The Platonic Brain: Representational Convergence in EEG Foundation Models
Organizations: University of Buenos Aires, Buenos Aires, Argentina · Paris Brain Institute (ICM), Sorbonne Université, INSERM, CNRS, Pitié-Salpêtrière Hospital, Paris, France · Université Paris-Saclay, Inria, CEA, Palaiseau, France · Sigma Nova, Paris, France
Abstract
The Platonic Representation Hypothesis (PRH) predicts that artificial neural networks converge on shared representations as scale and performance increase. We test whether these predictions hold for representations of the human brain with EEG foundation models. Using EEG recordings from six participants watching a television series, together with aligned visual and language content, we tested whether EEG foundation-model representations converge within and across modalities as their embeddings become better at decoding an informative set of EEG markers. We found that EEG models with greater decodability showed stronger cross-family alignment in both local neighbourhood similarity and global structure, not consistently increasing with model parameter count. Cross-modal convergence was modality and metric dependent: greater EEG decodability was associated with stronger global alignment to language, but not consistently to vision models, while local alignment showed no consistent association. This dissociation may reflect local sensitivity to low-level sensory features, whereas global geometry may capture weaker shared semantic structure.
Figures & tables
Appendix figures & tables8 assets
Supplementary material from the paper’s appendix.
Appendix
| Family | Size | Params (M) | Window (s) | Windows | Marker | MKNN | CKA |
|---|---|---|---|---|---|---|---|
| FEMBA | tiny | 8 | 5 | 2160 | 0.057 | 0.136 | |
| FEMBA | base | 48 | 5 | 2160 | 0.061 | 0.215 | |
| FEMBA | large | 78 | 5 | 2160 | 0.060 | 0.203 | |
| LUNA | base | 7 | 5 | 2160 | 0.063 | 0.284 | |
| LUNA | large | 43 | 5 | 2160 | 0.073 | 0.279 | |
| LUNA | huge | 311 | 5 | 2160 | 0.070 | 0.283 |
| Marker | Median | Best | Best model |
|---|---|---|---|
| abs_delta | +0.466 | +0.887 | reve-base |
| rel_delta | +0.676 | +0.768 | reve-large |
| abs_theta | +0.232 | +0.877 | reve-large |
| rel_theta | +0.523 | +0.631 | steegformer-large |
| abs_alpha | +0.066 | +0.824 | reve-large |
| rel_alpha | +0.593 | +0.671 | steegformer-large |
Representation Alignment
Representation alignment studies how learned feature spaces can be compared or mapped to transfer meaning, capabilities, and information across models and tasks.
See all 119 papers