Jingyi Shen

Jingyi Shen works at the intersection of machine learning and scientific visualization, developing deep learning methods such as flow-based generative models and latent-space representations to analyze, compress, and explore large scientific datasets. Their work also spans applied predictive modeling, including stock price forecasting, mobile app usage prediction, and industrial data analysis, and more recently touches on efficient inference techniques for large neural network models. This suggests a research profile combining foundational deep learning methods with applications in visualization and data-driven prediction tasks.

Publication output has been relatively steady with modest year-to-year fluctuation over the past decade, averaging about two papers per year in the last five years, with a notable spike of preprints listed for 2026.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026