Hi there! My name is Yingzhen (映真) and I hope you enjoy this website. 😀
My research aims to build reliable machine learning systems which can generalise to unseen environments. Two of my current research focuses are:
- Probabilistic ML principles/algorithms for frontier deep learning models;
- Scalable structural representation learning with deep generative models.
I'm also broadly interested in ML topics such as uncertainty quantification, sequential & dynamic data modelling, causal discovery, adaptive ML methods, decision-making algorithms, transfer/meta-learning, information theory and optimisation. See the info for prospective students/postdocs.
Currently I hold two Associate Professor positions at:
- Department of Computing at Imperial College London, UK
- CCDS at Nanyang Technological University, Singapore
In Mar 2024 - Feb 2026 I was also a Turing Fellow at The Alan Turing Institute, UK. Before coming back to academia, I've spent 2.5 wonderful years as a senior researcher at Microsoft Research Cambridge, UK. I read my PhD with Prof. Richard E. Turner in machine learning at the University of Cambridge, UK, where I was also a member of Darwin College.
My PhD thesis is about approximate inference. If you want to know more about approximate inference & probabilistic ML, check out the following materials:
- NeurIPS 2020 tutorial on "Advances in Approximate Inference" (with Cheng Zhang)
- ProbAI 2022 tutorial on "Introduction to Bayesian Neural Networks"
- GeMSS 2023 tutorial on "Sequential Generative Models"
- AAAI 2023 new faculty highlight "Robust and Adaptive Deep Learning via Bayesian Principles" [talk video]
- UAI 2025 tutorial on "Modern Approximate Inference: Variational Methods and Beyond" (with Diana Cai)
- An incomplete list of topics in approximate inference (still updating)