# ZUNA: Flexible EEG Superresolution with Position-Aware Diffusion Autoencoders
**URL:** https://mne.discourse.group/t/zuna-flexible-eeg-superresolution-with-position-aware-diffusion-autoencoders/11696
**Category:** Announcements
**Tags:** eeg, biophysical-modeling
**Created:** [February 18, 2026, 9:06pm UTC](https://mne.discourse.group/t/zuna-flexible-eeg-superresolution-with-position-aware-diffusion-autoencoders/11696 "2026-02-18T21:06:22Z")
**Posts on this page:** 5
**Page:** 1
### Author:  [@chris-warner-II](https://mne.discourse.group/u/chris-warner-II)
#### Post date: [February 18, 2026, 9:06pm UTC](https://mne.discourse.group/t/zuna-flexible-eeg-superresolution-with-position-aware-diffusion-autoencoders/11696/1 "2026-02-18T21:06:22Z")
Zyphra is excited to announce ZUNA, our first foundation model trained on brain data. ZUNA is a 380M-parameter diffusion autoencoder trained to denoise, reconstruct, 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 outperforms spherical spline interpolation which is ubiquitously used by EEG researchers and practitioners and is included as the default in the widely-used MNE package. ZUNA is easy to use as a pip installable package. Visit [Zyphra](https://www.zyphra.com/post/zuna) for more information and support!
---
### Author:  [@discourse\_ai\_spam](https://mne.discourse.group/u/discourse_ai_spam)
#### Post date: [February 18, 2026, 9:06pm UTC](https://mne.discourse.group/t/zuna-flexible-eeg-superresolution-with-position-aware-diffusion-autoencoders/11696/2 "2026-02-18T21:06:25Z")
---
### Author:  [@system](https://mne.discourse.group/u/system)
#### Post date: [February 24, 2026, 8:13pm UTC](https://mne.discourse.group/t/zuna-flexible-eeg-superresolution-with-position-aware-diffusion-autoencoders/11696/3 "2026-02-24T20:13:31Z")
---
### Author:  [@moritzandres](https://mne.discourse.group/u/moritzandres)
#### Post date: [March 11, 2026, 11:04am UTC](https://mne.discourse.group/t/zuna-flexible-eeg-superresolution-with-position-aware-diffusion-autoencoders/11696/4 "2026-03-11T11:04:38Z")
Thanks a lot for an amazing large-scale, open-weights EEG foundation model.
I was wondering if you plan to compare it to other EEG-FMs?
In my opinion, the **EEG-FM-Bench** paper could be good start for this.
Love to see ZUNA crush the benchmarks! 🙂
---
### Author:  [@chris-warner-II](https://mne.discourse.group/u/chris-warner-II)
#### Post date: [March 12, 2026, 9:22pm UTC](https://mne.discourse.group/t/zuna-flexible-eeg-superresolution-with-position-aware-diffusion-autoencoders/11696/5 "2026-03-12T21:22:07Z")
Thanks for the pointer. Will look into this.