mlsanityData to 14 Oct 2026

ZUNA1.1: A more flexible EEG foundation model for Denoising and Super-resolution

arXiv 2607.27308 ↗First posted 29 Jul 2026cs.LG q-bio.NCcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 34 references that are in the map. First posted on arXiv 29 Jul 2026.

Builds on

22 of 34 references.

References · 22

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  6. 2023Consistency Modelscited by 1,822
  7. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 1,039
  8. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 694
  9. 2024Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCIcited by 327
  10. 2020Query-Key Normalization for Transformerscited by 280
  11. 2021BENDR: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG datacited by 199
  12. 2024CBraMod: A Criss-Cross Brain Foundation Model for EEG Decodingcited by 199
10 more
  1. 2017DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEGcited by 157
  2. 2024NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signalscited by 88
  3. 2023Neuro-GPT: Towards A Foundation Model for EEGcited by 74
  4. 2024SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signalscited by 41
  5. 2025EEG Foundation Models: A Critical Review of Current Progress and Future Directionscited by 32
  6. 2024BrainWave: A Brain Signal Foundation Model for Clinical Applicationscited by 26
  7. 2025EEG-FM-Bench: A Comprehensive Benchmark for the Systematic Evaluation and Diagnostic Analyses of EEG Foundation Modelscited by 23
  8. 2026NeuralBench: A Unifying Framework to Benchmark NeuroAI Modelscited by 16
  9. 2026NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfacescited by 7
  10. 2026ZUNA: Flexible EEG Superresolution with Position-Aware Diffusion Autoencoderscited by 3

Built on by

Not cited yet.