{
  "id": 965,
  "url": "https://arxiv.org/abs/2606.16462v1",
  "title": "Learning aligned EEG representations with subject-specific encoders",
  "summary": "Cross-subject EEG decoding promises more training data, but it also exposes neural networks to strong inter-subject distribution shifts. We study whether task supervision and architecture alone can learn subject-aligned representations. We replace a shared EEG encoder with subject-specific encoders followed by a common classifier, and compare this hybrid model with standard EEGNet, AttentionBaseNet, and CTNet baselines with Euclidean Alignment (EA) on four motor-imagery datasets. EA improves sha",
  "authors": "Bruna J. Lopes, Gabriel Schwartz, Sylvain Chevallier, Raphael Y. de Camargo, Bruno Aristimunha",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-15T09:31:56.000Z",
  "fetched_at": "2026-07-14T14:14:54.534Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/965",
  "original_url": "https://arxiv.org/abs/2606.16462v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}