Xuenan Xu
Junior Researcher at Shanghai AI Laboratory
Yangpu District, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolXuenan Xu is a Ph.D.-trained researcher specializing in general audio understanding and generation, with eight years of engineering and research experience spanning speech, sound, and music. Currently a Junior Researcher at Shanghai AI Laboratory after internships and visiting roles at Meta, Alibaba, and the University of Surrey, Xuenan builds AI model training frameworks and practical systems in Python. Their work ranges from fine-grained temporal audio captioning and codec learning to large-scale productization—evidenced by implementing an open-source Tongyi AI storyteller and optimizing EMG handwriting models at Meta. Based in Shanghai, they combine academic rigor with hands-on engineering, often bridging model compression and real-world deployment challenges. An unusual strength is fluency across the stack: from frontend prototypes early in their career to cutting-edge audio ML research today.
8 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Shanghai Jiao Tong University
Github Skills (38)
opentype10
octicons10
fonts10
heroicons10
powerline10
aggregator10
statusline10
material-design-icons10
recipe10
webfonts10
font-size10
ufo10
font-awesome10
variable-fonts10
android-application10
Programming languages (2)
Github contributions (5)
wsntxxn/AudioCaption
Nov 2020 - Feb 2023
Audio captioning recipe
Contributions:3 releases, 27 commits, 1 PR in 2 years 2 months
audiocaptionrecipe
wsntxxn/TextToAudioGrounding
Oct 2020 - Nov 2022
Contributions:6 commits, 14 pushes, 4 comments in 2 years
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.