Tensor Memory: Fixed-Size Recurrent State for Long-Horizon Transformers

• URL: http://arxiv.org/abs/2605.27686v1
• Date: Tue, 26 May 2026 21:03:42 GMT
• Title: Tensor Memory: Fixed-Size Recurrent State for Long-Horizon Transformers
• Abstract summary: Transformers process images and videos by flattening space and time into long token sequences.<n>While attention and KV caching preserve past features, their memory grows with sequence length and they lack an explicit, persistent spatial state.<n>We propose a lightweight module that augments Transformer blocks with a fixed-size recurrent 3D memory.
• Score: 20.67103891489219
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformers process images and videos by flattening space and time into long token sequences. While attention and KV caching preserve past features, their memory grows with sequence length and they lack an explicit, persistent spatial state, making long-horizon video understanding and occlusion-sensitive reasoning difficult. We propose Tensor Memory, a lightweight module that augments Transformer blocks with a fixed-size recurrent 3D memory tensor: tokens write into a voxel grid via a differentiable soft write that deposits content as a Gaussian-weighted volume around a predicted continuous 3D location, the memory is updated with an efficient local interaction operator and gated recurrent dynamics, and tokens read back context via continuous sampling with gated residual fusion. Because the memory tensor has a constant size, Tensor Memory decouples state capacity from input length while preserving a spatial inductive bias. We evaluate the module on standard language, image, and video benchmarks and on a controlled toy diagnostic suite designed to isolate when persistent state is beneficial; it integrates with standard Transformer training pipelines and can be attached to or removed from existing blocks without other architectural changes.

Related papers

• Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation [89.70897512515477]
  Action-controlled image-to-video generation is a promising paradigm for interactive world simulation, where each control signal should elicit an immediate visual response.<n>Maintaining visual fidelity and 3D consistency over long autoregressive rollouts remains challenging.<n>Existing 3D-aware methods often suffer from catastrophic drift due to two impediments: information loss from textitLatent--RGB Cycling, and the training--inference gap induced by the textiterror-free hypothesis.<n>We present textbfRobust Dreamer, a memory-augmented framework built around how to
  arXiv  Detail & Related papers  (2026-05-29T05:21:33Z)
• Rethinking Memory as Continuously Evolving Connectivity [63.58181883607843]
  Existing memory-augmented LLM agents treat memory as a static repository with pre-defined representations and fixed retrieval pipelines.<n>We propose FluxMem, a connectivity-evolving memory framework that models memory as a heterogeneous graph and progressively refines its topology through three stages.<n>Across three fundamentally distinct benchmarks including LoCoMo, Mind2Web, and GAIA, FluxMem achieves consistent state-of-the-art performance, demonstrating strong adaptation and generalization in complex agentic environments.
  arXiv  Detail & Related papers  (2026-05-27T17:35:34Z)
• Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior [107.2098567818173]
  Latent Recurrent Transformer (LRT) is a lightweight augmentation of autoregressive transformers.<n>LRT reuses a high-level source-layer hidden state from the previous token as recurrent memory for the next token.
  arXiv  Detail & Related papers  (2026-05-26T10:10:26Z)
• Adaptive Memory Decay for Log-Linear Attention [1.0099625992507715]
  Sequence models face a fundamental tradeoff between memory capacity and computational efficiency.<n>Log-linear attention navigates this tradeoff by organizing memory across a Fenwick tree hierarchy.<n>We propose learning directly from the input via a lightweight two-layer, producing per-token, per-level decay that adapts to content rather than position.
  arXiv  Detail & Related papers  (2026-05-07T21:05:28Z)
• CAWN: Continuous Acoustic Wave Networks for Autoregressive Language Modeling [46.16066322190728]
  We introduce the Continuous Acoustic Wave Network (CAWN), a fully continuous sequence-mixing architecture.<n>Instead of discrete matrix-based attention, CAWN projects hidden states into multi-headed complex-domain phasors.<n>To prevent signal degradation over ultra-long contexts, we introduce a dual-gated Selective Phase Resonance mechanism.
  arXiv  Detail & Related papers  (2026-04-05T20:13:22Z)
• 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)
• S$^3$-Attention:Attention-Aligned Endogenous Retrieval for Memory-Bounded Long-Context Inference [11.779449360037518]
  We present S3-Attention, a memory-first inference-time framework that treats long-context processing as attention-aligned endogenous retrieval.<n>S3-Attention decodes transient key and query projections into top-k sparse feature identifiers using lightweight sparse autoencoders.<n>It constructs a CPU-based inverted index mapping features to token positions or spans during a single streaming scan.
  arXiv  Detail & Related papers  (2026-01-25T05:25:22Z)
• Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning [53.72709564555407]
  Memo is a transformer-based architecture and training recipe for reinforcement learning.<n>It incorporates the creation and retrieval of memory by interleaving periodic summarization tokens with the inputs of a model during training.<n>We demonstrate Memo's effectiveness on a gridworld meta-RL benchmark and a multi-object navigation task in photo-realistic indoor settings.
  arXiv  Detail & Related papers  (2025-10-22T16:24:47Z)
• Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache [67.47789629197857]
  We propose a training-free framework that exploits the heterogeneous roles of transformer head dimensions.<n>By projecting the long-context-insensitive dimensions onto Fourier bases, FourierAttention approximates their temporal evolution with fixed-length spectral coefficients.<n>We show that FourierAttention achieves the best long-context accuracy on LongBench and Needle-In-A-Haystack.
  arXiv  Detail & Related papers  (2025-06-13T15:35:54Z)
• Breaking Quadratic Barriers: A Non-Attention LLM for Ultra-Long Context Horizons [0.0]
  We present a novel non attention based architecture for large language models (LLMs) that efficiently handles very long context windows.<n>Unlike traditional Transformer designs, which suffer from quadratic memory and overload due to the nature of the self attention mechanism, our model avoids token to token attention entirely.
  arXiv  Detail & Related papers  (2025-05-09T00:25:46Z)
• LaMemo: Language Modeling with Look-Ahead Memory [50.6248714811912]
  We propose Look-Ahead Memory (LaMemo) that enhances the recurrence memory by incrementally attending to the right-side tokens. LaMemo embraces bi-directional attention and segment recurrence with an additional overhead only linearly proportional to the memory length. Experiments on widely used language modeling benchmarks demonstrate its superiority over the baselines equipped with different types of memory.
  arXiv  Detail & Related papers  (2022-04-15T06:11:25Z)

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.