Google Research Introduces SensorFM: A Wearable Health Foundation Model Pretrained on One Trillion Minutes of Sensor Data

Google Research, Google DeepMind, and university collaborators introduced SensorFM, a wearable health foundation model pretrained on over one trillion minutes of unlabeled sensor data from 5 million participants. The model uses a ViT-1D masked-autoencoder backbone and outperformed feature-engineered baselines on 34 of 35 tasks using frozen embeddings with a PCA-50 linear probe. The research also included an agentic classroom that searched 30,516 prediction heads and a clinician evaluation for a Personal Health Agent.

SensorFM, a wearable health foundation model from Google Research, Google DeepMind, and university collaborators. We walk through its ViT-1D masked-autoencoder backbone, pretrained on more than one trillion minutes of unlabeled sensor signals from 5,000,000 consented participants. We examine the co-scaling results across four model sizes and four data volumes, including the case where capacity outruns data. We show how frozen embeddings plus a PCA-50 linear probe beat feature-engineered baselines on 34 of 35 tasks. We also review the agentic classroom that searched 30,516 prediction heads, and the clinician evaluation grounding a Personal Health Agent. The post Google Research Introduces SensorFM: A Wearable Health Foundation Model Pretrained on One Trillion Minutes of Sensor Data https://www.marktechpost.com/2026/07/10/google-research-introduces-sensorfm-a-wearable-health-foundation-model-pretrained-on-one-trillion-minutes-of-sensor-data/ appeared first on MarkTechPost https://www.marktechpost.com .