I am a Senior Staff Research Scientist at Google, where I lead a team of scientists and engineers in developing and deploying production-level computer vision and machine learning models. Our work includes the development of perception and generative models for Google’s Face Unlock feature, from its first launch on Pixel 4 (2019) with NIR sensors, and evolving to commodity RGB sensors across all classes of Pixel devices, including Pixel 7 (2022), Pixel Fold & 7a and Pixel 8 (2023), Pixel 8a and 9 Series (2024), Pixel 9a (2025).
Prior to Google, I was a Deep Learning Scientist at Apple, where I played a key role in developing on-device models for several products, including Apple’s first Face ID for iPhone X and iPad Pro (2017), as well as real-time camera features deployed on subsequent iPhones (2018). Before Apple, I was a research staff at the Robotics Institute at Carnegie Mellon University from Aug 2010–2013, and received my Ph.D. from the same institute in Jan 2017.
I have (co-)authored over 40 publications in leading CV/ML conferences and journals. I led the early development of IntraFace, an automated face analysis software that received the Best Demo Award in IEEE Conference on Automatic Face and Gesture Recognition (AFGR) in 2015. A spinoff of IntraFace, FacioMetrics, was later acquired by Facebook in Nov 2016. I continue to contribute to the academic community by serving as an Area Chair on conferences such as AFGR, ACCV, and ICMI.
Ph.D. in Robotics
Carnegie Mellon University
B.S. in Computer Science
National Cheng Kung University
Interns
Students
Area Chair
Organizing Committee
Conference Review
Journal Review
Awards