Vasilis Papageorgiou

Title

Large Language Models and the New Era of Machine Learning

Abstract

The advent of Large Language Models (LLMs) has marked a significant milestone in the field of natural language processing and artificial intelligence. These powerful models have redefined the landscape of machine learning, paving the way for unprecedented advancements in understanding and generating human-like text. In this talk, I will explore the fascinating world of LLMs and their revolutionary impact on various fields. I will provide an introduction to LLMs, delve into their main architectural component - the Transformer network, and explain how they operate. Furthermore, I will briefly mention the role of prompting in unlocking LLMs' emergent properties, which enables intriguing possibilities such as in-context and few-shot learning. Additionally, I will share some recent work from my group and discuss other interesting aspects of LLMs that could transform the way we approach natural language processing and artificial intelligence.

About the Speaker

Vasilis Papageorgiou received his 5-year Diploma degree in Electrical and Computer Engineering (ECE) from the Technical University of Crete (TUC), Greece, in 2021. In August 2022, he joined the University of Wisconsin-Madison, where he is currently pursuing his Ph.D. in Computer Sciences. His current research interests include both theoretical and practical aspects of Machine Learning and Deep Learning. He was a co-recipient of the IEEE WCNEE 2021 best paper award.