We are very happy to share that Dr. Efstratios Gavves (Assoc. Prof. at University of Amsterdam) will visit our department for an invited talk regarding “Grounding Foundation Models in Reality with Physics- and Causality-informed World Models”.
Logistics:
📅 Date: Thursday Nov-21, 7pm (Greece time)
🏢 Location: Auditorium hall (1st floor), Department of Informatics and Telematics, Harokopio University, 9 Omirou Str., 17778, Tavros
💻 (Capability for) remote connection: https://us06web.zoom.us/j/83240713654?pwd=eCrSCTwPblbbSxEI6Zm7ZGHqzy3HO7.1
🌍 Participation: The talk is open to the general public
Talk abstract: Foundation Models have taken the AI world by storm with their ability to generalize to novel, complex tasks beyond the scope of their training data. Whether they achieve this through true generalization or by ‘remembering’ vast training sets is debatable, but their performance is undeniably superior to previous approaches. With this success, the critical questions now are: What are the limitations of current large-scale learning? What frontiers remain? And what are the implications of these developments? In this talk, I argue that Robot Learning represents one of the most exciting frontiers, with Robot General Intelligence standing as the quintessential goal for AI. However, current approaches to Robot Learning face fundamental limitations that prevent them from achieving this ideal. I will present my recent work on a novel paradigm that incorporates explicit physical and causal priors into world models, enabling real robots to perform one-shot policy learning. This approach allows robots to learn new tasks from as little as one demonstration, pushing the boundaries of what’s possible in real-world robot learning.
