I am a Ph.D. student in the School of Computing and Information Systems at the University of Melbourne, where I am fortunate to be advised by Professor Sarah Erfani and Dr. Feng Liu. Prior to my doctoral studies, I received my Master of Data Science from the same university under the guidance of Associate Professor Mingming Gong and Dr. Liuhua Peng. I also hold a Bachelor of Science in Mathematics and Statistics from the University of Melbourne.
My research focuses on robustness and generalisation in large language models, particularly how post-training can adapt model behaviour to new requirements while preserving useful capabilities. I am interested in the gap between improvements under limited supervision and reliable behaviour in deployment, and in developing learning methods that remain dependable as tasks and environments change.
More broadly, I am interested in the statistical foundations of trustworthy machine learning, including uncertainty quantification and conformal prediction. I draw on my background in mathematics and statistics to study model reliability and principled evaluation, with additional work in time-series modelling.
Robustness and generalisation in large language models, particularly through post-training and adaptation. My focus is on reliable behaviour under changing conditions while preserving the useful capabilities of foundation models.
02
Trustworthy & Statistical Learning
The statistical foundations of trustworthy machine learning, including uncertainty quantification and conformal prediction. I am interested in principled ways to assess reliability and understand the limits of model predictions.
03
Time Series Modelling
Machine learning for temporal data, spanning forecasting and generative modelling. I study how models capture evolving patterns and generalise across different settings, guided by statistical structure.