Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling?

• URL: http://arxiv.org/abs/2604.03619v1
• Date: Sat, 04 Apr 2026 07:30:29 GMT
• Title: Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling?
• Abstract summary: TABLeT is a novel approach that tokenizes fMRI volumes using a pre-trained 2D natural image autoencoder.<n>Across large-scale benchmarks, TABLeT outperforms existing models in multiple tasks.<n>Our findings suggest a promising approach for scalable and interpretabletemporal modeling of brain activity.
• Score: 18.529904812096024
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Modeling long-range spatiotemporal dynamics in functional Magnetic Resonance Imaging (fMRI) remains a key challenge due to the high dimensionality of the four-dimensional signals. Prior voxel-based models, although demonstrating excellent performance and interpretation capabilities, are constrained by prohibitive memory demands and thus can only capture limited temporal windows. To address this, we propose TABLeT (Two-dimensionally Autoencoded Brain Latent Transformer), a novel approach that tokenizes fMRI volumes using a pre-trained 2D natural image autoencoder. Each 3D fMRI volume is compressed into a compact set of continuous tokens, enabling long-sequence modeling with a simple Transformer encoder with limited VRAM. Across large-scale benchmarks including the UK-Biobank (UKB), Human Connectome Project (HCP), and ADHD-200 datasets, TABLeT outperforms existing models in multiple tasks, while demonstrating substantial gains in computational and memory efficiency over the state-of-the-art voxel-based method given the same input. Furthermore, we develop a self-supervised masked token modeling approach to pre-train TABLeT, which improves the model's performance for various downstream tasks. Our findings suggest a promising approach for scalable and interpretable spatiotemporal modeling of brain activity. Our code is available at https://github.com/beotborry/TABLeT.

Related papers

• Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis [93.7120829382642]
  Nemotron-Labs-Diffusion-Image is a state-of-the-art masked discrete diffusion model for text-to-image synthesis.<n>Standard MDMs lack self-correcting capability because discrete tokens cannot be modified once they are unmasked.<n>Nemotron-Labs-Diffusion-Image incorporates a token-editing mechanism that enables the model to dynamically revise already-unmasked tokens during inference.
  arXiv  Detail & Related papers  (2026-06-29T05:48:41Z)
• NeuroRVQ: Multi-Scale EEG Tokenization for Generative Large Brainwave Models [66.91449452840318]
  We introduce NeuroRVQ, a scalable Large Brainwave Model (LBM) centered on a codebook-based tokenizer.<n>Our tokenizer integrates: (i) multi-scale feature extraction modules that capture the full frequency neural spectrum; (ii) hierarchical residual vector quantization (RVQ) codebooks for high-resolution encoding; and, (iii) an EEG signal phase- and amplitude-aware loss function for efficient training.<n>Our empirical results demonstrate that NeuroRVQ achieves lower reconstruction error and outperforms existing LBMs on a variety of downstream tasks.
  arXiv  Detail & Related papers  (2025-10-15T01:26:52Z)
• OmniSAT: Compact Action Token, Faster Auto Regression [70.70037017501357]
  We introduce an Omni Swift Action Tokenizer, which learns a compact, transferable action representation.<n>The resulting discrete tokenization shortens the training sequence by 6.8$times$, and lowers the target entropy.
  arXiv  Detail & Related papers  (2025-10-08T03:55:24Z)
• BrainSymphony: A Transformer-Driven Fusion of fMRI Time Series and Structural Connectivity [2.3486335708866606]
  BrainSymphony is a lightweight, parameter-efficient foundation model for neuroimaging.<n>It achieves state-of-the-art performance while being pre-trained on significantly smaller public datasets.<n>BrainSymphony establishes that architecturally-aware, multimodal models can surpass their larger counterparts.
  arXiv  Detail & Related papers  (2025-06-23T06:00:21Z)
• Dynadiff: Single-stage Decoding of Images from Continuously Evolving fMRI [3.0450307343472405]
  We introduce Dynadiff, a new single-stage diffusion model designed for reconstructing images from dynamically evolving fMRI recordings.<n>Our model outperforms state-of-the-art models on time-resolved fMRI signals, especially on high-level semantic image reconstruction metrics.<n>Overall, this work lays the foundation for time-resolved brain-to-image decoding.
  arXiv  Detail & Related papers  (2025-05-20T16:14:37Z)
• Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models [92.18057318458528]
  Token-Shuffle is a novel method that reduces the number of image tokens in Transformer.<n>Our strategy requires no additional pretrained text-encoder and enables MLLMs to support extremely high-resolution image synthesis.<n>In GenAI-benchmark, our 2.7B model achieves 0.77 overall score on hard prompts, outperforming AR models LlamaGen by 0.18 and diffusion models LDM by 0.15.
  arXiv  Detail & Related papers  (2025-04-24T17:59:56Z)
• Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis [62.57727062920458]
  We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL.<n>We leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers.<n>Our model not only matches but often exceeds the performance of existing models like SDXL in generating high-quality, high-resolution images.
  arXiv  Detail & Related papers  (2024-10-10T17:59:17Z)
• TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation [65.65530016765615]
  We propose a hierarchical predictive coding framework that captures multi-scale dependencies through three complementary learning objectives.<n> TokenUnify integrates random token prediction, next-token prediction, and next-all token prediction to create a comprehensive representational space.<n>We also introduce a large-scale EM dataset with 1.2 billion annotated voxels, offering ideal long-sequence visual data with spatial continuity.
  arXiv  Detail & Related papers  (2024-05-27T05:45:51Z)
• NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation [55.51412454263856]
  This paper proposes to directly modulate the generation process of diffusion models using fMRI signals. By training with about 67,000 fMRI-image pairs from various individuals, our model enjoys superior fMRI-to-image decoding capacity.
  arXiv  Detail & Related papers  (2024-03-27T02:42:52Z)
• VM-UNet: Vision Mamba UNet for Medical Image Segmentation [2.3876474175791302]
  We propose a U-shape architecture model for medical image segmentation, named Vision Mamba UNet (VM-UNet) We conduct comprehensive experiments on the ISIC17, ISIC18, and Synapse datasets, and the results indicate that VM-UNet performs competitively in medical image segmentation tasks.
  arXiv  Detail & Related papers  (2024-02-04T13:37:21Z)
• Spatio-Temporal Encoding of Brain Dynamics with Surface Masked Autoencoders [10.097983222759884]
  Surface Masked AutoEncoder (sMAE) and surface Masked AutoEncoder (MAE) These models are trained to reconstruct cortical feature maps from masked versions of the input by learning strong latent representations of cortical development and structure function. Results show that (v)sMAE pre-trained models improve phenotyping prediction performance on multiple tasks by $ge 26%$, and offer faster convergence relative to models trained from scratch.
  arXiv  Detail & Related papers  (2023-08-10T10:01:56Z)
• Data-driven modelling of brain activity using neural networks, Diffusion Maps, and the Koopman operator [0.0]
  We propose a machine-learning approach to model long-term out-of-sample dynamics of brain activity from task-dependent fMRI data. We use Diffusion maps (DMs) to discover a set of variables that parametrize the low-dimensional manifold on which the emergent high-dimensional fMRI time series evolve. We construct reduced-order-models (ROMs) on the embedded manifold via two techniques: Feedforward Neural Networks (FNNs) and the Koopman operator.
  arXiv  Detail & Related papers  (2023-04-24T09:08:12Z)
• Joint fMRI Decoding and Encoding with Latent Embedding Alignment [77.66508125297754]
  We introduce a unified framework that addresses both fMRI decoding and encoding. Our model concurrently recovers visual stimuli from fMRI signals and predicts brain activity from images within a unified framework.
  arXiv  Detail & Related papers  (2023-03-26T14:14:58Z)
• Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image Synthesis [52.41439725865149]
  Cross-modality magnetic resonance (MR) image synthesis can be used to generate missing modalities from given ones. Existing (supervised learning) methods often require a large number of paired multi-modal data to train an effective synthesis model. We propose a Multi-scale Transformer Network (MT-Net) with edge-aware pre-training for cross-modality MR image synthesis.
  arXiv  Detail & Related papers  (2022-12-02T11:40:40Z)

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.