AI Paper Atlas

Research map / Time series / Long-term forecasting

Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series

Guoqi Yu, Juncheng Wang, Chen Yang, Jing Qin, Angelica I Aviles-Rivero, Shujun Wang

ICLR 2026 · Time series › Long-term forecasting · approach: Graph-based multivariate forecasting · 5 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 dual (temporal plus channel) tokenization instead of no tokenization (ablation)TeCh · APAVAaccuracy: 50.68 -> 86.86Improved
add dual tokenization instead of temporal-only (ablation)TeCh · APAVAaccuracy: 55.93 -> 86.86Improved
add dual tokenization instead of channel-only (ablation)TeCh · PTBaccuracy: 85.96 -> 84.15Hurt
add dual tokenization instead of temporal-only (ablation)TeCh · TDBrainaccuracy: 93.21 -> 89.79Hurt
add dual tokenization instead of channel-only (ablation)TeCh · UCI-HARaccuracy: 92.98 -> 94.15Improved
add CoTAR token interaction instead of removing it (ablation)TeCh · APAVAaccuracy: 83.31 -> 86.86Improved
replace attention with CoTAR (ablation)TeCh · TDBrainaccuracy: 90.40 -> 93.21Improved
replace attention with CoTAR (ablation)TeCh · UCI-HARaccuracy: 93.13 -> 94.15Improved
replace attention with CoTAR (ablation)TeCh · PTBaccuracy: 85.74 -> 85.96Improved
add CoTAR instead of removing it (ablation)TeCh · ADFTDF1: 47.26 -> 48.84No clear effect
replace Medformer with TeChTeCh · ADFTDaverage of six metrics: 54.63 -> 54.16Hurt
replace Medformer with TeChTeCh · APAVAaverage of six metrics: 79.74 -> 88.99Improved

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