{"slug": "zuna1-1-a-more-flexible-eeg-foundation-model-for-denoising-and-super-resolution", "title": "ZUNA1.1: A more flexible EEG foundation model for Denoising and Super-resolution", "summary": "Researchers released ZUNA1.1, a 380M-parameter diffusion autoencoder for EEG signal reconstruction that can handle variable-length sequences up to 30 seconds, arbitrary channel counts and scalp locations, and reconstruct arbitrary temporal intervals. The model performs at least on par with its predecessor ZUNA1 while being more flexible, and substantially outperforms standard methods like spherical spline interpolation used in the MNE package. ZUNA1.1 is open-sourced under the Apache 2.0 license.", "body_md": "arXiv:2607.27308v1 Announce Type: new\nAbstract: We introduce ZUNA1.1, a 380M-parameter diffusion autoencoder for flexible EEG signal reconstruction. ZUNA1.1 is capable of reconstructing variable length sequences of up to 30s, with an arbitrary number of EEG channels at arbitrary scalp locations, and can reconstruct arbitrary temporal intervals within channels in addition to reconstructing entire channels. We demonstrate that ZUNA1.1 performs at least on par with our earlier ZUNA1 model, while being far more flexible and capable of handling a wide range of reconstruction tasks. ZUNA1.1 continues to substantially outperform standard EEG denoising and reconstruction methods such as spherical spline interpolation, which is ubiquitously deployed in the MNE package. The ZUNA1.1 model is released open source under the permissive Apache 2.0 license.", "url": "https://wpnews.pro/news/zuna1-1-a-more-flexible-eeg-foundation-model-for-denoising-and-super-resolution", "canonical_source": "https://arxiv.org/abs/2607.27308", "published_at": "2026-07-31 04:00:00+00:00", "updated_at": "2026-07-31 04:34:47.729453+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "generative-ai"], "entities": ["ZUNA1.1", "ZUNA1", "MNE"], "alternates": {"html": "https://wpnews.pro/news/zuna1-1-a-more-flexible-eeg-foundation-model-for-denoising-and-super-resolution", "markdown": "https://wpnews.pro/news/zuna1-1-a-more-flexible-eeg-foundation-model-for-denoising-and-super-resolution.md", "text": "https://wpnews.pro/news/zuna1-1-a-more-flexible-eeg-foundation-model-for-denoising-and-super-resolution.txt", "jsonld": "https://wpnews.pro/news/zuna1-1-a-more-flexible-eeg-foundation-model-for-denoising-and-super-resolution.jsonld"}}