Summary
Yule Wang is a Ph.D. candidate and graduate research assistant at Georgia Tech specializing in probabilistic machine learning where he develops generative and sequence models for high-dimensional multivariate time-series, with applications in computational neuroscience. He combines deep generative approaches—disentangled VAEs and diffusion models—with domain-focused inference to uncover scientifically meaningful latent dynamics, including work on myoelectric control using sEMG. With eight years of experience spanning research internships at Meta, Alibaba, and ByteDance, Yule has shipped production improvements like a 1.4% AUC gain in large-scale CTR systems and measurable user-satisfaction boosts in NLP products. He bridges academic rigor and engineering impact, translating complex probabilistic models into deployable solutions. Based in Atlanta, he brings cross-disciplinary training from Shanghai Jiao Tong University to tackle sequence modeling problems that require both theoretical depth and practical scalability.
8 years of coding experience