BridgeRouter：按实例路由跨模态桥，提升脑电模型迁移精度
BridgeRouter: Gain-Aware Instance Routing over Cross-Modal Bridge Portfolios
一篇挺巧的论文：让 EEG 基础模型不重训就能跑 EMG 和 ECG 任务，靠 MLP 预测哪条迁移桥增益最大，FOG 上比单选桥高 11 个多点。
论文提出 BridgeRouter，把多条跨模态迁移桥的选择建模为实例级算法选择问题。训练时用任务标签计算每条路由相对 Single Best Solver 的负对数似然增益，由轻量 MLP 从目标模态特征预测增益。推理时只需目标模态输入，执行一条最优桥路径。在 FOG 数据集的 EMG 冻结步态检测上，BridgeRouter 达到 81.38±1.11% 平衡准确率，比 BIOT SBS 高 11.49 个百分点；在 ISRUC 的 ECG 睡眠分类上达到 62.92±2.17%，比 CBraMod SBS 高 3.83 个百分点。
BridgeRouter: Gain-Aware Instance Routing over Cross-Modal Bridge Portfolios
Lightweight representation bridges make pretrained, task-adapted EEG foundation models executable on other biosignal modalities without retraining their backbones. However, selecting a single bridge pathway globally assigns every instance to the same transfer route and ignores complementary errors across routes. We therefore formulate multi-bridge transfer as an instance-level algorithm-selection problem and introduce BridgeRouter, a gain-aware router over a portfolio of frozen cross-modal pathways. A validation-selected Single Best Solver (SBS) serves as a protected default route. During training, task labels are used to compute the reduction in negative log-likelihood provided by each alternative route relative to the SBS, and a lightweight MLP predicts these route-specific gains from a target-modality representation extracted by a frozen encoder. At inference, BridgeRouter observes only the target modality, requires neither EEG, task labels, nor predictions from all candidate routes, and executes exactly one bridge pathway: the route with the largest predicted gain when that gain exceeds a validation-calibrated threshold, and the SBS otherwise. We evaluate seven EEG foundation-model bridge pathways for EMG-based freezing-of-gait detection on FOG and ECG-based sleep classification on ISRUC. Across five seeds, BridgeRouter achieves $81.38\pm1.11\%$ balanced accuracy on FOG, improving over the BIOT SBS by $11.49$ percentage points, and $62.92\pm2.17\%$ on ISRUC, improving over the CBraMod SBS by $3.83$ points. Per-instance bridge oracles reach $99.96\%$ and $78.61\%$, respectively, revealing substantial remaining portfolio headroom. These results show that anchor-relative gain prediction can convert complementary cross-modal bridge behavior into deployable instance-level routing improvements while retaining single-route inference.