# Neural Stored-program Memory

arXiv: https://arxiv.org/abs/1906.08862 · HTML: https://mlsanity.com/paper/1906.08862/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2019.

## Built on by (most cited first, 14 of 14)

- [Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed Scaffold](https://mlsanity.com/paper/2202.00159/) (2022)
- [Object-Centric Representation Learning for Video Question Answering](https://mlsanity.com/paper/2104.05166/) (2021)
- [Learning to Rehearse in Long Sequence Memorization](https://mlsanity.com/paper/2106.01096/) (2021)
- [Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers](https://mlsanity.com/paper/2105.07957/) (2021)
- [Learning Language Representations with Logical Inductive Bias](https://mlsanity.com/paper/2302.09458/) (2023)
- [Learning to Constrain Policy Optimization with Virtual Trust Region](https://mlsanity.com/paper/2204.09315/) (2022)
- [A Framework for Inference Inspired by Human Memory Mechanisms](https://mlsanity.com/paper/2310.09297/) (2023)
- [Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecasting](https://mlsanity.com/paper/2510.01206/) (2025)
- [State-Space Constraints Can Improve the Generalisation of the Differentiable Neural Computer to Input Sequences With Unseen Length](https://mlsanity.com/paper/2110.09138/) (2021)
- [Continual Fine-Tuning of Large Language Models via Program Memory](https://mlsanity.com/paper/2605.13162/) (2026)
- [Memory Capacity of Recurrent Neural Networks with Matrix Representation](https://mlsanity.com/paper/2104.07454/) (2021)
- [Functional Indirection Neural Estimator for Better Out-of-distribution Generalization](https://mlsanity.com/paper/2210.12739/) (2022)
- [Heterogenous Memory Augmented Neural Networks](https://mlsanity.com/paper/2310.10909/) (2023)
- [Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory](https://mlsanity.com/paper/2404.11870/) (2024)

## Abstract (arXiv)

Neural networks powered with external memory simulate computer behaviors. These models, which use the memory to store data for a neural controller, can learn algorithms and other complex tasks. In this paper, we introduce a new memory to store weights for the controller, analogous to the stored-program memory in modern computer architectures. The proposed model, dubbed Neural Stored-program Memory, augments current memory-augmented neural networks, creating differentiable machines that can switch programs through time, adapt to variable contexts and thus resemble the Universal Turing Machine. A wide range of experiments demonstrate that the resulting machines not only excel in classical algorithmic problems, but also have potential for compositional, continual, few-shot learning and question-answering tasks.