My research interests lie in machine learning and data science, especially in causal discovery, transfer learning, and deep learning. I study how the causal generative process of data can benefit learning in non-standard settings, such as transfer learning and weakly-supervised learning. I also develop methods to infer causal models from various kinds of observational data, including incomplete time series, noisy data, and nonstationary/heterogeneous data. On the application side, I am interested in computer vision, biomedical informatics, and economic data analysis.