# Key-value memory in the brain

arXiv: https://arxiv.org/abs/2501.02950 · HTML: https://mlsanity.com/paper/2501.02950/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 139 references that are in the map.
- First posted on arXiv 6 Jan 2025.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Linear Transformers Are Secretly Fast Weight Programmers](https://mlsanity.com/paper/2102.11174/) (2021)
- [Hopfield Networks is All You Need](https://mlsanity.com/paper/2008.02217/) (2020)
- [Random Feature Attention](https://mlsanity.com/paper/2103.02143/) (2021)
- [Physics of Language Models: Part 3.1, Knowledge Storage and Extraction](https://mlsanity.com/paper/2309.14316/) (2023)
- [Dense Associative Memory for Pattern Recognition](https://mlsanity.com/paper/1606.01164/) (2016)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel](https://mlsanity.com/paper/1908.11775/) (2019)
- [Using Fast Weights to Attend to the Recent Past](https://mlsanity.com/paper/1610.06258/) (2016)
- [Relating transformers to models and neural representations of the hippocampal formation](https://mlsanity.com/paper/2112.04035/) (2021)
- [Learning to Encode Position for Transformer with Continuous Dynamical Model](https://mlsanity.com/paper/2003.09229/) (2020)
- [Universal Hopfield Networks: A General Framework for Single-Shot Associative Memory Models](https://mlsanity.com/paper/2202.04557/) (2022)
- [The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention](https://mlsanity.com/paper/2202.05798/) (2022)
- [Overparameterized Neural Networks Implement Associative Memory](https://mlsanity.com/paper/1909.12362/) (2019)
- [Biological learning in key-value memory networks](https://mlsanity.com/paper/2110.13976/) (2021)
- [Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed Scaffold](https://mlsanity.com/paper/2202.00159/) (2022)
- [Sparse Distributed Memory is a Continual Learner](https://mlsanity.com/paper/2303.11934/) (2023)

## Built on by (most cited first, 24 of 24)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [Liger: Linearizing Large Language Models to Gated Recurrent Structures](https://mlsanity.com/paper/2503.01496/) (2025)
- [Comba: Improving Bilinear RNNs with Closed-loop Control](https://mlsanity.com/paper/2506.02475/) (2025)
- [Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences](https://mlsanity.com/paper/2509.16189/) (2025)
- [Fast-weight Product Key Memory](https://mlsanity.com/paper/2601.00671/) (2026)
- [Fast weight programming and linear transformers: from machine learning to neurobiology](https://mlsanity.com/paper/2508.08435/) (2025)
- [Flexible Prefrontal Control over Hippocampal Episodic Memory for Goal-Directed Generalization](https://mlsanity.com/paper/2503.02303/) (2025)
- [Memorization and Knowledge Injection in Gated LLMs](https://mlsanity.com/paper/2504.21239/) (2025)
- [A Scenario-Driven Cognitive Approach to Next-Generation AI Memory](https://mlsanity.com/paper/2509.13235/) (2025)
- [Sharp Capacity Thresholds in Linear Associative Memory: From Top-1 Retrieval to Tail-Average Learning](https://mlsanity.com/paper/2605.05189/) (2026)
- [Sparse Attention as Compact Kernel Regression](https://mlsanity.com/paper/2601.22766/) (2026)
- [From Memories to Maps: Mechanisms of In-Context Reinforcement Learning in Transformers](https://mlsanity.com/paper/2506.19686/) (2025)
- [GENESIS: A Generative Model of Episodic-Semantic Interaction](https://mlsanity.com/paper/2510.15828/) (2025)
- [Why the Brain Consolidates: Predictive Forgetting for Optimal Generalisation](https://mlsanity.com/paper/2603.04688/) (2026)
- [HKVM-RAG: Key-Value-Separated Hypergraph Evidence Organization for Multi-Hop RAG](https://mlsanity.com/paper/2606.07218/) (2026)
- [Hebbian learning the local structure of language](https://mlsanity.com/paper/2503.02057/) (2025)
- [Echo State Transformer: Attention Over Finite Memories](https://mlsanity.com/paper/2507.02917/) (2025)
- [Dissociating model architectures from inference computations](https://mlsanity.com/paper/2507.15776/) (2025)
- [Memory Retrieval in Transformers: Insights from The Encoding Specificity Principle](https://mlsanity.com/paper/2601.20282/) (2026)
- [MemDefrag: Latent Memory Defragmentation for Large Language Models](https://mlsanity.com/paper/2607.05969/) (2026)
- [Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning](https://mlsanity.com/paper/2607.08393/) (2026)
- [Temporal Context Reinstatement Drives Episodic-Like Order Memory in Long-Context Language Models](https://mlsanity.com/paper/2607.22575/) (2026)
- [A neural network that maintains and retrieves memories based on context](https://mlsanity.com/paper/2609.37791/) (2026)
- [Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks](https://mlsanity.com/paper/2610.03858/) (2026)

## Abstract (arXiv)

Classical models of memory in psychology and neuroscience rely on similarity-based retrieval of stored patterns, where similarity is a function of retrieval cues and the stored patterns. While parsimonious, these models do not allow distinct representations for storage and retrieval, despite their distinct computational demands. Key-value memory systems, in contrast, distinguish representations used for storage (values) and those used for retrieval (keys). This allows key-value memory systems to optimize simultaneously for fidelity in storage and discriminability in retrieval. We review the computational foundations of key-value memory, its role in modern machine learning systems, related ideas from psychology and neuroscience, applications to a number of empirical puzzles, and possible biological implementations.