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
- June15throughJune16
Workshop
Event DetailsIn step with its mission to making AI more accurate and accessible, IFML will be participating in the 2026 WeTeach_CS...
- April1712:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Lengthy data acquisition remains a major bottleneck in magnetic resonance imaging (MRI), often necessitating tradeoffs in resolution and signal-to-…
- April1012:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Sparse recovery, i.e., estimating a sparse signal theta* in R^d from few noisy measurements y = Xtheta* + xi...
- April32 - 3 pm
IFML Seminar
Event DetailsAbstract: In this work, we give a polynomial time and sample complexity algorithm for efficiently learning the parameters of a...
- March1312:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: A central challenge in machine learning is reliability: ensuring that an algorithm’s predictions remain accurate and stable even when...
- March3throughMarch4Event Details
Join Texas Robotics, the Machine Learning Lab, and Good Systems on March 3 & 4 for a two-day symposium exploring...
