Generative Artificial Intelligence (GenAI) has rapidly emerged as a transformative paradigm in modern data-driven research and applications. In this talk, I will provide a brief introduction to the core ideas underpinning GenAI, including Transformer architectures, Large Language Models (LLMs), and Deep Graph Neural Networks. The presentation will outline the basic principles of deep learning, while deliberately omitting heavy mathematical and algorithmic details to ensure accessibility for a broad audience.
I will then highlight a selection of recent research projects that I have been involved in, illustrating how GenAI techniques can be applied across diverse domains, demonstrating the flexibility and interdisciplinary potential of generative models and graph-based learning methods.