About
I am a PhD student in Mathematical Informatics at the Graduate School of Information Science and Technology, University of Tokyo, supervised by Prof. Taiji Suzuki. I am also a Research Associate at the Deep Learning Theory Team, RIKEN AIP. I also work closely with Prof. Song Liu on various research projects.
Education
I received my Bachelor’s degree in Mathematics with Statistics from the University of Bristol (2021–2024), graduating with First Class Honours. I then completed a Master’s degree in Computational Statistics and Machine Learning (CSML) at University College London (UCL) (2024–2025), graduating with Distinction. My Master’s thesis was supervised by Prof. David Barber and Dr. Mingtian Zhang at the UCL AI Centre.
I am currently pursuing a PhD in Mathematical Informatics at the University of Tokyo (2026-2029).
Publications & Works in Progress
- Leyang Wang, Yakun Wang, Song Liu and Taiji Suzuki. Zero Flux: Flow-Based Comparison of High-Dimensional Discrete Distributions - In Progress
- Yakun Wang, Leyang Wang, Song Liu and Taiji Suzuki. Zero-Flow Two-Sample Tests - In Progress
- Yakun Wang*, Leyang Wang*, Song Liu and Taiji Suzuki. Zero-Flow Encoders - ICML 2026
- Leyang Wang*, Mingtian Zhang*, Zijing Ou and David Barber. VarDiU: A Variational Diffusive Upper Bound for One-Step Diffusion Distillation — NeurIPS 2025 Workshop on Structured Probabilistic Inference & Generative Modeling
- Jiahao Yu, Qizhen Ying, Leyang Wang, Ziyue Jiang and Song Liu. Missing Data Imputation by Reducing Mutual Information with Rectified Flows — NeurIPS 2025
- Song Liu, Leyang Wang and Yakun Wang. Guiding Time-Varying Generative Models with Natural Gradients on Exponential Family Manifold — UAI 2025 & ICLR Deep Generative Model in Machine Learning: Theory, Principle and Efficacy Workshop Outstanding Long Paper Award
- Daniel J. Williams*, Leyang Wang*, Qizhen Ying, Song Liu and Mladen Kolar. High-Dimensional Differential Parameter Inference in Exponential Family using Time Score Matching — AISTATS 2025
* Equal contribution
Awards, Scholarships & Bursaries
- Conference on Uncertainty in Artificial Intelligence (UAI) Scholarship — 2025
- ICLR DeLTa Workshop Outstanding Long Paper Award — 2025
- Summer Research Bursary, School of Mathematics, University of Bristol — 2024
My research interests lie in statistical machine learning, with a focus on deep generative models and their applications to computer vision. I am particularly interested in developing principled methods for solving high-dimensional machine learning problems through statistical discrepancies minimisation.
Reviewer
- UAI 2026
Research Interests
- Probabilistic Modelling
- Statistical Discrepancy Minimisation
- Density Estimation