Sensori model learns health representations from 24-hour wrist movement
iScienceLuvr · x · 2026-09-01
Research introduces Sensori, a self-supervised foundation model learning general-purpose health representations directly from 24 hours of raw tri-axial wrist movement.
- Dataset: 122,640 participants contributing 683,617 person-days of free-living recordings.
- Architecture: Uses a multiscale architecture where pooling progressively reduces temporal resolution.
- Training: Pretrained with masked reconstruction and day-level contrastive learning.
- Results: Adding Sensori embeddings significantly improved AUROC for 52 of 102 conditions, with largest gains for neurological and psychiatric disorders.
More from Research
- ExploitGym system prompts reveal little of interest — voooooogel · 2026-09-01
- ECCV 2026: EquiFusion Enables Kinematics-Agnostic Human Motion Prediction — CSProfKGD · 2026-09-01
- LightFuse SOTA Relightable 3D Gaussian Reconstruction Beats Baseline by 9.74dB — janusch_patas · 2026-09-01
- Doubt cast on SWA effective receptive field math — giffmana · 2026-09-01
- Call for Papers: Synthetic Populations Research at Frontiers in AI — frederickaplan · 2026-09-01
- Multimodal AI Reveals Mechanism of Shape-Memory Alloy Degradation — bravo_abad · 2026-09-01