit Brussel (VUB) and International Solvay Institutes, Brussels, Belgium +2
Teaching signal synchronization in deep neural networks with prospective neurons
Nov 18, 2025Nicolas Zucchet, Qianqian Feng, Axel Laborieux +3Working Memory Neural Processes
Computer Science Department, ETH Zürich · Gatsby Computational Neuroscience Unit, University College London · Friedrich Miescher Institute for Biomedical Research +3
Reward function compression facilitates goal-dependent reinforcement learning
Sep 8, 2025Gaia Molinaro, Anne G. E. CollinsReinforcement Learning Working Memory
University of California, Berkeley Berkeley, CA 94704

Sep 29, 2026J/K move · Enter open · S save

A neural network that maintains and retrieves memories based on context

Hayoung Song, JeongJun Park, Qihong Lu, Giacomo Vedovati+3

Department of Psychology, University of Texas at Austin · Center for Theoretical and Computational Neuroscience, Washington University in St. Louis · Department of Neuroscience, University of Texas at Austin+6

Working Memory Episodic Memory Recurrent Neural Networks Neural Encoding

Open paper AskPDF arXiv

Every day, people continuously infer situational context and adjust the way they understand and remember the world. Context, signaled by the prefrontal cortex, is known to modulate working memory and episodic memory, but the algorithmic understanding of this modulation remains limited. Here, we train a recurrent neural network (RNN), augmented with an episodic memory buffer, to infer context using Bayesian inference as it continuously makes predictions of upcoming scenes while watching naturalistic movies. When the inferred context modulates the RNN's recurrent connectivity (the basis of working memory) in a low-rank manner, the model's activity patterns best match neural responses in human participants who watched the same movies during fMRI. Context also modulates episodic memory retrieval, such that the model retrieves memories based on not only content similarity but also context similarity. This is implemented as a key-value system with self-attention, designed to additionally encode context and retrieve context-congruent memories. The resulting model not only better resembles human brain representations but also learns to retrieve memories like humans much faster than a model without context modulation. Together, our findings suggest a computational mechanism by which context modulates information maintenance and long-term memory retrieval in naturalistic environments.