Models (6)
A dual-stream self-supervised foundation model for continuous glucose monitoring data, separating slow physiological state from transient glucose events.
A family of sensor-language foundation models from Google that aligns wearable biosignals with natural language for zero-shot recognition, retrieval, and captioning.
A multimodal wearable foundation model trained on 40M hours of six-sensor data from 165K+ people, establishing scaling laws for physiological sensor signals.
Google's family of medical multimodal models built on Gemini, adding uncertainty-guided web search, custom modality encoders, and long-context EHR reasoning.
Google's generalist multimodal biomedical AI that encodes clinical text, medical images, and genomics with a single set of weights across 14 tasks.
Sparse attention transformer extending BERT to sequences up to 8x longer via random, local, and global attention patterns, with demonstrated applications in genomic sequence modeling.