BrainRVQ: A High-Fidelity EEG Foundation Model via Dual-Domain Residual Quantization and Hierarchical Autoregression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cui, Mingzhe, Chen, Tao, Jiao, Yang, Wang, Yiqin, Xie, Lei, Pan, Yi, Mainardi, Luca
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908840499347456
author Cui, Mingzhe
Chen, Tao
Jiao, Yang
Wang, Yiqin
Xie, Lei
Pan, Yi
Mainardi, Luca
author_facet Cui, Mingzhe
Chen, Tao
Jiao, Yang
Wang, Yiqin
Xie, Lei
Pan, Yi
Mainardi, Luca
contents Developing foundation models for electroencephalography (EEG) remains challenging due to the signal's low signal-to-noise ratio and complex spectro-temporal non-stationarity. Existing approaches often overlook the hierarchical latent structure inherent in neural dynamics, leading to suboptimal reconstruction of fine-grained information. In this work, we propose BrainRVQ, a general-purpose EEG foundation model pre-trained on a large-scale corpus of clinical EEG data. Unlike standard masked modeling, BrainRVQ features a Dual-Domain Residual Vector Quantization (DD-RVQ) tokenizer that disentangles temporal waveforms and spectral patterns into hierarchical discrete codes. We further introduce a hierarchical autoregressive pre-training objective that learns to reconstruct these codes in a coarse-to-fine manner, utilizing an importance-guided curriculum masking strategy to prioritize information-rich neural events over background noise. Extensive experiments across 8 diverse downstream datasets demonstrate that BrainRVQ consistently outperforms state-of-the-art baselines, validating its effectiveness in learning robust and generalizable neural representations. Our code and model weights are available:https://github.com/keqicmz/BrainRVQ
format Preprint
id arxiv_https___arxiv_org_abs_2602_16951
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BrainRVQ: A High-Fidelity EEG Foundation Model via Dual-Domain Residual Quantization and Hierarchical Autoregression
Cui, Mingzhe
Chen, Tao
Jiao, Yang
Wang, Yiqin
Xie, Lei
Pan, Yi
Mainardi, Luca
Signal Processing
Machine Learning
Developing foundation models for electroencephalography (EEG) remains challenging due to the signal's low signal-to-noise ratio and complex spectro-temporal non-stationarity. Existing approaches often overlook the hierarchical latent structure inherent in neural dynamics, leading to suboptimal reconstruction of fine-grained information. In this work, we propose BrainRVQ, a general-purpose EEG foundation model pre-trained on a large-scale corpus of clinical EEG data. Unlike standard masked modeling, BrainRVQ features a Dual-Domain Residual Vector Quantization (DD-RVQ) tokenizer that disentangles temporal waveforms and spectral patterns into hierarchical discrete codes. We further introduce a hierarchical autoregressive pre-training objective that learns to reconstruct these codes in a coarse-to-fine manner, utilizing an importance-guided curriculum masking strategy to prioritize information-rich neural events over background noise. Extensive experiments across 8 diverse downstream datasets demonstrate that BrainRVQ consistently outperforms state-of-the-art baselines, validating its effectiveness in learning robust and generalizable neural representations. Our code and model weights are available:https://github.com/keqicmz/BrainRVQ
title BrainRVQ: A High-Fidelity EEG Foundation Model via Dual-Domain Residual Quantization and Hierarchical Autoregression
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2602.16951