PhysioWave-T：面向生理信号的 token 高效小波基础模型
PhysioWave-T: Token-Efficient Wavelet Foundation Models for Biosignals
一份开源的生理信号基础模型，EEG 在 9 项指标里 8 项超过 LaBraM 和 EEGPT，延迟还降了最多 7 倍，做脑电或肌电的可以直接看代码。
PhysioWave-T 是一套针对 EEG、ECG、sEMG 的 token 高效小波基础模型，通过动态尺度折叠把 (J+1)CS 个 token 压缩为 CS 个。其 30M 参数的 EEG 模型在超过 1500 万个窗口（19–128 通道）上预训练，EEG 编码器在 9 项指标中有 8 项领先 BENDR、BIOT、LaBraM 和 EEGPT。尺度折叠使 Transformer 延迟降低 4.0–7.2 倍，峰值内存降低 6.8–12.7 倍且无精度损失。配合 RALF 融合方法，在 SeizeIT2 癫痫检测上把 11 次误报/小时下的事件敏感度从 61.4% 提升到 74.4%。模型代码已在 GitHub 开源。
PhysioWave-T: Token-Efficient Wavelet Foundation Models for Biosignals
We present PhysioWave-T, a token-efficient wavelet foundation model family for EEG, ECG, and sEMG. Dynamic scale folding recombines J+1 wavelet subbands prior to tokenization, compressing sequence length from (J+1)CS to CS tokens for J levels, C channels, and S temporal patches. Route-specific front ends and learned channel-name embeddings allow one Transformer per modality to handle diverse montages and sampling rates, while unseen setups reuse the backbone via lightweight adapters. We pre-train a 30M-parameter EEG model on over 15M windows (19--128 channels), alongside ECG (30M) and sEMG (12M) encoders. Across four EEG routes, scale folding cuts Transformer latency by 4.0--7.2x and peak memory by 6.8--12.7x over scale expansion without accuracy loss. Our EEG encoder leads 8 of 9 metrics against BENDR, BIOT, LaBraM, and EEGPT, and surpasses LUNA-L on wearable seizure detection with fewer parameters. Reliability-aware latent fusion (RALF) further integrates summary tokens from independently pre-trained encoders via sample-adaptive weights. On SeizeIT2, RALF raises event sensitivity at 11 false alarms/h from 61.4% to 74.4% and window AUPRC from 0.321 to 0.399 over the best unimodal baseline, outperforming weighted-logit and concatenation fusion across all variants. PhysioWave-T also achieves state-of-the-art sEMG accuracies and top macro-F1 on PTB-XL Super and Chapman-Shaoxing. Code and models: https://github.com/ForeverBlue816/PhysioWave.
