EEG

LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis
Topology-agnostic EEG foundation model that delivers state-of-the-art performance with 300× fewer FLOPs and 10× lower memory usage.
Berkay Döner, Thorir Mar Ingolfsson, Luca Benini, Yawei Li
PDF Code Project Preprint (arXiv) GitHub Repository DOI
LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis
FEMBA: Efficient and Scalable EEG Analysis with a Bidirectional Mamba Foundation Model
Bidirectional Mamba EEG foundation model that matches transformer accuracy while scaling linearly with sequence length.
Anna Tegon, Thorir Mar Ingolfsson, Xiaying Wang, Luca Benini, Yawei Li
PDF Code Project Preprint (arXiv) GitHub Repository DOI
FEMBA: Efficient and Scalable EEG Analysis with a Bidirectional Mamba Foundation Model
SzCORE: Seizure Community Open-Source Research Evaluation Framework for EEG-Based Seizure Detection
Community-driven framework standardizing datasets, metrics, and tooling for reproducible EEG seizure detection research.
Jonathan Dan, Una Pale, Alireza Amirshahi, William Cappelletti, Thorir Mar Ingolfsson, Xiaying Wang, Andrea Cossettini, Adriano Bernini, Luca Benini, Sándor Beniczky, David Atienza, Philippe Ryvlin
PDF Code Dataset Open Access PDF DOI (Epilepsia) SzCORE GitHub
CEReBrO: Compact Encoder for Representations of Brain Oscillations Using Efficient Alternating Attention
Alternating-attention EEG foundation model pre-trained on 20k+ hours that doubles speed and cuts memory by 6× versus standard transformers.
Alexandru Dimofte, Glenn Anta Bucagu, Thorir Mar Ingolfsson, Xiaying Wang, Andrea Cossettini, Luca Benini, Yawei Li
PDF Project Preprint (arXiv) DOI
BioFoundation: Foundation Models for Biosignals
Open-source framework powering LUNA, FEMBA, CEReBrO, and other EEG foundation models — including LUNA, accepted at NeurIPS 2025.
PDF Code GitHub Paper
BISeizuRe: BERT-Inspired Seizure Data Representation to Improve Epilepsy Monitoring
BERT-inspired EEG encoder that cuts seizure-detection false positives to 0.23 FP/h after subject-specific tuning.
Luca Benfenati, Thorir Mar Ingolfsson, Andrea Cossettini, Daniele Jahier Pagliari, Alessio Burrello, Luca Benini
PDF Dataset Project Preprint (arXiv) TUH EEG Corpus
GAPses: Versatile Smart Glasses for Comfortable and Fully-Dry Acquisition and Parallel Ultra-Low-Power Processing of EEG and EOG
Fully dry EEG/EOG smart glasses with on-board GAP9 processing delivering 99% biometric accuracy and 12-hour autonomy.
Sebastian Frey, Mattia Alberto Lucchini, Victor Kartsch, Thorir Mar Ingolfsson, Andrea Helga Bernardi, Michael Segessenmann, Jakub Osieleniec, Simone Benatti, Luca Benini, Andrea Cossettini
PDF Preprint (arXiv) DOI