IFML Seminar
IFML Seminar: 10/03/25 - Successor Measures and Self-supervised Reinforcement Learning
Abstract: We introduce a method for learning behavioral foundation models using the successor measure. We show that any visitation distribution can be represented using an affine combination of policy-independent basis functions. By learning these...
Upcoming Events
- October312:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: We introduce a method for learning behavioral foundation models using the successor measure. We show that any visitation distribution...
- October1012:15 - 1:15pm
IFML Seminar
Event DetailsABSTRACT: What would it mean for AI to understand skilled human activity? In augmented reality (AR), a person wearing smart...
- 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...
Past Events
- March812:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Lion (Evolved Sign Momentum) is an optimizer discovered through program search ( https://arxiv.org/abs/2302. 06675). It was shown to perform...
- March112:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Diffusion models have emerged as a powerful new approach to generative modeling. In this talk, we present the first...
- February2312:15 - 1 pm
IFML Seminar
Event DetailsAbstract: The problem of parallel stochastic convex optimization (SCO) was first formalized by Nemirovski in ’94. In this problem, there...
- February1612:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Foundational large language models, while successful at shorter contexts, struggle to scale to longer context inputs. Preventing performance decay…
- February212:15 - 1 pm
IFML Seminar
Event DetailsAbstract: The Gromov-Wasserstein (GW) distance quantifies dissimilarity between metric measure (mm) spaces and provides a natural correspondence between them…
- January2612:15 - 1 pm
IFML Seminar
Event DetailsAbstract: How can we find and apply the best optimization algorithm for a given problem? This question is as old...
