LaunchHealthJuly 10, 2026

Google Research introduces SensorFM, wearable health foundation model trained on 1…

SensorFM is pre-trained on over 1 trillion minutes of sensor data across 35 health endpoints. It addresses label scarcity by learning from raw data and can be fine-tuned for multiple downstream health tasks.

How this story unfolded

13 days · 5 reports · 1 community post · from Jul 7

Jul 7
- STELLA: Efficient Sensor-to-LLM Translation for On-Device Human Activity Recognitionarxiv.org
Jul 9
- Inertia-1: An Open Exploration of Wearable Motion Foundation Modelsarxiv.org
- Physical activities enable scalable foundation modelling for broad-spectrum health predictionarxiv.org
Jul 10
- Omni-Sleep: A Sleep Foundation Model via Hierarchical Contrastive Learning of CNS--ANS Dynamicarxiv.org
- Google Research Introduces SensorFM: A Wearable Health Foundation Model Pretrained on One Trillion Minutes of Sensor Datamarktechpost.com
Jul 20
- Inertia-1: An Open Exploration to a Unified Motion Foundation Model

Daily brief

Get tomorrow's AI brief in your inbox

Google Research introduces SensorFM, wearable health foundation model trained on 1…

How this story unfolded

Daily brief

More stories today