About me

Hello there!

I am a PhD candidate at University of Bristol, supervised by Song Liu. I am interested in using machines to uncover the intrinsic nature of the world. To this end, my current research focuses on generative modeling, which provides a principled way for capturing the latent factors and generative processes behind observed phenomena.

Selected Publications & Preprints

• (Preprint) Zero-Flow Encoders. Wang, Y.*, Wang,L.*, Liu, S. & Suzuki, T.

• (NeurIPS2025) Direct Fisher Score Estimation for Likelihood Maximization. Khoo, S., Wang, Y., Liu, S. & Beaumont, M.
  • Spotlight, Top 3%
• (UAI2025) Guiding Time-Varying Generative Models with Natural Gradients on Exponential Family Manifold. Liu, S., Wang, L. & Wang, Y.
  • Outstanding long paper, at Deep Generative Model in Machine Learning: Theory, Principle and Efficacy workshop at ICLR2025.

* Equal contribution