AI Paper Atlas

Research map / Time series / Causal and generative time series

Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder Identification

Hwa Hui Tew, Junn Yong Loo, Leong Fang Yu, Julia K. Lau, Ding Fan, Hernando Ombao, Raphael CW Phan, Chee Pin Tan, Chee-Ming Ting

ICLR 2026 · Time series › Causal and generative time series · approach: Irregular series and imputation · 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
add DSFM synthetic data augmentation (1x)BrainNetCNN · MDDaccuracy: 58.90 -> 70.84Improved
add DSFM synthetic data augmentation (1x)BrainNetCNN · ABIDEaccuracy: 64.67 -> 71.54Improved
add Vanilla-GAN augmentationBrainNetCNN · MDDaccuracy: 58.90 -> 58.86No clear effect
use ECS normalization instead of MinMax (ablation)DSFM · MDDContext-FID: 1.505 -> 0.098Improved
use ECS normalization instead of MinMax (ablation)DSFM · MDDCorrelational score: 57.3 -> 18.2Improved
use block size 4 instead of 2 (ablation)DSFM · MDDContext-FID: 0.121 -> 0.098No clear effect
use Haar instead of dB-4 wavelet (ablation)DSFM · MDDContext-FID: 0.199 -> 0.098No clear effect
use wavelet plus DCT spectral flow matching instead of Fourier (ablation)DSFM · MDDCorrelational score: 107.90 -> 18.20Improved
use flow matching instead of diffusion on wavelet representation (ablation)DSFM · MDDContext-FID: 3.57 -> 2.19Improved
add dual-spectral DCT stage to wavelet flow matching (ablation)DSFM · MDDContext-FID: 2.19 -> 0.10Improved
include mid-frequency LH3 and LH4 subbands (ablation)DSFM FC classification · MDDaccuracy: 63.30 -> 70.84Improved
include LL and LH5 high-pass subbands (vs. high-pass setting) (ablation)DSFM FC classification · MDDaccuracy: 65.40 -> 70.84Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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