IFML Seminar
IFML Seminar: 08/28/26 - Fast and Robust Diffusion Posterior Sampling for MR Image Reconstruction Using Preconditioned Langevin Sampling
Abstract: The Unadjusted Langevin Algorithm (ULA) in combination with diffusion models can generate high-quality MRI reconstructions with uncertainty quantification from highly undersampled k-space data. However, sampling methods such as diffusion posterior sampling (DPS) and...
Upcoming Events
- August2812:30 - 1:30pm
IFML Seminar
Event DetailsAbstract: The Unadjusted Langevin Algorithm (ULA) in combination with diffusion models can generate high-quality MRI reconstructions with uncertainty…
Past Events
- February2712:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Sampling is a fundamental algorithmic task with many connections to optimization. In this talk, we survey a recent algorithm...
- February2012:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: To assess the ability of current AI systems to correctly answer research-level mathematics questions, we share a set of...
- February1312:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Particle physicists developed an algorithm called COWs (Customized Orthogonal Weights) for separating signals from backgrounds in certain…
- February612:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Modern generative AI has developed along two distinct paths: autoregressive models for language and diffusion models for image and...
- November2112:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Intelligence often emerges through interaction and competition. Likewise, advanced AI algorithms often rely on competing learning objectives.…
- November1412:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Diffusion language models (DLMs) represent a nascent but promising alternative to GPT-style autoregressive (AR) language models: as opposed to...
