I am an Assistant Professor of Computer Science at the University of Birmingham. My research interests lie between formal methods and artificial intelligence. I develop automatic techniques to guarantee that algorithmic systems are safe and trustworthy by combining ideas from machine learning and automated reasoning. Here's my CV and here's a picture of me.
Students interested in pursuing a PhD at the University of Birmingham in formal methods and artificial intelligence are invited to get in touch.
Contact
School of Computer Science, University of Birmingham
Edgbaston, Birmingham, B15 2TT, UK
m.giacobbe@bham.ac.uk
Selected Publications
Formal Methods for Safe Artificial Intelligence
Verifying Reinforcement Learning up to Infinity. Edoardo Bacci, Mirco Giacobbe, David Parker. IJCAI, 2021. [paper]
How Many Bits Does it Take to Quantize Your Neural Network? Mirco Giacobbe, Thomas A. Henzinger, and Mathias Lechner. TACAS, 2020. [paper]
Neuro-symbolic Methods for Formal Verification
Formal Synthesis of Lyapunov Neural Networks. Alessandro Abate, Daniele Ahmed, Mirco Giacobbe, and Andrea Peruffo. IEEE L-CSS, 2021. [paper]
Learning Probabilistic Termination Proofs. Alessandro Abate, Mirco Giacobbe, and Diptarko Roy. CAV, 2021 [paper]
Neural Termination Analysis. Mirco Giacobbe, Daniel Kroening, and Julian Parsert. ESEC/FSE, 2022 [paper]
Formal Verification of Cyber-physical Systems
Continuous-Time Models for System Design and Analysis. Rajeev Alur, Mirco Giacobbe, Thomas A. Henzinger, Kim G. Larsen, Marius Mikucionis. Computing and Software Science, 2019. [paper]
Counterexample-guided Refinement of Template Polyhedra. Sergiy Bogomolov, Goran Frehse, Mirco Giacobbe, and Thomas A. Henzinger. TACAS, 2017. [paper] [tech. details]
Systems Biology
Model checking Gene Regulatory Networks (best paper award). Mirco Giacobbe, Ashutosh Gupta, Calin Č. Guet, Thomas A. Henzinger, Tiago Paixão, and Tatjana Petrov. TACAS, 2015. [artifact] [paper] [extended paper]