Lecturer in Machine Learning
School of Computer Science, The University of Sydney
Email: yu.yao@sydney.edu.au
I completed my doctoral studies at The University of Sydney, where I studied under Professor Tongliang Liu. I worked as a postdoctoral fellow at Mohamed bin Zayed University of Artificial Intelligence and Carnegie Mellon University, collaborating with Professor Tongliang Liu and Professor Kun Zhang.
My goal is to make the machine learning systems to be reliable and aligned with human values. This includes the following directions:
- Robustness: How can we build ML systems that are robust to different types of noise in different data modalities? How can we improve ML systems' adaptability to changing environments? How can we design the evaluation methods to existing ML systems in real-world settings?
- Interpretable Representation: How can we explain the representation learned by different ML methods? What would be the necessary assumptions for developing disentangled representations under different cases? How can we use multimodal data together to encourage the disentanglement? What empirical methods are needed to effectively achieve such disentanglement?