Organizers and advisory board.
Lead Research Scientist at Poseidon Research, working on defences against steganographic communication in language models. PhD in Computer Science (UBA). Two terms at MATS, where he co-led research showing that frontier LLMs produce unfaithful Chain-of-Thought reasoning (140+ citations). Previously worked on InterpBench.
Postdoctoral Research Associate at the University of Oxford with the OXCAV group. PhD in Computer Science (UBA), specializing in formal methods for the analysis of distributed systems. Former PIBBSS Fellow, exploring the intersection of formal methods and machine learning for verifiably safe AI.
Editor in Chief, IEEE Transactions on Software Engineering. Professor at the University of Buenos Aires. PhD at Imperial College London. General Chair for the 38th International Conference of Software Engineering (ICSE).
Researcher at the Computer Science Institute (ICC), CONICET-UBA. PhD at Stanford. Board Member of the International Speech Communication Association (ISCA).
Co-Director of MATS, Co-Founder and Board Member of LISA, Manifund Regrantor, and advisor to AI Safety ANZ, Catalyze Impact, and Pivotal Research. PhD in Physics at the University of Queensland.
Senior Science Associate at Schmidt Sciences. Previously Research Director of the London Initiative for Safe AI (LISA). Computer Science PhD on technical AI safety at the University of Oxford.
Programme Director for the Safeguarded AI programme at ARIA (UK Advanced Research & Innovation Agency). Before ARIA, she co-founded and led PIBBSS, a research initiative exploring interdisciplinary approaches to AI risk, governance and safety.