Published 'Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference' in NeurIPS 2024, Best paper of ICML Workshop on Structured Probabilistic Inference & Generative Modeling.
Research Experience
Worked at Bytedance AI Lab under the supervision of Prof. Lei Li.
Education
Ph.D. student at HKUST, co-advised by Prof. Tong Zhang and Prof. Yang Xiang; M.Sc. degree from the University of Science and Technology of China, supervised by Prof. Enhong Chen.
Background
Research interests: machine learning algorithms and theory, including sampling algorithms, stochastic/nonconvex optimization, and mean-field analysis.