Rate My Professor Xuhui Fan

Dr. Xuhui Fan is a Lecturer in Artificial Intelligence in the School of Computing within the Faculty of Science and Engineering at Macquarie University. He obtained his Bachelor’s degree in Mathematical Statistics from the University of Science and Technology of China in 2010 and his PhD in Computer Science from the University of Technology Sydney in May 2015. Prior to joining Macquarie University, Fan held the position of Lecturer in the School of Information and Physical Sciences at the University of Newcastle, Australia. He also served as a Postdoctoral Fellow in the School of Mathematics and Statistics at the University of New South Wales and as a Project Engineer at Data61, CSIRO (formerly NICTA). These roles have equipped him with extensive experience in both academic research and applied computational projects.

Fan’s research focuses on generative AI, large language models, Gaussian processes, deep generative models, variational inference methods, stochastic point processes, Bayesian nonparametrics, space partitions, and Markov chain Monte Carlo methods. He has authored numerous publications in leading journals and conferences, contributing significantly to advancements in machine learning and artificial intelligence. Key works include 'Data-dependent Rectangular Bounding Processes' (IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026), co-authored with Bin Li, Prosha A. Rahman, and Scott A. Sisson; 'Federated Neural Nonparametric Point Processes' (Artificial Intelligence, 2026), with Hui Chen and others; 'Hyperbolic-Enhanced Mixture-of-Experts Mamba for Sequential Recommendation' (AAAI Conference on Artificial Intelligence, 2026); 'PBDD: a prompt-based learning approach for few-shot social media depression detection' (IEEE Transactions on Computational Social Systems, 2026); and 'A client–server based recognition system: non-contact single/multiple emotional and behavioral state assessment methods' (Computer Methods and Programs in Biomedicine, 2025). Earlier notable publications encompass 'Free-Form Variational Inference for Gaussian Process State-Space Models' (ICML, 2023), 'Continuous-Time Edge Modelling using Non-Parametric Point Processes' (NeurIPS, 2021), 'Rectangular Bounding Process' (NeurIPS, 2018), and several others presented at ICML, AISTATS, and NeurIPS. Fan leads the Macquarie Generative AI research group and serves as Chief Investigator on the project 'LP23: Ethical Enterprise Representations for Personalised Sustainable Finance' (2025–2028). He is affiliated with the Data Horizons Research Centre and Frontier AI Research Centre at Macquarie University.