一个接口适配多种脑电模型，无需为每种模型重做个性化。
Universal BCI Personalization: One API for Frozen EEG Trunks and Foundation Models
- 设计通用接口，兼容五类经典脑电编码器和一个基础模型，无需重复搭建个性化系统。
- 在18个数据集上测试，仅需校准即可达到微调精度的大部分水平，耗时降低数量级。
- 适合想快速集成多模型脑机接口的厂商，尤其适合资源有限的场景。
冻结的脑电编码器日益普及，但针对每个模型进行微调的默认方法难以扩展。我们提出 Nimbus Personalizer：一个统一的API，将编码器与贝叶斯头部连接，可选地通过仿射中间层适配异构冻结编码器，无需为每种架构新增个性化模块。核心贡献是跨编码器的通用接口（非机器学习新方法），使OEM厂商只需集成一次，即可灵活更换编码器。实验证明，该接口可在五类经典编码器（EEGNet、Shallow、Deep、Conformer、ATCNet）及一个基础编码器（REVE）上运行，覆盖四个运动想象数据集共18个实验单元。当嵌入空间容量足够时，该头部作为低成本默认起点，相比热启动微调或参数高效微调（PEFT），所需适应时间减少数个数量级，同时恢复了大部分微调带来的准确率提升；在12/18个单元中，仅校准即可保持性能稳定。头部表现进一步验证了接口的有效性。个体层面置信区间识别出最清晰的数据集，其余均包含零点。所有结果均为探索性分析（采用个体层次自举法，无确认性检验）；何时升级适应策略的问题将在配套控制层工作中讨论。
原文摘要 · Abstract (English)
Frozen EEG encoders proliferate; per-model fine-tune defaults do not scale. We present Nimbus Personalizer: one contract encode to Bayesian head to BrainState (optional affine mid-tier) that sits on heterogeneous frozen trunks without a new personalization stack per architecture. Thesis (systems): the contribution is the trunk-agnostic API - not LDA-on-embeddings as an ML novelty - so OEMs integrate once and swap trunks. Evidence: the same surface runs on five classical trunks EEGNet, Shallow, Deep, Conformer, ATCNet x four MI datasets (18 cells) and on a foundation encoder (REVE) under the same Personalizer. Where embedding capacity exists, the head is a cheap default mid-point versus warm-start fine-tune or PEFT, costing orders of magnitude less adaptation wall time while recovering much of the fine-tune accuracy gain; calibration-only-when-clean holds in 12/18 cells. Head gains are supporting evidence that the API is useful where capacity exists. Subject-level confidence intervals identify the clearest dataset and span zero elsewhere. All results are exploratory (subject-level bootstrap, no confirmatory tests); the decision logic for when to escalate adaptation is addressed in our companion work on the control layer.
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。