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

• URL: http://arxiv.org/abs/2601.00426v1
• Date: Thu, 01 Jan 2026 18:34:06 GMT
• Title: RMAAT: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformers
• Authors: Md Zesun Ahmed Mia, Malyaban Bal, Abhronil Sengupta,
• Abstract summary: This work explores computational principles derived from astrocytes-glial cells critical for biological memory and synaptic modulation.<n>We introduce the Recurrent Memory Augmented Transformer (RMAAT), an architecture integrating astrocyte functionalities.
• Score: 11.099872871193028
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• From Complex Dynamics to DynFormer: Rethinking Transformers for PDEs [6.873342825786888]
  Transformer-based neural operators have emerged as powerful data-driven alternatives.<n>We propose DynFormer, a novel dynamics-informed neural operator.<n>We show that DynFormer achieves up to a 95% reduction in relative error compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-03T15:45:09Z)
• Memory Caching: RNNs with Growing Memory [56.25483647131372]
  We introduce Memory Caching (MC), a technique that enhances recurrent models by caching checkpoints of memory states (a.k.a. hidden states)<n>We propose four variants of MC, including gated aggregation and sparse selective mechanisms, and discuss their implications on both linear and deep memory modules.<n>The results indicate that while Transformers achieve the best accuracy, our MC variants show competitive performance, close the gap with Transformers, and performs better than state-of-the-art recurrent models.
  arXiv  Detail & Related papers  (2026-02-27T18:53:41Z)
• Parallel Delayed Memory Units for Enhanced Temporal Modeling in Biomedical and Bioacoustic Signal Analysis [17.73662095849247]
  Parallel Delayed Memory Unit (PDMU) is a delay-gated state-space module for short-term temporal credit assignment.<n>PDMU enhances short-term temporal state interactions and memory efficiency via a gated delay-line mechanism.<n>PDMU supports parallel training and sequential inference, and can be easily integrated into existing linear RNN frameworks.
  arXiv  Detail & Related papers  (2025-12-01T12:46:56Z)
• The Curious Case of In-Training Compression of State Space Models [49.819321766705514]
  State Space Models (SSMs) tackle long sequence modeling tasks efficiently, offer both parallelizable training and fast inference.<n>Key design challenge is striking the right balance between maximizing expressivity and limiting this computational burden.<n>Our approach, textscCompreSSM, applies to Linear Time-Invariant SSMs such as Linear Recurrent Units, but is also extendable to selective models.
  arXiv  Detail & Related papers  (2025-10-03T09:02:33Z)
• High-Fidelity Scientific Simulation Surrogates via Adaptive Implicit Neural Representations [51.90920900332569]
  Implicit neural representations (INRs) offer a compact and continuous framework for modeling spatially structured data.<n>Recent approaches address this by introducing additional features along rigid geometric structures.<n>We propose a simple yet effective alternative: Feature-Adaptive INR (FA-INR)
  arXiv  Detail & Related papers  (2025-06-07T16:45:17Z)
• Dynamic Memory-enhanced Transformer for Hyperspectral Image Classification [3.5093938502961763]
  Hyperspectral image (HSI) classification remains a challenging task due to the intricate spatial-spectral correlations.<n>Existing transformer models excel in capturing long-range dependencies but often suffer from information redundancy and attention inefficiencies.<n>MemFormer introduces a memory-enhanced multi-head attention mechanism that iteratively refines a dynamic memory module.<n>A dynamic memory enrichment strategy progressively captures complex spatial and spectral dependencies, leading to more expressive feature representations.
  arXiv  Detail & Related papers  (2025-04-17T17:43:34Z)
• Model Hemorrhage and the Robustness Limits of Large Language Models [119.46442117681147]
  Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment.<n>We define this phenomenon as model hemorrhage - performance decline caused by parameter alterations and architectural changes.
  arXiv  Detail & Related papers  (2025-03-31T10:16:03Z)
• ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer [58.49950218437718]
  We present ReCoM, an efficient framework for generating high-fidelity and generalizable human body motions synchronized with speech.<n>The core innovation lies in the Recurrent Embedded Transformer (RET), which integrates Dynamic Embedding Regularization (DER) into a Vision Transformer (ViT) core architecture.<n>To enhance model robustness, we incorporate the proposed DER strategy, which equips the model with dual capabilities of noise resistance and cross-domain generalization.
  arXiv  Detail & Related papers  (2025-03-27T16:39:40Z)
• Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model [55.116403765330084]
  Current AIGC methods, such as score-based diffusion, are still deficient in terms of rapidity and efficiency. We propose a time-continuous and analog in-memory neural differential equation solver for score-based diffusion. We experimentally validate our solution with 180 nm resistive memory in-memory computing macros.
  arXiv  Detail & Related papers  (2024-04-08T16:34:35Z)
• Estimation of Energy-dissipation Lower-bounds for Neuromorphic Learning-in-memory [5.073292775065559]
  An ideal neuromorphic neurally-inspired neurally-equilibriums rely on local but parallel parameter updates to solve problems that range from quadratic programming to Ising machines.<n>An analysis presented in this paper captures the out-of- thermodynamics of learning and the resulting energy-efficiency estimates are model-agnostic.<n>To show practical applicability of our results, we apply our analysis for estimating the lower-bound on the energy-to-solution metrics for large-scale AI workloads.
  arXiv  Detail & Related papers  (2024-02-21T21:02:11Z)
• Recurrent Action Transformer with Memory [39.58317527488534]
  This paper proposes a novel model architecture that incorporates a recurrent memory mechanism designed to regulate information retention. We conduct experiments on memory-intensive environments (ViZDoom-Two-Colors, T-Maze, Memory Maze, Minigrid-Memory), classic Atari games, and MuJoCo control environments. The results show that using memory can significantly improve performance in memory-intensive environments, while maintaining or improving results in classic environments.
  arXiv  Detail & Related papers  (2023-06-15T19:29:08Z)
• Transformer-based Planning for Symbolic Regression [18.90700817248397]
  We propose TPSR, a Transformer-based Planning strategy for Symbolic Regression. Unlike conventional decoding strategies, TPSR enables the integration of non-differentiable feedback, such as fitting accuracy and complexity. Our approach outperforms state-of-the-art methods, enhancing the model's fitting-complexity trade-off, Symbolic abilities, and robustness to noise.
  arXiv  Detail & Related papers  (2023-03-13T03:29:58Z)
• Memformer: A Memory-Augmented Transformer for Sequence Modeling [55.780849185884996]
  We present Memformer, an efficient neural network for sequence modeling. Our model achieves linear time complexity and constant memory space complexity when processing long sequences.
  arXiv  Detail & Related papers  (2020-10-14T09:03:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.