Events

Date: 5 March 2025   Time: 11:00 - 12:30

Location: Peter Landin Room 4.01, 4th floor (next to the elevators)

Abstract: Recent developments in AI have shown the remarkable power of deep learning, deep reinforcement learning, and LLMs. The resulting systems, however, require large amounts of data, are not transparent or reliable, and struggle with structural forms of reuse and generalization. In this talk, I'll argue that these limitations can be addressed by learning suitable symbolic representations from raw data, and illustrate the approach by considering two concrete problems in the setting of actions and planning: learning general world models and learning general planning strategies.

Bio: Hector Geffner is an Alexander von Humboldt Professor at RWTH Aachen University in Germany. Before joining RWTH in 2023, he was an ICREA Research Professor at the Universitat Pompeu Fabra in Barcelona, Spain. Hector obtained a Ph.D. in Computer Science at UCLA and worked at the IBM T.J. Watson Research Center in New York and at the Universidad Simon Bolivar in Caracas. Distinctions for his work include the ACM Dissertation Award and three ICAPS Influential Paper Awards. He currently leads a project on representation learning for acting and planning (RLeap) funded by an ERC grant.