Girish Narayanswamy

University of Washington

girish_prof.jpg

I am a final year PhD Student at the University of Washington Ubicomp Lab where I am advised by Professor Shwetak Patel. I additionally collaborate closely with Daniel McDuff and Xin Liu at Google, where I spent two years as a Student Researcher.

I am primarily interested in developing solutions which expand health access and improve health sensing. Specifically, my research lies at the intersection of aritifical intelligence, signal processing, and sensing as applied to human health. My most recent works explore the development of sensor foundation models (LSM-1, LSM-2, SensorLM) and their utility in understanding human physiology and behavior.

Before joining UW, I attended the University of Colorado Boulder, where I completed a B.S. in Electrical and Computer Engineering with emphases in signal processing and embedding systems. Over the course of my undergraduate and graduate studies I have had the opportunity to intern at Google, OctoAI, Uplinq AI, Qualcomm, and Medtronic.

In my free time I enjoy being outside (hiking, camping, skiing), drawing, photography, and spending time with friends and family. While at CU I had the honor to play for Mamabird, the university’s ultimate frisbee team – a perennial national contender. I am also a black belt in Shotokan Karate.

selected publications

  1. lsm2.png
    LSM-2: Learning from Incomplete Wearable Sensor Data
    Girish Narayanswamy*, Maxwell A Xu*, Kumar Ayush, and 22 more authors
    arXiv preprint arXiv:2506.05321, 2025
  2. sensorlm.gif
    SensorLM: Learning the Language of Wearable Sensors
    Yuwei Zhang, Kumar Ayush, Siyuan Qiao, and 17 more authors
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025
  3. lsm_scaling.gif
    Scaling Wearable Foundation Models
    Girish Narayanswamy*, Xin Liu*, Kumar Ayush, and 14 more authors
    In The Thirteenth International Conference on Learning Representations, 2025
  4. bigsmall.gif
    Bigsmall: Efficient multi-task learning for disparate spatial and temporal physiological measurements
    Girish Narayanswamy, Yujia Liu, Yuzhe Yang, and 4 more authors
    In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024
  5. rppg_toolbox.jpg
    rppg-toolbox: Deep remote ppg toolbox
    Xin Liu, Girish Narayanswamy*, Akshay Paruchuri*, and 7 more authors
    Advances in Neural Information Processing Systems, 2023

news

Jul 22, 2025 LSM-2 is featured on the Google Research Blog.
Jul 04, 2025 Our workshop, TS4H (Time-Series for Health), was accepted to NeurIPS ‘25!
Jun 08, 2025 Google open sourced my on-device respiratory sensing models! Find them on Github and Hugging Face!
Apr 26, 2025 Presenting LSM at ICLR ‘25. Excited to explore Singapore!
Nov 20, 2020 LSM is featured on the Google Research Blog.