{
  "abstract": "Electroencephalography (EEG) foundation models (FMs) have recently emerged as a promising paradigm for brain–computer interfaces, aiming to learn transferable neural representations from large-scale heterogeneous recordings. Despite rapid progress, a fair and comprehensive comparison of existing EEG FMs is still lacking, owing to inconsistent pre-training objectives, preprocessing choices and downstream evaluation protocols. To fill this gap, we present EEG-FM-Compass. We first review 55 representative models and organize their design choices into a unified taxonomic framework including data standardization, model architectures and self-supervised pre-training strategies. We then evaluate 12 open-source FMs and competitive specialist baselines across 13 EEG datasets spanning 9 brain–computer interface paradigms. Emphasizing real-world deployments, we consider both cross-subject generalization under a leave-one-subject-out protocol and rapid calibration under a within-subject few-shot setting. We further compare full-parameter fine-tuning with linear probing to assess the transferability of pre-trained representations, and examine the relationship between model scale and downstream performance. Our results indicate that (i) linear probing is frequently insufficient; (ii) specialist models trained from scratch remain competitive across many tasks; and (iii) larger FMs do not necessarily yield better generalization performance under current data regimes and training practices.",
  "abstract_shown": true,
  "affiliations": [
    "Ministry of Education Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology , Wuhan 430074 ,",
    "Zhongguancun Academy , Beijing 100094 ,",
    "State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Institute of Automation, Chinese Academy of Sciences , Beijing 100190 ,"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Dingkun Liu",
      "orcid": "0009-0007-6091-2051"
    },
    {
      "affs": [
        0
      ],
      "name": "Yuheng Chen"
    },
    {
      "affs": [
        0
      ],
      "name": "Zhu Chen"
    },
    {
      "affs": [
        0
      ],
      "name": "Zhenyao Cui"
    },
    {
      "affs": [
        2,
        1
      ],
      "name": "Yaozhi Wen"
    },
    {
      "affs": [
        0
      ],
      "name": "Jiayu An"
    },
    {
      "affs": [
        0
      ],
      "name": "Jingwei Luo",
      "orcid": "0009-0004-4441-9927"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Dongrui Wu",
      "orcid": "0000-0002-7153-9703"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fhpernhday89d.bib",
  "cited_by": 31,
  "doi": "10.1093/nsr/nwag466",
  "fulltext_url": null,
  "id": "fhpernhday89d",
  "issns": [
    "2053-714X",
    "2095-5138"
  ],
  "landing_url": "https://doi.org/10.1093/nsr/nwag466",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2805|EEG and Brain-Computer Interfaces"
    ]
  ],
  "openalex": "W7172428723",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-31",
  "publisher": "Oxford University Press",
  "ris": "https://research.draconitic.com/paper/fhpernhday89d.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T13:20:55Z",
      "native_id": "W7172428723",
      "source": "openalex",
      "url": "https://doi.org/10.1093/nsr/nwag466"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "openalex:2805|EEG and Brain-Computer Interfaces",
      "subfield": "neuroscience"
    }
  ],
  "title": "EEG-FM-Compass: progress, benchmarking and future directions for EEG foundation models",
  "title_text": "EEG-FM-Compass: progress, benchmarking and future directions for EEG foundation models",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T13:20:48Z",
  "url": "https://research.draconitic.com/paper/fhpernhday89d",
  "venue": "National Science Review",
  "versions": []
}