 |
| Laure Soulier |
| speaker |
Bio
Laure Soulier is Professor in Computer Science at ISIR at the Institut for Intelligent Systems and Robotics (ISIR) of Paris, within the MLIA team. Her research is motivated by the proposal of new models based on deep learning for information retrieval and automatic natural language processing. The common objective of these models is to process and access textual data. (Large) language models are at the core of her various projects, which have applications related to semantic learning, human-machine interaction (in information retrieval and robotics), and continual learning. Since 2018, she has been involved in two major research projects focusing on data-to-text generation and conversational information retrieval. Her topics of interest include data-to-text generation, conversational search, language models for robotics, continual learning and domain adaptation.
Google scholar page • Personal webpage
Talk
The release of ChatGPT has changed the way AI technologies are perceived as possible for the next years. In this keynote, we will dive deep into the inner workings of ChatGPT and more particularly of (large) language models. From early Bengio’s works in 2003 to very recent advances in the research community, we will explore the evolution of model architectures, their ability to reason, and their potential for generalization and adaptation.