Michalis Vazirgiannis
Distinguished Professor, Ecole Polytechnique, France &
Αffiliate Professor MBZUAI, UAE
M. Vazirgiannis is a Distinguished Professor at Ecole Polytechnique in France. Since 2025 he also holds an affiliate Professor position in MBZUAI at UAE. He has been intensively involved in data science and AI related research. His broad research area is in methods for data scienceand machine/deep learning methods for diverse data types and applications (including graphs, text, time series). Recently he is working on multimodal LLMs with applications in the area of proteins/cells and also LLMs for Arabic dialects. In the same context he has lead efforts for pretrained language models and resources for multilingual NLP and Biomedical applications. The other branch of his research is on Graph Machine/deep learning and graph generative AI especially GNNs and aspects including expressiveness, efficiency, generation. His research and industrial impact is spanning different domains such as web advertising, social networks, online gambling, insurance, legal text applications, aviation and maritime industry and the bio/medical domain. He has been teaching machine/deep learning and AI courses for academic and executive training studies in France, China, UAE, Morocco, Spain, Greece. Pr. Vazirgiannis has published more than 250 papers in international journals and proceedings of international conferences including NeurIPS, AAAI/IJCAI, AISTATS, ICLR, EMNLP/ACL, JMLR, JAIR, KDD, Nature/Digital Medicine, Scientific Reports. On the side of supervision he has supervised 35 completed PhD theses. Finally he has been able to attract significant funding for research from national and international sources, from research agencies and industrial partners (including Google, Airbus, Huawei, Deezer, BNP, LVMH). He lead(s) academic research chairs (DIGITEO 2013-15, ANR/HELAS 2020-26, WASP/KTH 2020-25) and an industrial one (AXA, 2015-2018). He has received several awards and distinctions including i. Marie Curie Intra European Fellowship (2006-8) ii. “Rhino-Bird International Academic Expert Award” in recognition of his academic/professional work from Tencent (2017), iii. best paper awards in international conferences (such as IJCAI 2018, CIKM2013, COLING2025). He has been invited to media interviews in France, USA and China and published popularized articles in French and Greek magazines/newspapers on Artificial Intelligence topics.
More info at: http://www.lix.polytechnique.fr/dascim/
Title: Graph Generative AI for Science and Engineering
Graph-structured representations are ubiquitous across the physical, biological, and engineered worlds. While foundation models have fundamentally transformed text and vision, adapting generative artificial intelligence to non-Euclidean, geometrically constrained systems introduces unique algorithmic challenges. This keynote presents state-of-the-art graph generative AI methodologies, bridging discrete graph topology, continuous geometric deep learning, and multi-modal alignment. We examine core generative architectures—including Variational Graph Autoencoders (VGAEs), continuous diffusion processes, flow matching, and cross-modal LLM prompting—tailored to solve mission-critical scientific and industrial tasks. First, in biomedicine and pharmacology, we discuss graph generative pipelines for de novo molecular design and functional captioning (e.g., Prot2Text/PPI2Text), decoding complex biochemical structures into interpretable properties. Second, in electronic design automation (EDA), we demonstrate how graph generation optimizes Boolean circuit synthesis and placement dynamics for advanced chip architectures. Finally, in construction engineering and architecture, we explore generative graph frameworks that automate floor-plan layout synthesis, and aspects of MEP) routing and BIM network integration. The session concludes with a roadmap for scaling multimodal graph foundation models across industrial engineering.