About the IAPP

Vincent Corruble received degrees in Engineering (Ecole Centrale de Lille), a M.Sc. in Systems Engineering (University of Virginia), a Ph.D. in Artificial Intelligence (UPMC, Paris 6). After postdocs in South Africa, the US, and the UK, he joined the faculty of Sorbonne University, LIP6 laboratory, where he has been a member of the Multi-Agent Systems group since 2007.

He has contributed to the fields of Machine Learning and Pattern Recognition, Machine discovery and Data Science, with applications to the history of medicine and medical research. He also worked on learning agents and multi-agent systems, with significant applications in the areas of Game AI, and in Smart Cities and urban simulation.

Last but not least, Vincent Corruble has developed a major interest for AI safety, and more specifically on how agents and humans can develop safe cooperation and trust over time, and on the following critical issue: 'what do we gain and lose as individuals and as a society when we rely increasingly on machines to make mundane or critical decisions'. In this context, he visited the Center for Human-compatible AI at UC Berkeley in 2019, and has been a Research Affiliate with this center since.