Memory-Augmented Neural Networks

Follow this topic Ask about this topic

Memory-augmented neural networks study how models can store, retrieve, update, and forget information beyond what is held in their current activations or weights. Approaches include differentiable key-value and associative memories, recurrent state-space memories, memory tokens, and hierarchical working and long-term stores, often paired with attention or learned retrieval. These methods are evaluated on long-context recall and language modeling, continual learning, and temporal tasks such as video tracking, forecasting, and robot control. A central tension is how to make memory selective and useful over long horizons while keeping computation and storage bounded and avoiding interference, drift, or forgetting.

Latest papers

92 papers16 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

Streaming Recurrent Memory
Oct 26, 2026Mohamed Elsayed, Minh Pham, A. Rupam MahmoodRecurrent Neural Networks Memory-Augmented Neural Networks
Department of Computing Science, University of Alberta · CIFAR Canada AI Chair, Amii
Write What Matters: Disentangling Token Selection from Slot Allocation in Recurrent Memory
Oct 25, 2026Chen Chen, Rui ChengMemory-Augmented Neural Networks Long-Context Modeling
Hong Kong Baptist University · Anhui University
Engram Memory Network: Brain-Inspired Prototype Explanations
Oct 20, 2026Hyunjun Kim, Myoung Hoon HaPrototype-Based Explanation Explainable Image Classification
Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea · Center for Neuroscience-inspired AI, KAIST, Daejeon, South Korea
AnchorRM: Parallel Intra-Batch State Reconstruction with Anchor-Based Residual Memory for Temporal Graph Neural Networks
Oct 20, 2026Haroon Gharwi, Kai Shu, Yue DaiTemporal GNNs Memory-Augmented Neural Networks
Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA · Department of Computer Science, Emory University, Atlanta, GA, USA
Cross-Visibility-Gap Identity Persistence for 4D Scene Graphs
Oct 20, 2026Jiahui Hu, Li Gao, Yu Liu +14D Scene Understanding Multi-Object Tracking
Department of Computer Science, The University of Hong Kong · Chongqing University · Department of Computing, The Hong Kong Polytechnic University
Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration
Oct 15, 2026Wenju Sun, Qingyong Li, Boyang Li +4Task-Incremental Learning Incremental Learning
Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, China, 100044. · College of Computing and Data Science, Nanyang Technological University, Singapore, 639798. · Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry, Wuyi University, Fujian, China, 354300.
HEM-Med: A Hierarchical Agentic Memory Framework for Safe Multi-Center Medication Recommendation
Oct 14, 2026Min Xiao, Jin Li, Shoujin Wang +3Medication Recommendation Clinical Decision Support
Key Laboratory of Computing Power Network and Information Security, Ministry of Education; Shandong Computer Science Center (National Supercomputer Center in Jinan); Qilu University of Technology (Shandong Academy of Sciences); Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing; Shandong Fundamental Research Center for Computer Science, Jinan, Shandong, China · University of Technology Sydney
Engram Neuron Inspired Adaptive Memorization for Lifelong Learning
Oct 10, 2026Suiyang Jiang, Bomin Wang, Hangqi Zhou +2Continual Learning Memory-Augmented Neural Networks
School of Data Science, Fudan University, 220 Handan Road, Shanghai, 200433, China · Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, 220 Handan Road, Shanghai, 200433, China
Double-Take: Improving Capacity, Binding, and Selectivity In Long-Context Within Bidirectional Memory
Oct 9, 2026Vakul Raghavan, Utkarsh Grover, Mingyang Mao +2Long-Context Modeling Memory-Augmented Neural Networks
Department of Mathematics and Computer Science, Rutgers University, Newark, NJ, USA · Embodied Robotics and Automation Lab, University of South Florida, Tampa, FL, USA
MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers
Oct 8, 2026Jiuming Liu, Mengmeng Liu, Guangming Wang +6Point Cloud Registration Memory-Augmented Neural Networks
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University · University of Twente · University of Cambridge +2
Bridging KV-Cache Quantization and Linear Attention: From Theory to Pretrained Weight Migration
Oct 8, 2026Kaicheng Xiao, Liran Dong, Haotian Li +1Memory-Augmented Neural Networks KV-Cache Quantization
The Chinese University of Hong Kong
Continuous Memory Machines
Oct 6, 2026Ciaran Regan, Kai Arulkumaran, Luke Darlow +3Memory-Augmented Neural Networks Recurrent Neural Networks
University of Tsukuba · Sakana AI
Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks
Oct 2, 2026Maximilian Schlegel, Rajai Nasser, Seijin Kobayashi +6Deep Learning Optimization Memory-Augmented Neural Networks
Google, Paradigms of Intelligence Team, Zurich, Switzerland · MIT CSAIL, Cambridge, MA, USA · Department of Computer Science and Wu Tsai Institute, Yale University, New Haven, CT, USA
AIBL: Augmented Instance-Based Learning with Structured Memory and Neural Embeddings
Oct 2, 2026Radha Poovendran, Andrea Stocco, Linda BushnellOnline Continual Learning Memory-Augmented Neural Networks
University of Washington, Seattle, WA, 98195, USA.
MiLoop: Selective Memory Propagation for Neural Combinatorial Optimization
Oct 1, 2026Changliang Zhou, Yuanyao Chen, Rongsheng Chen +2Memory-Augmented Neural Networks RL for Combinatorial Optimization
School of Automation and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen, China · Guangdong Provincial Key Laboratory of Fully Actuated System Control Theory and Technology, Southern University of Science and Technology, Shenzhen, China · Pengcheng Laboratory, Shenzhen, China
Extreme Length Generalization in a Compact Recurrent Architecture for One-Shot Exploration
Oct 1, 2026Izen Thornton, Aaron Shey, William SuMemory-Augmented Neural Networks Recurrent Neural Networks
FRANK Autonomous Systems Inc., frankautonomous.com · University of California, Berkeley
NeurDuo-EEG: A Long-Sequence EEG Foundation Model with Persistent State and Explicit Memory
Sep 29, 2026Yifan Wang, Haiping Liu, Yang Cui +13Memory-Augmented Neural Networks Electroencephalography
University of Manchester · ETH Zürich · Shanghai Jiao Tong University +5
SchemaMem: Schema-Indexed Recurrent Memory for Delayed State Retrieval
Sep 27, 2026Sungwoo Goo, Hwi-yeol Yun, Sangkeun JungMemory-Augmented Neural Networks Persistent Memory for Language Models
College of Pharmacy, Chungnam National University Daejeon, Republic of Korea · Department of Computer Science & Engineering, Chungnam National University Daejeon, Republic of Korea
Structured Sparse Memory for Recurrent Reasoning
Sep 27, 2026Zixuan Zhao, Samuel Wheeler, Neil Getty +3Memory-Augmented Neural Networks Recurrent Neural Networks
Department of Computer Science University of Chicago Chicago, IL 60637 · Argonne National Laboratory Lemont, IL 60439
Online Task Adaptation via Self-Organisation
Sep 24, 2026Krsto ProrokovićNeural Cellular Automata Memory-Augmented Neural Networks
Independent Researcher Montenegro
Storing Is Not Remembering: LSTM-UT and Bounded Gated Memory for Looped Transformers
Sep 17, 2026Aras Kavuncu, Muhammad Burhan HafezMemory-Augmented Neural Networks Recurrent Transformers
University of Southampton, Electronics and Computer Science
Self-Evolving Memory for Generative Recommendation
Sep 14, 2026Xinyu Lin, Zhuosong Jiang, Zixiao Suo +12Memory-Augmented Neural Networks Recommender Systems
National University of Singapore · Meta AI
When the Gradient Sees Rank: Provable Necessity, Causal Recruitment, and Composition in Trained Matrix Memories
Sep 12, 2026Samuel LarsonAssociative Memory Memory-Augmented Neural Networks
Pebble ML
Does Video Memory Use What It Retrieves? A Causal Audit of Memory Specificity
Sep 10, 2026Aditi Tiwari, Akshit Bhalla, Darshan Prasad +1Memory-Augmented Neural Networks Causal Intervention
University of Illinois Urbana-Champaign · Adobe Research
Kalman Delta Networks: Uncertainty-aware Associative Memory
Sep 7, 2026Ngoc Bui, Tinglin Huang, Rex YingMemory-Augmented Neural Networks Linear Attention
Department of Computer Science, Yale University
Memory in Deep Time-Series Models
Sep 5, 2026Minh Hoang Nguyen, Huu Hiep Nguyen, Manh Nguyen +3Memory-Augmented Neural Networks Sequence Modeling
Deakin Applied AI Initiative, Deakin University, Geelong, VIC, Australia
TDDM-Melatt: A Decoupled Memory and Diffusion Framework for Generalizable Encrypted Traffic Classification
Aug 31, 2026Ze Chen, Qiming Yu, Zijia Song +2Memory-Augmented Neural Networks Disentangled Representation Learning
National University of Defense Technology Hefei, Anhui, China
Modality Disentangled Learning for Incomplete Multimodal Emotion Recognition: A Primitive Memory Distillation Perspective
Aug 31, 2026Jiaqi Zhang, Zheng Pang, Mengting Li +9Missing-Modality Learning Memory-Augmented Neural Networks
Jiangsu University · Griffith University · National University of Singapore +8
Kathleen Remembers: Length-Invariant One-Shot Recall Without Attention
Aug 31, 2026George FountzoulasMemory-Augmented Neural Networks Persistent Memory for Language Models
Department of Computer Engineering & Informatics Frederick University, Nicosia, Cyprus
The Von-Neumann State-Space Transformer for neural decoding
Aug 25, 2026Morteza SarafyazdTransformer Neural Decoding
BrainCo, Somerville, US.

Oct 26, 2026J/K move · Enter open · S save

Streaming Recurrent Memory

Mohamed Elsayed, Minh Pham, A. Rupam Mahmood

Department of Computing Science, University of Alberta · CIFAR Canada AI Chair, Amii

Recurrent Neural Networks Memory-Augmented Neural Networks Associative Memory

Open paper AskPDF arXiv

Natural intelligence learns from a continuous stream of sensorimotor experience: data can arrive at high bandwidth, and behavior adapts to feedback as soon as it arrives, even when it is delayed. In contrast, most modern deep learning systems rely on stored datasets, replay buffers, and retained contexts through which credit is later assigned. At high data rates, storing and revisiting past experience can be impractical under tight memory and computational constraints. This paper studies recurrent memory under a streaming learning constraint: the learner learns from experience as soon as it arrives without storing raw experience. We ask whether a streaming learner can maintain a state that remains useful for future prediction and control from delayed feedback. We introduce Streaming Recurrent Memory (SRM), a recurrent memory designed for the streaming setting which preserves information that may matter later while remaining trainable with one-step backpropagation through time (BPTT). SRM provides a streaming-compatible recurrence that is designed to recall past information by content or time, track elapsed steps, and compose transformations whose outcome depends on the order in which inputs are observed. Across controlled memory tasks and streaming applications, SRM learns effectively with one-step BPTT, outperforming recurrent baselines in associative recall and online language modeling while achieving near-perfect success in associative T-Maze with delayed rewards. These results suggest that fixing how inputs are stored in the recurrent state, while learning how that state is read out, enables effective streaming learning without long-range backpropagation.