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
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
- 525 improved
- 58 no clear effect
- 7 mixed
- 56 hurt
- Learning-Augmented Scalable Linear Assignment Problem Optimization via Neural Dual Warm-Starts ICML 2026 · add positional encodings to features (d=13 -> d=21) · Block-structured, N=4096 · speedupImproved
- Mesh Based Simulations with Spatial and Temporal awareness ICML 2026 · use learned positional embedding, learnable relative bias or weighted adjacency instead of RoPE · Aneurysm · RMSEHurt
- Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning ICML 2026 · add sinusoidal positional encoding to the pruner · Robomimic Tool Hang · success rate (%): 28 -> 54Improved
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.
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add support samples as in-context examples | ECHO · SEED | balanced accuracy: 0.7407 -> 0.8193 | Improved |
| add support samples as in-context examples | ECHO · Mental Arithmetic | balanced accuracy: 0.5442 -> 0.6851 | Improved |
| add support samples as in-context examples | ECHO · Attention | balanced accuracy: 0.8056 -> 0.8194 | Improved |
| add support samples as in-context examples | ECHO · BCIC 2020-T1 (unseen) | balanced accuracy: 0.7500 -> 0.7782 | Improved |
| use decoder-centric seq2seq formulation instead of encoder-centric variant | ECHO · SEED | balanced accuracy: 0.6548 -> 0.7407 | Improved |
| use decoder-centric seq2seq formulation instead of encoder-centric variant | ECHO · BCIC 2020-T1 (unseen) | balanced accuracy: 0.5250 -> 0.7500 | Improved |
| add sample-level positional encoding in decoder | ECHO · ablation figure | accuracy: drops to chance level when removed | Improved |
| add decoder textual positional encoding | ECHO · ablation figure | accuracy: structural collapse when removed | Improved |
| multi-task ECHO vs single-task baselines | ECHO · cognitive tasks (SEED, Stieger, Mental Arithmetic, Attention) | balanced accuracy: +0.0602 avg | Improved |
| multi-task ECHO vs single-task baselines | ECHO · Mumtaz2016 and High-Gamma | balanced accuracy: +0.0409 avg | Improved |
| multi-task ECHO without support vs single-task baseline | ECHO (No Support) · Stieger2021-LR ROC AUC | ROC AUC: 0.9339 vs 0.9245 | No 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.
- CBraMod — CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding (ICLR 2025) · better on 1 of 1 shared result
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
- NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals (ICLR 2025 · similarity 0.88)
- CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding (NeurIPS 2025 · similarity 0.88)
- CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding (ICLR 2025 · similarity 0.86)
- MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding (NeurIPS 2026 · similarity 0.86)
- REVE: A Foundation Model for EEG - Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects (NeurIPS 2025 · similarity 0.86)
- LEAF: Language-EEG Aligned Foundation Model for Brain-Computer Interfaces (NeurIPS 2026 · similarity 0.86)
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.
