Formal Methods in AI Rigorous foundations for trustworthy intelligent systems

Group members

Current group members, alumni, and visitors working on formal methods, logic, and machine learning for safe intelligent systems.

Current members

Photo of Francesco Belardinelli
Dr. Francesco Belardinelli
Senior Lecturer, Principal Investigator
Head of Lab and Deputy Director of UKRI CDT in Safe and Trusted AI.
Photo of Omar Adalat
Omar Adalat
PhD Student
Verifiable and safe multi-agent reinforcement learning (2025-).
Photo of Farbod Faraji
Dr. Farbod Faraji
Eric and Wendy Schmidt AI in Science Research Fellow
Project: Development and Application of Neuro-Symbolic AI to Fusion Plasma Science
Photo of Maksim Anisimov
Maksim Anisimov
PhD Student
Provably mitigating catastrophic forgetting in continual reinforcement learning (2023-).
Photo of Alex Goodall
Alex Goodall
PhD Student
Robust world-model learning and shielding for reinforcement learning (2022-).
Photo of Titus Buckworth
Titus Buckworth
PhD Student
Neuro-symbolic methods for AI (2022-).
Photo of Ashutosh Agrahari
Ashutosh Agrahari
MRes in AI/ML (2026-)
Project in Safe RL.

Visitors

Photo of Edwin Hamel De Le Court
Dr. Edwin Hamel-de le Court
Postdoctoral Research Associate
Project: Abstraction-based technique for safe reinforcement learning (EPSRC NIA, 2023-25).
Photo of Matteo Leonesi
Matteo Leonesi
PhD Internship
September 2026 – March 2027
Photo of Giorge Ribic
Giorge Ribic
Undergrad Internship
September 2026 - December 2026

Past members

PhD

Photo of Matt Macdermott
Matt MacDermott
PhD Student
Model checking agents that learn (2021-2026).
Photo of Francis Ward
Francis Rhys Ward
PhD Graduate (2020-2025)
Formalising and Evaluating Deception in AI Agents.
Photo of Borja Gonzalez Leon
Borja Gonzalez Leon
PhD Graduate (2019-24)
Systematic grounded language learning in safety-aware autonomous agents.
Photo of Aamal Hussain
Aamal Hussain
PhD Graduate (2019-24)
Asymptotic convergence and performance of multi-agent Q-learning dynamics.

MRes/MPhil

Photo of Luka Corliss
Luka Corliss
MRes in AI (2023-24)
Neuro-symbolic policy learning and representation for interpretable, verifiable reinforcement learning.
Photo of Daniel Donnelly
Daniel Donnelly
MRes in AI (2023-24)
Runtime verification for safe and verifiable AI.
Photo of Nikolay Topol
Nikolay Topol
MRes in AI (2022-23)
Explainable reinforcement learning with causality.

Visitors

Photo of Terrence Fernandes
Terrence Fernandes
Internship
Masters' Internship (Feb 2026 - June 2026)
© 2025-2026 Formal Methods in AI