跳到正文
arXiv cs.AI· Abhilash Durgam, Nyle Siddiqui, Jeffrey A. Chan-Santiago, Qiushi Fu, Elakkat D. Gireesh, Mubarak Shah·· 2 小时前AI 评分34

CaMBRAIN:基于因果状态空间模型的实时连续 EEG 推理

CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models

AI 导读

研究者提出 CaMBRAIN,首个基于因果 Mamba 状态空间模型(SSM)的 EEG 实时推理模型,避开注意力机制的二次复杂度与滑窗限制。配合多阶段自监督训练流程以保留长程记忆,该模型在 3 个 EEG 数据集上取得 SOTA 结果,吞吐量较现有模型提升超过 10 倍,可对变长 EEG 信号进行长程连续推理。

正文 · 原文

View PDF HTML (experimental)

Abstract:Electroencephalography (EEG) is a critical, non-invasive method to monitor electrical brain activity. EEGs can span anywhere from a couple seconds to multiple hours, posing a major hurdle for existing deep learning methods due to two major factors: (1) existing EEG models are predominantly built upon the attention mechanism, incurring quadratic scaling as the sequence length increases, and (2) raw EEG signals must be processed in a sliding-window fashion due to fixed-length input requirements, preventing global understanding of the entire signal. To this extent, we propose CaMBRAIN - the first Causal, Mamba-based state space model (SSM) capable of real-time inference of EEG signals, arguing that bidirectional approaches are needlessly expensive given the causal, unidirectional nature of EEG. However, training such a model is non-trivial, as crucial EEG events can be extremely brief - within fractions of a second - yet separated by long intervals spanning minutes. Current EEG methods use self-supervised objectives that optimize for signal reconstruction, but these are not well suited for streaming SSMs; they fail to explicitly train the hidden state to retain the salient long-range context needed for streaming inference. We therefore introduce a multi-stage self-supervised training pipeline specifically tailored to encourage long-range memory retention and strong performance on EEG signals, while preserving the linear-time complexity of state space models. CaMBRAIN achieves state-of-the-art (SOTA) results across 3 different EEG datasets with >10x higher throughput than existing models, enabling the first model capable of long-range, continuous inference of variable-length EEG signals.
Subjects: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
Cite as: arXiv:2605.28792 [cs.AI]
  (or arXiv:2605.28792v3 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2605.28792

arXiv-issued DOI via DataCite

Submission history

From: Abhilash Durgam [view email]
[v1] Wed, 27 May 2026 17:50:36 UTC (7,173 KB)
[v2] Mon, 16 Nov 2026 04:05:41 UTC (1 KB) (withdrawn)
[v3] Wed, 18 Nov 2026 01:00:59 UTC (7,173 KB)

来源:arXiv cs.AI · arxiv.org