用双域分层量化建模脑电波，提升信号还原精度。
BrainRVQ: A High-Fidelity EEG Foundation Model via Dual-Domain Residual Quantization and Hierarchical Autoregression
- 双域残差向量量化分离时序与频谱特征
- 分层自回归预训练实现从粗到细的重建
- 适合临床脑电分析与神经信号建模研究
脑电图（EEG）基础模型的构建面临信噪比低和时频非平稳性复杂的挑战。现有方法常忽略神经动态的层级潜在结构，导致细微信息重建不佳。本文提出BrainRVQ，一个在大规模临床脑电数据上预训练的通用型脑电基础模型。不同于标准掩码建模，BrainRVQ采用双域残差向量量化（DD-RVQ）分词器，将时序波形与频谱模式解耦为分层离散码。进一步引入分层自回归预训练目标，通过重要性引导的课程掩码策略，优先重建富含信息的神经事件而非背景噪声。在8个不同下游数据集上的实验表明，BrainRVQ持续优于当前最优基线，验证了其学习鲁棒且可泛化的神经表征的有效性。代码与模型权重已公开：https://github.com/keqicmz/BrainRVQ
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。