IFML Seminar
IFML Seminar: 10/17/25 - Sample-Efficient Personalized Reward Models for Pluralistic Alignment
Abstract: Large pre-trained models trained on internet-scale data are often not ready for deployment out-of-the-box. They are heavily fine-tuned and aligned using large quantities of human preference data, usually elicited using pairwise comparisons. While...
Upcoming Events
- October1712:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Large pre-trained models trained on internet-scale data are often not ready for deployment out-of-the-box. They are heavily fine-tuned and...
- October2412:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Learning from sequential, temporally-correlated data is a core facet of modern machine learning and statistical modeling. Yet our fundamental...
- November712:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for...
Past Events
- September2212:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Graph neural networks (GNNs) are successful at learning representations from most types of network data but suffer from limitations...
- September1512:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Whittle index policy is a powerful tool to obtain asymptotically optimal solutions for the notoriously intractable problem of restless...
- April2812:15 - 1 pm
IFML Seminar
Event DetailsWe discuss the problem of positive-semidefinite extension: extending a partially specified covariance kernel from a subdomain Ω of a rectangular...
-
Event Details
Abstract: We demonstrate the power of combining the forward image acquisition model with deep learning solutions for inverse MRI problems...
- April20throughApril22
Workshop
Event DetailsThis workshop aims to bring together researchers with different backgrounds in computer science, machine learning, statistics and math who are...
- April1310 am - 4 pmEvent Details
The Machine Learning Laboratory Research Symposium will showcase the latest cutting-edge work from our students and faculty. We'll have an...
