AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

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

Peter Yongho Kim, Juhyeon Park, Jungwoo Park, Jubin Choi, Jungwoo Seo, Jiook Cha, Taesup Moon

CVPR 2026 · Architectures and efficiency › Attention and transformers · approach: Block-sparse attention kernels · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace SwiFT with TABLeT (27 tokens per volume, T=256)voxel-based fMRI models · ADHD-200 Diagnosisaccuracy: 63.9 -> 65.8Improved
TABLeT versus SwiFT on UKB sex accuracyTABLeT · UKB Sexaccuracy: 98.1 -> 97.7No clear effect
TABLeT versus SwiFT on HCP ageTABLeT · HCP AgeMAE: 0.699 -> 0.705No clear effect
add masked token modeling pre-training on UKB before fine-tuning (ablation)TABLeT · HCP AgePearson rho: 0.473 -> 0.552Improved
add masked token modeling pre-training (ablation)TABLeT · HCP SexAUC: 0.987 -> 0.986No clear effect
use off-the-shelf 2D natural-image DCAE instead of 3D DCAE trained on fMRI (ablation)TABLeT tokenizer · HCP Sexaccuracy: 92.2 -> 93.8Improved
use 2D DCAE instead of 3D DCAE (ablation)TABLeT tokenizer · ADHD-200 DiagnosisF1: 0.644 -> 0.630Mixed
fine-tune the 2D DCAE on fMRI (ablation)2D DCAE · fMRI reconstructionreconstruction qualityHurt
aggregate three slicing axes instead of a single axis (ablation)TABLeT tokens · UKB AgeMSE: 0.369 -> 0.340 (best single axis sagittal)Improved
aggregate three axes instead of coronal only (ablation)TABLeT tokens · HCP AgeMSE: 0.855 -> 0.773No clear effect
increase number of input frames T (50 to 256) (ablation)TABLeT · HCP Intelligence and ADHD-200MAE / AUCImproved
use TABLeT instead of SwiFT at T=50voxel-based model · Peak memory (batch size 4)memory: 7.33x more memory efficientImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy