Hao-min Liu
Research Scientist at Academia Sinica
New Taipei, Taiwan
Summary
👤
Senior🎓
Top SchoolHao-min Liu is a research scientist with eight years of experience applying machine learning and signal-processing techniques to real-world problems, from air-quality forecasting to music generation. At Academia Sinica he developed novel generative models—GANs and VAEs—to produce and arrange multi-instrument lead sheets, and designed hybrid ARIMA–neural approaches with wavelet clustering for hourly PM2.5 forecasting. Proficient in Python, TensorFlow, and PyTorch, he pairs strong implementation skills with a solid publication record of 10+ international papers. His work bridges creative AI and environmental sensing, demonstrating an uncommon combination of artistic-domain generation and rigorous time-series modeling.
8 years of coding experience
3 years of employment as a software developer
Master's degree, Electronics Engineering, 3.85/4.3, Master's degree, Electronics Engineering, 3.85/4.3 at National Chiao Tung UniversityUniversity of Illinois Urbana-Champaign
Chinese, English, German
Github Skills (6)
music-composition9
music9
music-information-retrieval9
music-generation9
audio9
jekyll2
Programming languages (2)
Github contributions (5)
liuhaumin/LeadsheetArrangement
Apr 2018 - Jan 2019
Lead Sheet Generation and Arrangement 自動簡譜編曲
Contributions:185 commits, 2 PRs, 164 pushes in 9 months
music-compositionmusic-generationleadsheetarrangement
liuhaumin/vine-tree
Aug 2017 - Dec 2018
Contributions:2 PRs, 11 pushes, 3 branches in 1 year 4 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.