Some specific research topics that he is interested in and currently working on:

• Probabilistic topic modeling: He is extremely interested in developing various topic models that can explore different discourse structures and other meta information associated with natural language text.
• Nonparametric Bayesian methods, e.g., Dirichlet process, Pitman-Yor process, and Indian Buffet process. He has been working on developing different sampling methods for Pitman-Yor process since his Ph.D. study.
• Inference/ optimization algorithms, e.g., MCMC methods, Variational Bayesian (VB), and various numerical optimization algorithms
• Relational learning techniques, e.g., probabilistic matrix factorization, tensor factorization, etc. He is interested in combining matrix factorization techniques with topic models to improve, for example, recommendation systems.
• Natural Language Processing. He has worked in the NLP group at Macquarie University for about four years. He is interested in how to utilize different linguistic features in topic modeling.