Research map / Vision-language and multimodal / Human and embodied modeling
CodeBrain: Towards Decoupled Interpretability and Multi-Scale Architecture for EEG Foundation Model
Jingying Ma, Feng Wu, Qika Lin, Yucheng Xing, Chenyu Liu, Ziyu Jia, Mengling Feng
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use dual temporal+frequency codebooks instead of a mixed codebook (ablation) | CodeBrain · FACED (9-class) | Cohen's Kappa: 0.4676 -> 0.5406 | Improved |
| use dual codebooks instead of temporal-only (ablation) | CodeBrain · FACED (9-class) | Cohen's Kappa: 0.4618 -> 0.5406 | Improved |
| use dual codebooks instead of frequency-only (ablation) | CodeBrain · FACED (9-class) | Cohen's Kappa: 0.5006 -> 0.5406 | Improved |
| use dual codebooks instead of a mixed codebook (ablation) | CodeBrain · SEED-V (5-class) | Cohen's Kappa: 0.2708 -> 0.2735 | Improved |
| use dual codebooks instead of a mixed codebook (ablation) | CodeBrain · ISRUC S3 (5-class) | Cohen's Kappa: 0.7400 -> 0.7671 | Improved |
| add contrastive loss to temporal codebook training (ablation) | CodeBrain · FACED (9-class) | Cohen's Kappa: 0.5222 -> 0.5406 | Improved |
| add contrastive loss to temporal codebook training (ablation) | CodeBrain · ISRUC S3 (5-class) | Cohen's Kappa: 0.7558 -> 0.7671 | Improved |
| add sliding window attention (ablation) | CodeBrain · SEED-V (5-class) | Cohen's Kappa: 0.2561 -> 0.2735 | Improved |
| add SGConv layer (ablation) | CodeBrain · FACED (9-class) | Cohen's Kappa: 0.1936 -> 0.5406 | Improved |
| add SGConv layer (ablation) | CodeBrain · ISRUC S3 (5-class) | Cohen's Kappa: 0.6218 -> 0.7671 | Improved |
| add gate mechanism (ablation) | CodeBrain · FACED (9-class) | Cohen's Kappa: 0.2578 -> 0.5406 | Improved |
| add gate mechanism (ablation) | CodeBrain · ISRUC S3 (5-class) | Cohen's Kappa: 0.5478 -> 0.7671 | Improved |
Later papers that compared with this method
2 later accepted papers report CodeBrain as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- COSMIO: A Benchmark for Cross-Survey Modality Imputation (NeurIPS 2026 · better on 5 of 6 shared results)
- SphereFlow: Missing Modality Imputation via Geometric Transport on Hypersphere (NeurIPS 2026 · better on 3 of 3 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
- CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding (NeurIPS 2025 · similarity 0.93)
- BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals (NeurIPS 2025 · similarity 0.90)
- CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding (ICLR 2025 · similarity 0.89)
- What do EEG Foundation Models Capture from Human Brain Signals? (NeurIPS 2026 · similarity 0.88)
- NeurIPT: Foundation Model for Neural Interfaces (NeurIPS 2025 · similarity 0.88)
- MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding (NeurIPS 2026 · similarity 0.88)
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.
