Xiaoyu Xiang

Research Scientist at Meta

San Francisco, California, United States
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
Xiao-Yu Xiang is a Senior Research Scientist at Meta Reality Labs with 11 years of experience bridging physics-driven engineering and cutting-edge computer vision and machine learning. Trained in engineering physics at Tsinghua and pursuing a PhD at Purdue, she has a strong experimental background from fiber laser research and particle-detector testing, which informs her empirical approach to ML problems. At Meta she progressed from research intern to senior scientist after internships at Facebook, ByteDance and HP where she worked on real-world image restoration, temporal smoothing for video landmarks, and face-set recognition. An active open-source contributor and ML engineer, she implemented and evaluated a one-stage space-time video super-resolution model from the CVPR 2020 literature, reflecting a deep engagement with video enhancement research. Outside the lab she’s an indie app developer with five apps on sale, demonstrating a practical focus on shipping products that translate research into user-facing tools.
code11 years of coding experience
github-logo-circle

Github Skills (6)

computer-vision10
pytorch10
machine-learning10
deep-learning10
python10
image-processing9

Programming languages (5)

JavaScriptHTMLMATLABPythonCuda

Github contributions (5)

github-logo-circle
Fast and Accurate One-Stage Space-Time Video Super-Resolution (accepted in CVPR 2020)
Role in this project:
userML Engineer
Contributions:1 review, 17 commits, 5 PRs in 2 months
Contributions summary:Xiaoyu's commits focused on implementing and testing a video super-resolution model. The code modifications included the addition of model files, test scripts, and training-related Python files. These changes suggest involvement in developing and evaluating a deep-learning-based approach to enhance video quality. Further contributions involved incorporating utility functions and data-handling scripts.
super-resolutionpytorchvideovideo-frame-interpolationvideo-super-resolution
Mukosame/Chinese-Colors

Apr 2015 - Jun 2016

Contributions:21 commits, 18 pushes, 1 branch in 1 year 2 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial