# RMAAT: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformers

arXiv: https://arxiv.org/abs/2601.00426 · HTML: https://mlsanity.com/paper/2601.00426/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 1 Jan 2026.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [Long Range Arena: A Benchmark for Efficient Transformers](https://mlsanity.com/paper/2011.04006/) (2020)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)
- [Gated Linear Attention Transformers with Hardware-Efficient Training](https://mlsanity.com/paper/2312.06635/) (2023)
- [Nystr"omformer: A Nystr"om-Based Algorithm for Approximating Self-Attention](https://mlsanity.com/paper/2102.03902/) (2021)
- [Random Feature Attention](https://mlsanity.com/paper/2103.02143/) (2021)
- [FNet: Mixing Tokens with Fourier Transforms](https://mlsanity.com/paper/2105.03824/) (2021)
- [Recurrent Memory Transformer](https://mlsanity.com/paper/2207.06881/) (2022)
- [Luna: Linear Unified Nested Attention](https://mlsanity.com/paper/2106.01540/) (2021)
- [Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity](https://mlsanity.com/paper/2002.10585/) (2020)
- [Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks](https://mlsanity.com/paper/2302.14311/) (2023)
- [Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets](https://mlsanity.com/paper/1901.09049/) (2019)
- [P-SpikeSSM: Harnessing Probabilistic Spiking State Space Models for Long-Range Dependency Tasks](https://mlsanity.com/paper/2406.02923/) (2024)
- [Neuron-Astrocyte Associative Memory](https://mlsanity.com/paper/2311.08135/) (2023)
- [Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs](https://mlsanity.com/paper/2302.03235/) (2023)
- [Delving Deeper Into Astromorphic Transformers](https://mlsanity.com/paper/2312.10925/) (2023)

## Built on by (most cited first, 1 of 1)

- [Energy-Aware Spike Budgeting for Continual Learning in Spiking Neural Networks for Neuromorphic Vision](https://mlsanity.com/paper/2602.12236/) (2026)

## Abstract (arXiv)

The quadratic complexity of self-attention mechanism presents a significant impediment to applying Transformer models to long sequences. This work explores computational principles derived from astrocytes-glial cells critical for biological memory and synaptic modulation-as a complementary approach to conventional architectural modifications for efficient self-attention. We introduce the Recurrent Memory Augmented Astromorphic Transformer (RMAAT), an architecture integrating abstracted astrocyte functionalities. RMAAT employs a recurrent, segment-based processing strategy where persistent memory tokens propagate contextual information. An adaptive compression mechanism, governed by a novel retention factor derived from simulated astrocyte long-term plasticity (LTP), modulates these tokens. Attention within segments utilizes an efficient, linear-complexity mechanism inspired by astrocyte short-term plasticity (STP). Training is performed using Astrocytic Memory Replay Backpropagation (AMRB), a novel algorithm designed for memory efficiency in recurrent networks. Evaluations on the Long Range Arena (LRA) benchmark demonstrate RMAAT's competitive accuracy and substantial improvements in computational and memory efficiency, indicating the potential of incorporating astrocyte-inspired dynamics into scalable sequence models.