Tom Bu

I am a Machine Learning Engineer at Meta Reality Labs, where I work on eye tracking for AR/VR devices. My work spans end-to-end model development — from data collection and ETL to model training and evaluation — with a focus on eye pose estimation and novel sensing modalities.

Previously, I was a Machine Learning Engineer at NEC Laboratories America, where I led on-device multi-modal perception deployment and developed a target-free multi-LiDAR/multi-camera calibration method. Before that, I worked at the CMU Argo AI Center for AV Research on crosswalk change detection and synthetic data generation for rare object detection.

I hold an M.S. in Robotics from Carnegie Mellon University (co-advised by Prof. John Dolan and Christoph Mertz) and a B.S. in Engineering from Yale University.

San Jose, CA

Education

M.S in Robotics
School of Computer Science
Aug 2020-Aug 2022

B.S. in Engineering
School of Engineering and Applied Science
Aug 2013-May 2017

Publications

  • Polarization-Based Eye Tracking with Personalized Siamese Architectures
  • Kalkanli B., Tom Bu, Shakeri M., Fix A., Stronks D., Model D., Zurauskas M.
  • ACM Symposium on Eye Tracking Research & Applications (ETRA); Proc. ACM Hum.-Comput. Interact., 2026
  • [Paper]
  • Polarization-resolved imaging improves eye tracking
  • Zurauskas M., Tom Bu, Alali S., Kalkanli B., Shi D., Alamos F., Pandit G., Mei C., Behrooz A., Mirjalili R., Stronks D., Fix A., Model D.
  • arXiv preprint, 2025
  • arXiv:2511.04652
  • [Paper]
  • Automatic multi-modality sensor calibration with near-infrared images
  • Tom Bu, Zhuang B., Chandraker M.
  • Patent No. WO2025076354, 2025
  • [Patent]
  • Handling road marking changes
  • Batsos K., Yousif K., Tom Bu, Jian Y.
  • Patent Application No. US20240192021, 2024
  • Filed 2022.12.08
  • [Patent]
  • Toward Map Updates With Crosswalk Change Detection Using a Monocular Bus Camera
  • Tom Bu, Christoph Mertz, John Dolan
  • Intelligent Vehicle Symposium (IV), 2023
  • Oral Presentation
  • [Paper] [Project] [Code]
  • Leveraging Structure from Motion to Localize Inaccessible Bus Stops
  • Panigrahi I., Tom Bu, Christoph Mertz
  • Robotics Institute Summer Scholars Working Papers Journal, 2022
  • arXiv:2210.03646
  • [Paper]
  • Toward HD Map Updates With Crosswalk Change Detection From Vehicle-Mounted Cameras
  • Tom Bu, Christoph Mertz, John Dolan
  • Master's Thesis, 2022
  • [Paper] [Poster] [Bibtex]
  • CARLA Simulated Data for Rare Road Object Detection
  • Tom Bu*, Xinhe Zhang*, Christoph Mertz, John Dolan
  • Intelligent Transportation Systems Conference (ITSC), 2021
  • Oral Presentation. * indicates equal contribution
  • [Talk] [Paper] [Code] [Poster] [Bibtex]
  • Determination of appendix position using a two stage deep neural network
  • Tom Bu, Chopra S., Bhave R., Liu J.
  • Patent No. 11253324, 2019
  • [Patent]
  • Dunhuang Image Restoration Using Attention Residual U-Net
  • Tom Bu
  • International Conference on Computer Vision (ICCV) Workshop, 2019
  • 2nd place solution in the Dunhuang Image Restoration Challenge. Invited talk at the e-Heritage workshop
  • [Slides]
  • Conditional Generator Using Nearest Neighbor Pseudo-labelled Segmentation
  • Tom Bu
  • International Conference on Computer Vision (ICCV) Workshop, 2019
  • 3rd place solution in the OpenEDS Eye Generation Challenge. Invited poster presentation at the Eye Tracking for VR and AR workshop
  • [Poster]

---

Industry Experience

  • Meta Reality Labs
  • Machine Learning Engineer
  • July 2024 – Present
  • NEC Labs America-Media Analytics
  • Machine Learning Engineer
  • January 2023 – July 2024
  • CMU Argo AI Center for AV Research
  • Graduate Researcher & ML Intern · Argo AI–sponsored
  • August 2020 – December 2022
  • Cognistx
  • Machine Learning Engineer
  • June 2018 – August 2020
  • Segway Ninebot-Segway Robotics
  • Robotics Intern
  • September 2017 – March 2018



---