ZUNA EU AI Act Compliance Profile

ZUNA: EEG Foundation Model

ZUNA is a 380M-parameter masked diffusion autoencoder trained to reconstruct, denoise, and upsample scalp-EEG signals. Given a subset of EEG channels, ZUNA can:

• Denoise existing EEG channels
• Reconstruct missing EEG channels
• Predict novel channel signals given physical coordinates on the scalp

ZUNA was trained on approximately 2 million channel-hours of EEG data from a wide range of publicly available sources. At 380M parameters, it is lightweight enough to run on a consumer GPU and can be used on CPU for many workloads.

Performance

ZUNA significantly outperforms existing standard methods for channel denoising, reconstruction, and upsampling. We compared ZUNA to MNE's default spherical spline interpolation method. ZUNA outperforms MNE in reconstruction accuracy across a range of unseen datasets, even those with a different preprocessing pipeline. ZUNA's advantage is particularly striking for higher upsampling ratios, demonstrating that it is effectively using general priors learned through large-scale pretraining.

Getting Started

For installation, tutorials, and API documentation, see the GitHub repository.

A Google Colab notebook i

Your obligations as a ZUNA deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Languages