Graph Memory Transformer (GMT)

• URL: http://arxiv.org/abs/2604.23862v1
• Date: Sun, 26 Apr 2026 20:09:25 GMT
• Title: Graph Memory Transformer (GMT)
• Abstract summary: Graph Memory Transformer (GMT) routes token representations over a learned bank of centroids connected by a learned directed transition matrix.<n>Base v7 model trains stably and exposes centroid usage, transition structure, and source-to-target movement.<n>Results are not intended as a state-of-the-art claim; they support the viability and structural interpretability of replacing dense within-token transformation with graph-mediated memory navigation.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We investigate whether the Feed-Forward Network (FFN) sublayer in a decoder-only transformer can be replaced by an explicit learned memory graph while preserving the surrounding autoregressive architecture. The proposed Graph Memory Transformer (GMT) keeps causal self-attention intact, but replaces the usual per-token FFN transformation with a memory cell that routes token representations over a learned bank of centroids connected by a learned directed transition matrix. In the base GMT v7 instantiation studied here, each of 16 transformer blocks contains 128 centroids, a 128 * 128 edge matrix, gravitational source routing, token-conditioned target selection, and a gated displacement readout. The cell therefore returns movement from an estimated source memory state toward a target memory state, rather than a retrieved value. The resulting model is a fully decoder-only language model with 82.2M trainable parameters and no dense FFN sublayers, compared with a 103.0M-parameter dense GPT-style baseline used in the evaluation. The base v7 model trains stably and exposes centroid usage, transition structure, and source-to-target movement as directly inspectable quantities of the forward computation. It remains behind the larger dense baseline in validation loss and perplexity (3.5995/36.58 vs. 3.2903/26.85), while showing close zero-shot benchmark behavior under the evaluated setting. These results are not intended as a state-of-the-art claim; they support the viability and structural interpretability of replacing dense within-token transformation with graph-mediated memory navigation. Broader scaling, optimized kernels, and more extensive benchmark evaluation are left for subsequent work.

Related papers

• CLEAR-MoE: Shared-Basis Expert Extraction from Frozen Vision Transformers via Calibration-Driven Layer Selection [0.0]
  CLEAR-MoE is a post-training pipeline that converts a frozen pretrained Vision Transformer (ViT) into a sparse Mixture-of-Experts (MoE) model without updating backbone weights.<n>On a GTX 960, routing and scatter-gather overhead make the CLEAR-MoE FFN 1.3-1.7x slower than the dense routers.
  arXiv  Detail & Related papers  (2026-06-26T18:12:03Z)
• Tensor Memory: Fixed-Size Recurrent State for Long-Horizon Transformers [20.67103891489219]
  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.
  arXiv  Detail & Related papers  (2026-05-26T21:03:42Z)
• Hierarchical Transformer Preconditioning for Interactive Physics Simulation [28.137076331332413]
  Hierarchical Transformer Preconditioner, a neural preconditioner anchored to a weak-admissibility H-matrix partition.<n>Network models the inverse through low-rank far-field factors.<n>Uses highway connections to propagate context across depth sparse.
  arXiv  Detail & Related papers  (2026-05-13T11:02:27Z)
• The Compute ICE-AGE: Invariant Compute Envelope under Addressable Graph Evolution [0.0]
  This paper presents empirical results from a production-grade C++ implementation of a deterministic semantic state substrate.<n>System was mathematically specified prior to implementation and realized as a CPU-resident graph engine.<n>Results indicate an empirically invariant thermodynamic regime in which scaling is governed by memory capacity rather than inference-bound recomposition.
  arXiv  Detail & Related papers  (2026-02-17T20:57:34Z)
• LINA: Linear Autoregressive Image Generative Models with Continuous Tokens [56.80443965097921]
  Autoregressive models with continuous tokens form a promising paradigm for visual generation, especially for text-to-image (T2I) synthesis.<n>We study how to design compute-efficient linear attention within this framework.<n>We present LINA, a simple and compute-efficient T2I model built entirely on linear attention, capable of generating high-fidelity 1024x1024 images from user instructions.
  arXiv  Detail & Related papers  (2026-01-30T06:44:33Z)
• Breaking the Memory Wall: Exact Analytical Differentiation via Tiled Operator-Space Evolution [3.551701030393209]
  Phase Gradient Flow (PGF) is a framework that computes exact analytical derivatives by operating directly in the state-space manifold.<n>Our method delivers O(1) memory complexity relative to sequence length, yielding a 94% reduction in peak VRAM and a 23x increase in throughput compared to standard Autograd.<n>Our work enables chromosome-scale sensitivity analysis on a single GPU, bridging the gap between theoretical infinite-context models and practical hardware limitations.
  arXiv  Detail & Related papers  (2025-12-28T20:27:58Z)
• Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation [84.00166854547241]
  Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention.<n>We propose SVG2, a training-free framework that maximizes identification accuracy and computation minimizes waste.
  arXiv  Detail & Related papers  (2025-05-24T21:30:29Z)
• Variable-size Symmetry-based Graph Fourier Transforms for image compression [65.7352685872625]
  We propose a new family of Symmetry-based Graph Fourier Transforms of variable sizes into a coding framework. Our proposed algorithm generates symmetric graphs on the grid by adding specific symmetrical connections between nodes. Experiments show that SBGFTs outperform the primary transforms integrated in the explicit Multiple Transform Selection.
  arXiv  Detail & Related papers  (2024-11-24T13:00:44Z)
• Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss [59.835032408496545]
  We propose a tile-based strategy that partitions the contrastive loss calculation into arbitrary small blocks. We also introduce a multi-level tiling strategy to leverage the hierarchical structure of distributed systems. Compared to SOTA memory-efficient solutions, it achieves a two-order-of-magnitude reduction in memory while maintaining comparable speed.
  arXiv  Detail & Related papers  (2024-10-22T17:59:30Z)
• Scaling Up 3D Kernels with Bayesian Frequency Re-parameterization for Medical Image Segmentation [25.62587471067468]
  RepUX-Net is a pure CNN architecture with a simple large kernel block design. Inspired by the spatial frequency in the human visual system, we extend to vary the kernel convergence into element-wise setting.
  arXiv  Detail & Related papers  (2023-03-10T08:38:34Z)
• BPT: Binary Point Cloud Transformer for Place Recognition [30.749570675511386]
  We propose a binary point cloud transformer for place recognition. A 32-bit full-precision model can be reduced to a 1-bit model with less memory occupation and faster binarized bitwise operations. Experiments on several standard benchmarks demonstrate that the proposed method can get comparable results with the corresponding full-precision transformer model.
  arXiv  Detail & Related papers  (2023-03-02T11:15:59Z)
• Global Context Vision Transformers [78.5346173956383]
  We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. We address the lack of the inductive bias in ViTs, and propose to leverage a modified fused inverted residual blocks in our architecture. Our proposed GC ViT achieves state-of-the-art results across image classification, object detection and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2022-06-20T18:42:44Z)
• Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking [82.34356879078955]
  We propose a compact memory embedding to enhance the discrimination of the segmentation-based deformable visual tracking method. Our method outperforms the excellent segmentation-based trackers, i.e., D3S and SiamMask on DAVIS 2017 benchmark.
  arXiv  Detail & Related papers  (2021-11-23T03:07:12Z)
• nnFormer: Interleaved Transformer for Volumetric Segmentation [50.10441845967601]
  We introduce nnFormer, a powerful segmentation model with an interleaved architecture based on empirical combination of self-attention and convolution. nnFormer achieves tremendous improvements over previous transformer-based methods on two commonly used datasets Synapse and ACDC.
  arXiv  Detail & Related papers  (2021-09-07T17:08:24Z)

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.