MSRNE Generative Modeling & Sampling Workshop | Day 1
Episode details
Episode description
The goal of the Generative Modeling & Sampling Workshop was to foster dialogue across communities working at the intersection of generative modeling, sampling, stochastic control, scientific machine learning, and related areas. By bringing together perspectives from machine learning, statistics, applied mathematics, physics, chemistry, and computational biology, the workshop aimed to highlight shared mathematical and algorithmic principles, explore foundational questions and emerging applications, and create opportunities for new collaborations. It served as a forum for exchanging ideas, identifying promising directions, and accelerating progress on both fundamental and applied problems. Event page: https://www.microsoft.com/en-us/research/event/msrne-generative-modeling-sampling-workshop/ Monday, August 10 | Generative Modeling 0:00 Opening remarks Yuanqi Du & Carles Domingo-Enrich 5:30 Generative machine learning for free energy estimates Jutta Rogal 40:52 Reasoning with generative models through energy minimization Yilun Du 1:14:34 Push probabilistic machine learning out of equilibrium Yuanqi Du 1:42:39 Blind denoising diffusion models Zahra Kadkhodaie 2:16:15 Robust inference-time steering of protein diffusion models via embedding optimization Luhuan Wu 2:51:24 Free energy estimation with neural transport on any state space Jiajun He 3:14:32 Scalable sampling with flow and diffusion models Denis Blessing & Mouyang Cheng 3:35:54 Scalable Boltzmann generators for equilibrium sampling of large-scale materials Max Schebek 3:55:40 Fast and ultra-capable protein design with Genie 3 Minji Lee 4:13:57 Efficient inference-time scaling for diffusion sampling: Continuous and discrete Jiequn Han Day 2 recording: https://youtu.be/UeSLh7Gt2V8
Watch also from the same channel
More episodes from this channel
You might be interested in
