AI Paper Atlas

Research map / Time series / Foundation models for time series

BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Series

Guikang Du, Haoran Li, Xinyu Liu, Zhibo Zhang, Xiaoli Gong, Jin Zhang

ICML 2026 · Time series › Foundation models for time series · approach: Time series representation learning · 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 FBAM (spectral alignment) and SCLN (ablation)Transformer backbone · APAVAF1 (%): 74.23 -> 79.77Improved
add FBAM (spectral alignment) (ablation)BioFormer · ADFTDF1 (%): 45.90 -> 53.82Improved
add SCLN on top of FBAM (ablation)BioFormer · APAVAF1 (%): 78.07 -> 79.77Improved
add SCLN on top of FBAM (ablation)BioFormer · PTB-XLF1 (%): 62.56 vs 62.53No clear effect
use phase-only modulation instead of magnitude+phase (ablation)BioFormer · PTBF1 (%): 83.06 -> 84.71Improved
use magnitude-only modulation instead of joint (ablation)BioFormer · APAVAF1 (%): 79.77 -> 75.82Hurt
align in frequency domain (FBAM) instead of time domain (TSAM) (ablation)Transformer · APAVAF1 (%): 76.71 -> 80.00Improved
align in frequency domain (FBAM) instead of time domain (TSAM) (ablation)Transformer · ADFTDF1 (%): 47.45 -> 52.13Improved
align in frequency domain (FBAM) instead of time domain (TSAM) (ablation)Transformer · PTB-XLF1 (%): 58.86 -> 60.90Improved
use FBAM instead of GRL/MMD/CORAL/SubjectNorm/MixStyle/DSU (ablation)Medformer · APAVAF1 (%): 76.21 -> 80.00 (Trans. GRL vs FBAM column)Improved
add SubjectNorm (ablation)Transformer · APAVAaccuracy (%): 73.12 -> 47.11Hurt
add FBAM to Medformer (ablation)Medformer · APAVAF1 (%): 76.02 -> 81.46Improved

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