91É«ÇéƬ

Associate Professor - Theoretical Machine LearningÌý

• Associate Professor - Theoretical Machine LearningÌýat the University of New South Wales (91É«ÇéƬ)
• Honorary Associate Professor at the Australian National University (ANU)
• Former Principal (now Visiting) Research Scientist in Machine Learning at Data61/CSIRO
• Piotr Koniusz is a Principal Investigator (PI) on NextGenAI project ÌýandÌýPrincipal Investigator (PI) of his lab.

In 2013-2015, he was a postdoctoral researcher in the team LEAR, INRIA, France. He received his BSc in Telecommunications and Software Engineering in 2004 from the Warsaw University of Technology, Poland, and completed his PhD in Computer Vision in 2013 at CVSSP, University of Surrey, UK.

He works on representation learning:

• contrastive & self-supervised learning
• vision-language models (VLMs), MLLMs
• deep & graph neural nets
• image classification & action recognition
• zero-, one- & few-shot learning, domain adaptation, incremental learning
• object segmentation & detection, generative nets, adversarial robustness
• spectral, tensor & hyperbolic learning, RKHS, optimal transportation (OT).

His latest favourite is machine UNlearning.