My research interests lie in the broad area of machine learning and artificial intelligence. I was drawn to the discipline of machine learning by the way it blends mathematics and real applications. I am mostly interested in developing unsupervised and semi-supervised learning algorithms and applying them to solve various real problems in computer vision, natural language processing, product search and recommendation, healthcare, and other application domains. On the theory side, I seek to develop deeper understanding into the principles of practical methods and answer questions like under what circumstance one method is better than another and when a particular assumption breaks down. I usually end up gaining new insights by studying such questions, which give me inspirations of developing more effective solutions. The topics I recently worked on include:

Pre-training and self-supervised learning;
Zero/Few-Shot learning and meta-learning;
Graph-based unsupervised and semi-supervised learning;
Intent recognition for dialogue systems;
Vision-language approaches and applications in healthcare;
Product search and recommender systems;
Real-world image restoration.