AI 中文总结
STEAM是一种分层迁移框架，通过双分支时空编码器与SSMoE模块实现EEG解码的通用表征学习与范式专业化，在7个数据集的14种评估设置中表现优异且推理成本具竞争力。
AI 中文摘要
脑机接口（BCI）已广泛应用于运动康复、疾病诊断及其他神经工程场景。然而，传统神经信号解码算法常面临泛化能力有限、适配成本高的问题，这促使人们对BCI基础模型产生研究兴趣。现有方法仍难以同时实现通用迁移性、精准解码及高效下游适配。本文提出STEAM，这是一种分层迁移框架，用于在EEG基础模型中协调通用表征学习与特定范式的专业化。该框架实例化为双分支时空编码器，其中共享软混合专家（SSMoE）模块对齐空间与时间分支，使互补表征通过一组紧凑的软槽交换信息。在7个下游数据集和14种评估设置中，STEAM在以FLOPs衡量的具竞争力推理成本下，取得了对比方法中最佳的平均排名。基于第一阶段通用初始化，分层预训练策略进一步使模型适配目标范式，无需从头重新训练，在特定范式解码准确率上实现持续提升。
英文摘要
Brain-computer interfaces (BCIs) have been widely used in motor rehabilitation, disease diagnosis, and other neural engineering scenarios. However, conventional neural signal decoding algorithms often suffer from limited generalizability and high adaptation costs, motivating recent interest in BCI foundation models. Existing approaches still struggle to jointly achieve general transferability, accurate decoding, and efficient downstream adaptation. We present STEAM, a hierarchical transfer framework that reconciles general-purpose representation learning with paradigm-specific specialization in EEG foundation models. The framework is instantiated as a dual-branch spatio-temporal encoder in which a shared soft mixture-of-experts (SSMoE) module aligns the spatial and temporal branches, allowing complementary representations to exchange information through a compact set of soft slots. Across seven downstream datasets and fourteen evaluation settings, STEAM attains the best average rank among the compared methods at a competitive inference cost measured in FLOPs. Building upon the Stage-I general initialization, the hierarchical pre-training strategy further specializes the model to a target paradigm without retraining from scratch, yielding consistent gains in paradigm-specific decoding accuracy.
