Hub Postdoctoral Research Associates

Thom is a Postdoctoral Research Associate with the Oxford Control and Verification Group at the University of Oxford. He obtained his doctoral degree (cum laude) from Radboud University in Nijmegen, the Netherlands. His research interests lie broadly on the intersection between control theory, artificial intelligence, and formal verification. With his research, Thom aims to develop techniques that can be used to provide rigorous mathematical guarantees about the safety and reliability of complex and uncertain systems.

Branton is a Postdoctoral Research Associate in the Mathematical Institute at the University of Oxford. He works on the theory of generalisation in learning systems. He uses ideas from algorithmic information theory and statistical physics to understand how learning systems evolve, and why they generalise. Most notably, he recently discovered a new kind of complexity phase transition in learning systems.

Xinyu is a Postdoctoral Research Associate in the Erlangen AI Hub at the University of Oxford, based in the Department of Mathematics. Her research lies at the intersection of stochastic control, game theory, reinforcement learning, and machine learning. She received her PhD in Industrial Engineering and Operations Research from the University of California, Berkeley.

Tristan is a theoretical physicist and applied mathematician specialising in the application of topological data analysis in optics and liquid crystalline structures. He his working on understanding the hypergraph structure stemming from the conformal predictions of an AI classifier as well as the different pooling approaches for graph neural networks and their higher order generalisations.

Eng-Jon recently joined the School of Mathematical Sciences at Queen Mary University of London and is working on applying topological data analysis methods to better understand how DNNs function and learn. His main interests are in visual feature tracking, data mining, pattern recognition, and theoretical machine learning methods. He is interested in how probability distributions propagate through deep neural network layers. He has also applied deep neural networks (DNNs) in the area of medical imaging.

Vukašin is a Postdoctoral Research Associate at the Mathematical Insititute at the University of Oxford. His research focuses on theoretical aspects of topological data analysis and its interactions with various areas of geometry, analysis and dynamics.

Roan is a Postdoctoral Research Associate at Durham University, specialising in the use of tropical geometry in analysing and training neural networks. More broadly, their research interests span tropical geometry, optimisation, probability, and applications in data science. Their PhD was focussed on the probabilistic and computational advantages in using tropical geometry for phylogenetic statistics.

Lukas Waas is a Postdoctoral Research Associate at the University of Oxford. His research spans homotopy theory, stratified spaces, and topological data analysis. In particular, he develops stratified persistent methods for studying heterogeneous and singular data, providing mathematically robust tools for analysing and detecting complex geometric and topological structures. 

Qiquan is a Postdoctoral Research Associate at Queen Mary University of London. Her research interests lie at the intersection of topological data analysis, machine learning, and statistics, with a particular focus on the use of topological methods in machine learning training to improve model interpretability and performance. She received her PhD in Mathematics from Imperial College London.
. 

Kate Wenqi Zhu is a final-year PhD candidate in Applied Mathematics at the University of Oxford. Her research focuses on leveraging higher-order information for efficient nonconvex optimization with applications to AI, with interests spanning computational complexity analysis, tensor approximation, sum-of-squares techniques, implementable high-order subproblem solvers, and adaptive regularization methods. She completed both her undergraduate degree and her first master’s degree in mathematics at Oxford, followed by an M.Sc. in Mathematical Modelling and Scientific Computing. She was awarded the Leslie Fox Prize for Numerical Analysis (Second Prize) in 2025. Prior to her doctoral studies, Kate spent over six years working in quantitative and analytical roles at Goldman Sachs and J.P. Morgan.