Metraipolis › archive › dc_5ff69f516cd2

MEL: Coordinate-Preserving EEG Tokenization for fMRI Translation — arXiv:2608.29304

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.29304
License (as archived): CC0-1.0
Archived: 2026-10-17T08:32:43.208Z
SHA-256 of the archived text: 243fd19d849187b06924208f14a1d46c7bc3ef554710777af5b243e40515672a
Stable URL of this page: https://metraipolis.com/documento/dc_5ff69f516cd2

How to cite

MEL: Coordinate-Preserving EEG Tokenization for fMRI Translation — arXiv:2608.29304 — arXiv (en), https://arxiv.org/abs/2608.29304 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ff69f516cd2 (Metraipolis archive dc_5ff69f516cd2, sha256 243fd19d849187b06924208f14a1d46c7bc3ef554710777af5b243e40515672a)

BibTeX

@misc{dc5ff69f516cd2,
  title = {MEL: Coordinate-Preserving EEG Tokenization for fMRI Translation — arXiv:2608.29304},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29304},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ff69f516cd2; sha256 243fd19d849187b06924208f14a1d46c7bc3ef554710777af5b243e40515672a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29304. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Translating electroencephalography (EEG) into functional magnetic resonance imaging (fMRI) is important for medical neuroimaging, clinical brain-state monitoring, and multimodal neural decoding, because it aims to infer spatially organized hemodynamic activity from fast and accessible electrophysiological recordings. Existing EEG-to-fMRI studies mainly pursue stronger decoders, but the problem is also constrained by a representation-interface mismatch: fMRI responses are delayed, temporally integrated, and spatially distributed, whereas generic EEG encodings often entangle temporal lag, channel identity, and frequency-band structure. We propose Multi-band EEG Latent-state Tokenization (MEL), a coordinate-preserving EEG representation framework that anchors each target fMRI response to its preceding EEG history and organizes it into lag-channel-frequency neural-state tokens. By explicitly capturing hemodynamic latency and spectral-spatial dynamics, MEL aligns fMRI-pertinent EEG representations with capacity-controlled readouts without depending entirely on model scaling. Experiments on VU EEG-fMRI benchmarks and external Oddball data show that MEL improves prediction over strong NeuroBOLT baselines. Ablations and controls further indicate that the gains come from structured EEG representation rather than leakage, shortcut statistics, or decoder capacity.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.29304 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T08:13:26.737Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).