Wei-tsung Lu
Member Of Technical Staff at xAI
San Francisco Bay Area United States
Summary
👤
Senior🎓
Top SchoolWei-tsung Lu is an audio AI researcher and engineer with 8+ years of experience building state-of-the-art systems for text-to-speech, controllable music generation, and music information retrieval. He has driven production-quality models and components—latent diffusion models, neural audio codecs, and multimodal alignment—while shipping features used by millions at TikTok/CapCut and leading research efforts at Skywork AI. His work on music source separation (Band-Split RoPE Transformer) won the MDX-23 challenge and has been widely adopted and reimplemented in industry tools. Now at xAI he’s applying that expertise to voice modeling for Grok, bridging cutting-edge research with product-scale deployment. Trained in music technology (NYU) and computer science (NTHU), he combines musical signal processing intuition with deep learning rigor, and is notable for turning research prototypes into high-impact, production systems.
8 years of coding experience
7 years of employment as a software developer
Master of Music, Music Technology, Master of Music, Music Technology at New York UniversityBachelor of Science - BS, Computer Science, Bachelor of Science - BS, Computer Science at National Tsing Hua University
Chinese, EnglishGithub contributions (5)
s603122001/Vocal-Melody-Extraction
Jun 2018 - Sep 2018
Contributions:29 commits, 24 pushes, 2 branches in 2 months
s603122001/Music-Style-Transfer
Jun 2018 - Jul 2021
Contributions:12 commits, 11 pushes, 3 branches in 3 years 1 month
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.