The Event information is available HERE
Since the event is already fully booked, we invite you to watch the livestream on YouTube on October 17th-18th HERE.
The last year has been a landmark one, with the arrival of ChatGPT and GPT-4, demarcating a new era of AI research on foundation models. While scale was always a key factor in learning, these models have shown that scale has an unexpectedly big impact on generalization and, importantly, the importance of multimodality. This paves the way for AI subfields that had splintered in the last decades, like language, vision, audio, and so on, to converge once again. This happens not simply to improve numbers by an iota but as instrumental learning components to generalist AI.
As such, together with several key researchers in NLP, vision, multimedia, and so on, we took the initiative to organize one of the first European workshops on this very subject and the first that brings renowned researchers from different AI sub-disciplines in Europe, who would normally not meet each other. The workshop will be under the umbrella of ELLIS, AIDA, and AI4Media, in an effort to draw in a diverse AI population. We hope to have deep interactions and lead to bigger initiatives, perhaps together with outside-EU colleagues and initiatives.