A Scalable Approach for Partially Local Federated Learning
Predicting Text Selections with Federated Learning
Grammar Correction as You Type, on Pixel 6
FRILL: On-Device Speech Representations using TensorFlow-Lite
MediaPipe Holistic — Simultaneous Face, Hand and Pose Prediction, on Device
Navigating Recorder Transcripts Easily, with Smart Scrolling
Announcing the Objectron Dataset
On-device, Real-time Body Pose Tracking with MediaPipe BlazePose
MediaPipe Iris: Real-time Iris Tracking & Depth Estimation
Improving Speech Representations and Personalized Models Using Self-Supervision
Federated Analytics: Collaborative Data Science without Data Collection
