IFML Seminar
IFML Seminar: 04/04/25 - Robust Autonomy Emerges from Self-Play
Abstract: Self-play has powered breakthroughs in two-player and multiplayer games. In this talk, I show that self-play is a surprisingly effective strategy in another domain: robust and naturalistic driving emerges entirely from self-play in...
Upcoming Events
- April412:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Self-play has powered breakthroughs in two-player and multiplayer games. In this talk, I show that self-play is a surprisingly...
- April1112:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: The widespread deployment of AI systems in critical domains demands more rigorous approaches to evaluating their capabilities and safety...
- April1812:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Ill-posed inverse problems appear in many critical scientific imaging scenarios where the goal is to reconstruct cleaner images faster...
- April2512:15 - 1:15pm
IFML Seminar
Event DetailsAbstract : In the literature on benign overfitting in linear models, also referred to as minimum norm interpolation, it is...
Past Events
- February20throughFebruary21
Workshop
Event Details2 days of academic research presentations on the mathematical theory underpinning modern machine learning paradigms. Presented by The University of...
- February1412:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Mainstream artificial neural network models, such as Deep Neural Networks (DNNs) are computation-heavy and energy-hungry. Weightless Neural…
- February712:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Reinforcement Learning from Human Feedback (RLHF) has become the predominant method for aligning large language models (LLMs) to be...
- January3112:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: We pose a fundamental question in computational learning theory: can we efficiently test whether a training set satisfies the...
- December1312:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Deep neural networks (DNNs) have become popular tools to solve ill-posed image recovery problems, such as those associated with...
- December101:30 - 4 pmEvent Details
One of the most striking findings in modern research on large language models (LLMs) is that, given a model and...
