# PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation

arXiv: https://arxiv.org/abs/2506.10351 · HTML: https://mlsanity.com/paper/2506.10351/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 68 references that are in the map.
- First posted on arXiv 12 Jun 2025.

## Builds on (most cited first, 27 of 27)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [Learning in the Frequency Domain](https://mlsanity.com/paper/2002.12416/) (2020)
- [U-Net and its variants for medical image segmentation: theory and applications](https://mlsanity.com/paper/2011.01118/) (2020)
- [Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement](https://mlsanity.com/paper/2403.06659/) (2024)
- [An Alternative Probabilistic Interpretation of the Huber Loss](https://mlsanity.com/paper/1911.02088/) (2019)
- [ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosis](https://mlsanity.com/paper/2408.08849/) (2024)
- [Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings](https://mlsanity.com/paper/2502.01108/) (2025)
- [emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation](https://mlsanity.com/paper/2412.02725/) (2024)
- [emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography](https://mlsanity.com/paper/2410.20081/) (2024)
- [On the token distance modeling ability of higher RoPE attention dimension](https://mlsanity.com/paper/2410.08703/) (2024)
- [OpenECG: Benchmarking ECG Foundation Models with Public 1.2 Million Records](https://mlsanity.com/paper/2503.00711/) (2025)
- [OTIS: Learning High-Quality Time Series Features With Tiny Encoders](https://mlsanity.com/paper/2410.07299/) (2024)
- [Uncertainty Quantification in Machine Learning for Biosignal Applications -- A Review](https://mlsanity.com/paper/2312.09454/) (2023)
- [MedalCare-XL: 16,900 healthy and pathological 12 lead ECGs obtained through electrophysiological simulations](https://mlsanity.com/paper/2211.15997/) (2022)

## Built on by (most cited first, 12 of 12)

- [TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edge](https://mlsanity.com/paper/2512.15729/) (2025)
- [A Unified Tokenization Framework for Pain Recognition using Heterogeneous 3D Modalities](https://mlsanity.com/paper/2607.19716/) (2026)
- [NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models](https://mlsanity.com/paper/2510.13068/) (2025)
- [Wavelet-Driven Masked Multiscale Reconstruction for PPG Foundation Models](https://mlsanity.com/paper/2601.12215/) (2026)
- [Wearable Foundation Models Should Go Beyond Static Encoders](https://mlsanity.com/paper/2603.19564/) (2026)
- [Learning Clinical Representations Under Systematic Distribution Shift](https://mlsanity.com/paper/2603.07348/) (2026)
- [Discriminative Representation Learning for Clinical Prediction](https://mlsanity.com/paper/2603.20921/) (2026)
- [Spectral Regularization for Diffusion Models](https://mlsanity.com/paper/2603.02447/) (2026)
- [Position: Evaluation of ECG Representations Must Be Fixed](https://mlsanity.com/paper/2602.17531/) (2026)
- [PanLUNA: An Efficient and Robust Query-Unified Multimodal Model for Edge Biosignal Intelligence](https://mlsanity.com/paper/2604.04297/) (2026)
- [Towards Real-Time ECG and EMG Modeling on μNPUs](https://mlsanity.com/paper/2604.18067/) (2026)
- [EMGBlend: Heterogeneity-Aware Self-Supervised Pretraining for Gesture and Force Decoding](https://mlsanity.com/paper/2609.25582/) (2026)

## Abstract (arXiv)

Physiological signals are often corrupted by motion artifacts, baseline drift, and other low-SNR disturbances, which pose significant challenges for analysis. Additionally, these signals exhibit strong non-stationarity, with sharp peaks and abrupt changes that evolve continuously, making them difficult to represent using traditional time-domain or filtering methods. To address these issues, a novel wavelet-based approach for physiological signal analysis is presented, aiming to capture multi-scale time-frequency features in various physiological signals. Leveraging this technique, two large-scale pretrained models specific to EMG and ECG are introduced for the first time, achieving superior performance and setting new baselines in downstream tasks. Additionally, a unified multi-modal framework is constructed by integrating pretrained EEG model, where each modality is guided through its dedicated branch and fused via learnable weighted fusion. This design effectively addresses challenges such as low signal-to-noise ratio, high inter-subject variability, and device mismatch, outperforming existing methods on multi-modal tasks. The proposed wavelet-based architecture lays a solid foundation for analysis of diverse physiological signals, while the multi-modal design points to next-generation physiological signal processing with potential impact on wearable health monitoring, clinical diagnostics, and broader biomedical applications. Code and data are available at: github.com/ForeverBlue816/PhysioWave