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

2026年7月10日 08:52

重點摘要

Most wearable health models are built one outcome at a time. That approach breaks down at thirty-five endpoints. Labels are expensive and retrospective annotation is infeasible.

站內 AI 整理稿

Most wearable health models are built one outcome at a time.That approach breaks down at thirty-five endpoints.Labels are expensive and retrospective annotation is infeasible.

Google Research introduced SensorFM, a foundation model for wearable health pre-trained on more than 1 trillion minutes of sensor data from 5 million people.22759 What is SensorFM?SensorFM is a Large Sensor foundation Model for wearable time-series representation learning.

It ingests 34 one-minute aggregate features drawn from five sensors: PPG, accelerometer, EDA, skin temperature, and altimeter.Those features are organized into seven categories, over a 24-hour context window.

The backbone is a ViT-1D encoder trained with a masked-autoencoder objective and a patch size of [20, 1].

原始來源：MarkTechPost AI ↗

查看原始來源

智東西AI工具與產品

秋招信息戰打不動？我們測了千問的新功能，讓Agent全程陪跑

阿里巴巴旗下大模型「千問」近日推出全新功能，針對秋季招聘季中求職者面臨的海量資訊與繁複流程，打造「Agent 全程陪跑」服務。根據官方測試，這項功能能協助使用者自動篩選職缺、整理企業資訊，甚至模擬面試問答，大幅減輕求職者自行蒐集與比對資訊的負擔。在實際體驗中，用戶只需輸入自身學經歷與目標產業，Agent 便會自動爬取最新的秋招公告，並按職位匹配度、截止日期等條件排序，同時附上企業背景與筆面試經驗摘要。

剛剛閱讀分析