I am Professor of Computer Science in the Department of Computer Science at University College London (UCL), where I also serve as Director of the UCL Centre for Artificial Intelligence. I lead the Machine Intelligence Lab. I also hold a Professorship in Computer Science in the Department of Computer Science and Engineering at the University of Bologna.
PhD Studentship Opportunities
I am offering PhD projects as part of the EPSRC Centre for Doctoral Training in Cyber-Physical Risk. If you are interested, please check the webpage and feel free to contact me if you would like to discuss the opportunities and the application process. Please note that these studentships are available only to UK home students. Eligibility criteria can be found here.
Recent News
-
October 2026 Elected as an ELLIS Fellow.
-
September 2026 New preprint: “Framing the Narrative: Ideological Mimicry in Large Language Models”. You can download the paper here.
-
September 2026 New preprint: “ContextAdapt: Evaluating Contextual Adaptation and Value Alignment in LLMs”. You can download the paper here.
-
September 2026 Our paper “Emergent Semantic Role Understanding in Language Models” has been accepted at NeurIPS’26. The camera ready version of the paper will appear soon. In the meantime, you can download the preprint here.
-
August 2026 New preprint: “The Relationship Between Professional and General Ethics in Generative AI”. You can download the paper here.
-
August 2026 New preprint: “The Role of Network Topology and Opponent Information in Shaping Cooperation in Multi-Agent Reinforcement Learning Systems”. You can download the paper here.
-
August 2026 New preprint: “The Limits of Automatic Evaluation of Creativity in Large Language Models”. You can download the paper here.
-
June 2026 Our paper “TERC: A Transfer Entropy Redundancy Criterion for State Variable Selection in Reinforcement Learning” has been accepted in Transactions on Machine Learning Research. You can download the paper here.
Previous news items can be found here.
Research Interests
Current areas of interest include:
- Theory and applications of machine learning;
- Multi-agent systems based on foundational models/large language models and/or reinforcement learning;
- AI-based decision-making (in single-agent and multi-agent scenarios);
- AI security;
- AI safety;
- AI creativity;
- AI and society;
- Machine learning for mobile, IoT, networked, and cyber-physical systems.
More information about my research activities can be found here. You can also check the research philosophy of my lab here.
Last updated: 11 October 2026.