Ömer Deniz Akyıldız

Group Members

O. Deniz Akyildiz

Assist. Prof. — Head of Group

Deniz is an assistant professor at Imperial who initiated the group in 2023, with broad interests in sampling, optimization, and stochastic filtering. [website]

Paula Cordero-Encinar

PhD student

Paula joined the group in 2024. She works on sampling, generative models, and theoretical foundations. She is co-supervised by Andrew Duncan and she is a part of StatML CDT. [website]

James Cuin

PhD student

James joined the group in 2025. He works on statistical inference and generative models. He is co-supervised by Yanbo Tang and he is a part of StatML CDT.

Joanna Marks

PhD student

Joanna joined the group in 2025. She works on generative models and optimal transport. Her second supervisor is Riccardo Passeggeri and she is a part of StatML CDT.

Paul F. Valsecchi Oliva

PhD student

Paul joined the group in 2023. He works on theoretical foundations of learning algorithms. His second supervisor is Andrew Duncan and he is a part of StatML CDT.

Tim Wang

PhD student

Tim joined the group in 2024. He works on generative models and interacting particle algorithms.

Matthew Young

PhD student

Matthew joined the group in 2025. He works on sampling and generative models. [website]

Jackie Zhang

PhD student

Jackie joined the group in 2025. He works on generative models and interacting particle systems.

Robin Mury

Visiting MSc student

Robin is a MSc student at ETH Zurich, visiting our group for the first half of 2026.

News from the Group

• January 2026: Congratulations to Tim Wang, Rafael Athanasiades and Adam Rozzio for getting their papers accepted at AISTATS 2026! The group will be presenting two papers at AISTATS. Tim's paper, titled Training Latent Diffusion Models with Interacting Particle Algorithms introduces an interacting particle method for training latent diffusion models. Adam (who was a summer intern in the group in 2024) and Rafael (who completed a miniproject in the group in 2025) co-authored the paper Momentum SVGD-EM for Accelerated Maximum Marginal Likelihood Estimation which introduces a new, accelerated method for maximum marginal likelihood estimation in latent variable models.
• December 2025: The group showcased three works at NeurIPS 2025 (two main-track papers and one workshop paper):
  • Paula presented Sampling by averaging: A multiscale approach to score estimation, tackling sampling from complex distributions via multiscale fast-slow systems.
  • James presented Learning Latent Variable Models via Jarzynski-adjusted Langevin Algorithm, introducing a new Monte Carlo method for latent variable models.
  • Deniz presented A Gradient Flow approach to Solving Inverse Problems with Latent Diffusion Models (primary author Tim Wang) at the Frontiers in Probabilistic Inference: Sampling Meets Learning workshop, proposing a framework for solving inverse problems with latent diffusion models.
• December 2025: Joanna presented the poster Scalable Learning of Energy-Based Priors via Interacting Particle Systems at the Amortized ProbML workshop. See more details.
• September 2025: Matthew's paper On diffusion posterior sampling via sequential Monte Carlo for zero-shot scaffolding of protein motifs was published in Transactions on Machine Learning Research (TMLR).
• July 2025: Paula received the Best Student Paper award for Proximal Interacting Particle Langevin Algorithms at the Conference on Uncertainty in Artificial Intelligence (UAI). Here is the announcement on X.

Past (Imperial)

StatML first year (mini) project supervision

Summer/Visiting students and Interns

Masters

Undergraduate

Warwick/Cambridge