In this talk, I will quickly highlight what has changed with generative AI models, and why we should stay with them even if it's early days. I will provide some examples of customer use cases, and how to run these models with confidence: secure private environments and inference infrastructure, well-trained people, and a responsible AI execution framework (not just principles). I will also...
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. We will explore the backbone architecture of current models called Transformer and its interesting properties. We will discuss why such language models can be considered...
The message-passing paradigm has been the “battle horse” of deep learning on graphs for several years, making graph neural networks a big success in a wide range of applications, from particle physics to protein design. From a theoretical viewpoint, it established the link to the Weisfeiler-Lehman hierarchy, allowing to analyse the expressive power of GNNs. We argue that the very...
I will present a short overview of Project RAISE, its objectives and current work.
