ChatPPG.

Jacob Sunshine

Jacob Sunshine has 1 paper in the ChatPPG research atlas (2025), linked to 1 model and 24 co-authors in the atlas. Main topics: Google, MAE, missing-data, AIM, multimodal, accelerometer.

Papers

  • LSM-2: Learning from Incomplete Wearable Sensor Data
    2025 · Google Research blog

    LSM-2 is Google Research's second Large Sensor Model, trained with Adaptive and Inherited Masking (AIM) so it can learn directly from wearable data with gaps, without filling them in first. It was trained on 40 million hours of data from more than 60,000 people wearing Fitbit and Google Pixel devices between March and May 2024. The model handles classification, regression and generative tasks, such as predicting hypertension, from fragmented sensor data.

    • Published: Google Research blog, July 2025 (arXiv preprint)
    • Method: Adaptive and Inherited Masking (AIM) MAE
    • Pretraining data: 40 million hours, 60,000+ participants

Models

Co-authors

A. Ali HeydariAhmed A. MetwallyDaniel McDuffDimitris SpathisGirish NarayanswamyJake GarrisonJames M. RehgKen GuKumar AyushMark MalhotraMaxwell A. XuMing-Zher PohPushmeet KohliSamy Abdel-GhaffarShrikanth NarayananShun LiaoShwetak PatelShyam A. TailorTim AlthoffXin LiuXuhai "Orson" XuYun LiuYuwei ZhangYuzhe Yang