AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

ECHO: Toward Contextual Seq2Seq Paradigms in Large EEG Models

Chenyu Liu, Yuqiu Deng, Tianyu Liu, Jinan Zhou, Xinliang Zhou, Ziyu Jia, Yi Ding

ICLR 2026 · Architectures and efficiency › Attention and transformers · approach: Transformer expressivity and circuits

This paper tried a common change: Add positional encoding

add sample-level positional encoding in decoder · ablation figure · accuracy: drops to chance level when removed Improved

What 646 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 support samples as in-context examplesECHO · SEEDbalanced accuracy: 0.7407 -> 0.8193Improved
add support samples as in-context examplesECHO · Mental Arithmeticbalanced accuracy: 0.5442 -> 0.6851Improved
add support samples as in-context examplesECHO · Attentionbalanced accuracy: 0.8056 -> 0.8194Improved
add support samples as in-context examplesECHO · BCIC 2020-T1 (unseen)balanced accuracy: 0.7500 -> 0.7782Improved
use decoder-centric seq2seq formulation instead of encoder-centric variantECHO · SEEDbalanced accuracy: 0.6548 -> 0.7407Improved
use decoder-centric seq2seq formulation instead of encoder-centric variantECHO · BCIC 2020-T1 (unseen)balanced accuracy: 0.5250 -> 0.7500Improved
add sample-level positional encoding in decoderECHO · ablation figureaccuracy: drops to chance level when removedImproved
add decoder textual positional encodingECHO · ablation figureaccuracy: structural collapse when removedImproved
multi-task ECHO vs single-task baselinesECHO · cognitive tasks (SEED, Stieger, Mental Arithmetic, Attention)balanced accuracy: +0.0602 avgImproved
multi-task ECHO vs single-task baselinesECHO · Mumtaz2016 and High-Gammabalanced accuracy: +0.0409 avgImproved
multi-task ECHO without support vs single-task baselineECHO (No Support) · Stieger2021-LR ROC AUCROC AUC: 0.9339 vs 0.9245No clear effect

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