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
- April134 - 5 pmEvent Details
AI Safety Abstract: Thoughts about AI safety, shaped by a year's leave at OpenAI to work on the intersection of...
- April1212 - 1 pmEvent Details
Abstract Machine learning approaches to medical image reconstruction are of considerable recent interest, especially supervised approaches that use a corpus…
- April712:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Machine learning systems are built using large troves of training data that may contain private or copyrighted content. In...
- March3112:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Unsupervised learning with functional data is an emerging paradigm of machine learning research with applications to computer vision, climate...
- March313:15 - 4 pm
IFML Seminar
Event DetailsAbstract: Deep learning is delivering unprecedented performance when applied to various data modalities, yet there are data distributions over which...
- March302 - 3 pmEvent Details
Abstract: Magnetic Resonance Imaging (MRI) enables non-invasive measurement of anatomy with a wide range of image contrast, but incurs significant...
