Saved in:
Bibliographic Details
Main Authors: Kim, Peter Yongho, Park, Juhyeon, Park, Jungwoo, Choi, Jubin, Seo, Jungwoo, Cha, Jiook, Moon, Taesup
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.03619
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910102914596864
author Kim, Peter Yongho
Park, Juhyeon
Park, Jungwoo
Choi, Jubin
Seo, Jungwoo
Cha, Jiook
Moon, Taesup
author_facet Kim, Peter Yongho
Park, Juhyeon
Park, Jungwoo
Choi, Jubin
Seo, Jungwoo
Cha, Jiook
Moon, Taesup
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03619
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling?
Kim, Peter Yongho
Park, Juhyeon
Park, Jungwoo
Choi, Jubin
Seo, Jungwoo
Cha, Jiook
Moon, Taesup
Computer Vision and Pattern Recognition
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.
title Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling?
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.03619