The team behind AISAR
Organizers
Iván Arcuschin
Lead Research Scientist at Poseidon Research, working on defences against steganographic communication in language models. He holds a PhD in Computer Science from the University of Buenos Aires. He completed two terms at MATS, the leading AI Safety research fellowship, where he co-led research showing that frontier LLMs produce unfaithful Chain-of-Thought reasoning (140+ citations). Previously he worked on InterpBench, a benchmark for evaluating interpretability methods.
Agustín Martinez Suñé
Postdoctoral Research Associate at the University of Oxford, working with the OXCAV group. He holds a PhD in Computer Science from the University of Buenos Aires, where he specialized in formal methods for the analysis of distributed systems. He is a former PIBBSS Fellow, where he began exploring the intersection of formal methods and machine learning to advance the development of verifiably safe AI systems.
Advisory Board
Sebastían Uchitel
Editor in Chief, IEEE Transactions on Software Engineering. Professor @ University of Buenos Aires. PhD @ Imperial College London. General Chair for the 38th International Conference of Software Engineering (ICSE).
Luciana Ferrer
Researcher @ Computer Science Institute (ICC), CONICET-UBA. PhD @ Stanford. Board Member of the International Speech Communication Association (ISCA).
Ryan Kidd
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 @ University of Queensland.
James Fox
Senior Science Associate @ Schmidt Sciences. Previously Research Director of the London Initiative for Safe AI (LISA). Computer Science PhD on technical AI safety @ University of Oxford.
Nora Anmman
Technical Specialist for the Safeguarded AI programme at the UK's Advanced Research & Innovation Agency. Before ARIA, she co-founded and led PIBBSS, a research initiative exploring interdisciplinary approaches to AI risk, governance and safety.