# Replay and compositional computation

arXiv: https://arxiv.org/abs/2209.07453 · HTML: https://mlsanity.com/paper/2209.07453/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2022.

## Built on by (most cited first, 8 of 8)

- [Provable Compositional Generalization for Object-Centric Learning](https://mlsanity.com/paper/2310.05327/) (2023)
- [ROSE: A Neurocomputational Architecture for Syntax](https://mlsanity.com/paper/2303.08877/) (2023)
- [Dreamweaver: Learning Compositional World Models from Pixels](https://mlsanity.com/paper/2501.14174/) (2025)
- [What is Intelligence? A Cycle Closure Perspective](https://mlsanity.com/paper/2404.05484/) (2024)
- [Ken Utilization Layer: Hebbian Replay Within a Student's Ken for Adaptive Exercise Recommendation](https://mlsanity.com/paper/2507.00032/) (2025)
- [High-resolution spatial memory requires grid-cell-like neural codes](https://mlsanity.com/paper/2507.00598/) (2025)
- [Lessons from Neuroscience for AI: How integrating Actions, Compositional Structure and Episodic Memory could enable Safe, Interpretable and Human-Like AI](https://mlsanity.com/paper/2512.22568/) (2025)
- [Rate-Coding Bundle Memory: A Unified Model of Memory and Control for Symbolic Computation in the Brain](https://mlsanity.com/paper/2608.29189/) (2026)

## Abstract (arXiv)

Replay in the brain has been viewed as rehearsal, or, more recently, as sampling from a transition model. Here, we propose a new hypothesis: that replay is able to implement a form of compositional computation where entities are assembled into relationally-bound structures to derive qualitatively new knowledge. This idea builds on recent advances in neuroscience which indicate that the hippocampus flexibly binds objects to generalizable roles and that replay strings these role-bound objects into compound statements. We suggest experiments to test our hypothesis, and we end by noting the implications for AI systems which lack the human ability to radically generalize past experience to solve new problems.