Mario Giulianelli is an associate professor of computational linguistics at University College London and a member of the European Laboratory for Learning and Intelligent Systems. Working at the intersection of AI, linguistics, and cognitive science, he studies predictive processing in biological and artificial neural networks, particularly how it enables humans and machines to learn and use language. His research also examines higher-level cognitive functions in AI systems beyond language and advances the science of AI evaluation, with a focus on agency, safety, and interpretability. In 2018, he published a paper introducing the first causal interpretability method for neural language models. Before joining UCL, he completed his PhD at the University of Amsterdam’s Institute for Logic, Language and Computation, held a postdoctoral fellowship at ETH Zürich’s Institute for Machine Learning, and worked as a senior research scientist at the UK AI Security Institute.