# Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals

arXiv: https://arxiv.org/abs/2412.09758 · HTML: https://mlsanity.com/paper/2412.09758/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 88 references that are in the map.
- First posted on arXiv 12 Dec 2024.

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding](https://mlsanity.com/paper/2412.07236/) (2024)
- [Large Language Models for Time Series: A Survey](https://mlsanity.com/paper/2402.01801/) (2024)
- [Large-scale Training of Foundation Models for Wearable Biosignals](https://mlsanity.com/paper/2312.05409/) (2023)
- [BioBART: Pretraining and Evaluation of A Biomedical Generative Language Model](https://mlsanity.com/paper/2204.03905/) (2022)
- [Self-supervised representation learning from 12-lead ECG data](https://mlsanity.com/paper/2103.12676/) (2021)
- [Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Data](https://mlsanity.com/paper/2206.02909/) (2022)
- [Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformer](https://mlsanity.com/paper/2205.09928/) (2022)
- [Improving Position Encoding of Transformers for Multivariate Time Series Classification](https://mlsanity.com/paper/2305.16642/) (2023)
- [Neural Contextual Anomaly Detection for Time Series](https://mlsanity.com/paper/2107.07702/) (2021)
- [Self-supervised transfer learning of physiological representations from free-living wearable data](https://mlsanity.com/paper/2011.12121/) (2020)
- [Leveraging Vision-Language Models for Granular Market Change Prediction](https://mlsanity.com/paper/2301.10166/) (2023)
- [Detector-Free Weakly Supervised Group Activity Recognition](https://mlsanity.com/paper/2204.02139/) (2022)
- [Estimating Blood Pressure from Photoplethysmogram Signal and Demographic Features using Machine Learning Techniques](https://mlsanity.com/paper/2005.03357/) (2020)
- [MAUS: A Dataset for Mental Workload Assessmenton N-back Task Using Wearable Sensor](https://mlsanity.com/paper/2111.02561/) (2021)
- [Unleashing the Power of Shared Label Structures for Human Activity Recognition](https://mlsanity.com/paper/2301.03462/) (2023)

## Built on by (most cited first, 30 of 32)

- [ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents](https://mlsanity.com/paper/2508.04038/) (2025)
- [sleep2vec: Unified Cross-Modal Alignment for Heterogeneous Nocturnal Biosignals](https://mlsanity.com/paper/2602.13857/) (2026)
- [Learning Transferable Sensor Models via Language-Informed Pretraining](https://mlsanity.com/paper/2603.11950/) (2026)
- [Wearable Foundation Models Should Go Beyond Static Encoders](https://mlsanity.com/paper/2603.19564/) (2026)
- [SlotFM: A Motion Foundation Model with Slot Attention for Diverse Downstream Tasks](https://mlsanity.com/paper/2509.21673/) (2025)
- [Generalist vs Specialist Time Series Foundation Models: Investigating Potential Emergent Behaviors in Assessing Human Health Using PPG Signals](https://mlsanity.com/paper/2510.14254/) (2025)
- [Sonata: A Hybrid World Model for Inertial Kinematics under Clinical Data Scarcity](https://mlsanity.com/paper/2604.18058/) (2026)
- [Wav2Arrest 2.0: Long-Horizon Cardiac Arrest Prediction with Time-to-Event Modeling, Identity-Invariance, and Pseudo-Lab Alignment](https://mlsanity.com/paper/2509.21695/) (2025)
- [BioX-Bridge: Model Bridging for Unsupervised Cross-Modal Knowledge Transfer across Biosignals](https://mlsanity.com/paper/2510.02276/) (2025)
- [A Systematic Evaluation of Sample-Level Tokenization Strategies for MEG Foundation Models](https://mlsanity.com/paper/2602.16626/) (2026)
- [A foundation model for electrodermal activity data](https://mlsanity.com/paper/2603.16878/) (2026)
- [Biosignal Fingerprinting: A Cross-Modal PPG-ECG Foundation Model](https://mlsanity.com/paper/2605.09579/) (2026)
- [AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild](https://mlsanity.com/paper/2605.22715/) (2026)
- [LLM Agents for Time-Series: A Survey](https://mlsanity.com/paper/2608.26226/) (2026)
- [SOTER: A Generative Time-Series Foundation Model for Wearable Human Physiological Signals](https://mlsanity.com/paper/2609.16804/) (2026)
- [DeepFeature: LLM-Empowered Context-aware Feature Generation for Wearable Biosignals](https://mlsanity.com/paper/2512.08379/) (2025)
- [EduGage: A Multimodal Dataset and Benchmark for Sensor-Based Momentary Assessment of Engagement in Self-Guided Video Learning](https://mlsanity.com/paper/2605.01238/) (2026)
- [CogAdapt: Adapting Clinical ECG Foundation Models for Wearable Cognitive Load Assessment](https://mlsanity.com/paper/2605.22774/) (2026)
- [VitalAgent: A Tool-Augmented Agent for Reactive and Proactive Physiological Monitoring over Wearable Health Data](https://mlsanity.com/paper/2605.29483/) (2026)
- [Physical activities enable scalable foundation modelling for broad-spectrum health prediction](https://mlsanity.com/paper/2607.06954/) (2026)
- [SpO2 Predictor-Guided Stage-Wise Time-Frequency Reconstruction of Low-Quality Dual-Wavelength PPG for Oxygen Saturation Estimation](https://mlsanity.com/paper/2607.07996/) (2026)
- [Zero-Shot Heart Rate Variability Forecasting from Consumer Wearables Using Time Series Foundation Models](https://mlsanity.com/paper/2607.20027/) (2026)
- [Foundation models for movement data: Are they ready for prime-time?](https://mlsanity.com/paper/2608.13316/) (2026)
- [Physiological World Models for Human State Transitions](https://mlsanity.com/paper/2608.15309/) (2026)
- [BALMS: Benchmarking Agentic LLMs for Longitudinal Mental Health Sensing](https://mlsanity.com/paper/2608.27219/) (2026)
- [Large language models in medical time series analysis](https://mlsanity.com/paper/2609.22262/) (2026)
- [PPG-LM: A Photoplethysmography-Language Model with Multi-Level Clinical Alignment](https://mlsanity.com/paper/2609.33516/) (2026)
- [EdgeCraft: Automated Model Crafting for Edge IoT](https://mlsanity.com/paper/2609.35167/) (2026)
- [Training and Scaling Compute-Optimal Physiological Waveform Foundation Models](https://mlsanity.com/paper/2610.05649/) (2026)
- [Lapras: Latent Reasoning for Time Series Language Models](https://mlsanity.com/paper/2610.11111/) (2026)

## Abstract (arXiv)

Time-series foundation models excel at tasks like forecasting across diverse data types by leveraging informative waveform representations. Wearable sensing data, however, pose unique challenges due to their variability in patterns and frequency bands, especially for healthcare-related outcomes. The main obstacle lies in crafting generalizable representations that adapt efficiently across heterogeneous sensing configurations and applications. To address this, we propose NormWear, the first multi-modal and ubiquitous foundation model designed to extract generalized and informative representations from wearable sensing data. Specifically, we design a channel-aware attention mechanism with a shared special liaison [CLS] token to detect signal patterns in both intra-sensor and inter-sensors. This helps the model to extract more meaningful information considering both time series themselves and the relationships between input sensors. This helps the model to be widely compatible with various sensors settings. NormWear is pretrained on a diverse set of physiological signals, including PPG, ECG, EEG, GSR, and IMU, from various public datasets. Our model shows exceptional generalizability across 11 public wearable sensing datasets, spanning 18 applications in mental health, body state inference, vital sign estimation, and disease risk evaluation. It consistently outperforms competitive baselines under zero-shot, partial-shot, and full-shot settings, indicating broad applicability in real-world health applications.