Scalable Training of Diffusion Samplers via Fixed-point Score Matching
Episode details
Episode description
This talk explores recent advancements in neural sampling using diffusion models. I will begin by highlighting the shortcomings of prior methods and explaining how recent approaches, inspired by the success of data-driven paradigms, overcome these limitations. I will conclude by showcasing practical applications in materials science and reinforcement learning. Speaker bio: Denis Blessing is a fourth-year PhD candidate at the Karlsruhe Institute of Technology (KIT) and a 2025 Google PhD Fellowship recipient. His research focuses on scalable algorithms for approximate inference and neural sampling with diffusion and flow models. Find seminar details and upcoming talks: https://www.microsoft.com/en-us/research/event/microsoft-research-new-england-generative-modeling-sampling-seminar/
Watch also from the same channel
More episodes from this channel
You might be interested in
