I am a researcher affiliated with the Centre for Explainable AI at Imperial College. My research largely focuses on safe & explainable AI, with special emphasis on contrastive explanations and their robustness. My work is currently supported by an Imperial College Research Fellowship.

Before, I was research associate in the Verification of Autonomous Systems group at Imperial College. I obtained a PhD in Computer Science from RWTH Aachen University and UNIGE with a thesis on AI Planning.

You might want to check out my CV to get a better picture of what I’ve done professionally so far.

News

  • I will give a(nother) invited talk on robustness of explanations at the IT University of Copenhagen in Feb next year. Details here. 2022. 12. 7.
  • Invited to give a talk on robustness of explanations at the University of Kent on Dec 5th. Get in touch if you're around! 2022. 11. 28.
  • Our paper "Formalising the Robustness of Counterfactual Explanations for Neural Networks" has been accepted at AAAI 23. Read pre-print here. 2022. 11. 19.
  • Visiting Einar Johnsen and his group at the University of Oslo Nov 23-25. Looking forward to interesting discussions on SMT, AI Planning and much more! 2022. 11. 14.
  • Invited to serve as a member of the PC for KR 2023. 2022. 11. 07.
  • Our new paper "Formalising the Robustness of Counterfactual Explanations for Neural Networks" is out on arxiv. Read the paper here. 2022. 09. 01.
  • Invited to serve as a member of the PC for AAAI 2023. 2022. 08. 08.
  • Invited to give a tutorial on Planning as SMT at the REMARO Fall School in Sep. Looking forward to catching up with old friends in Aachen! 2022. 07. 27.
  • I am co-organising the explAIn 2022 workshop at Imperial. The theme for this year is robustness in explainable AI. Want to know more? Click here. 2022. 07. 13.
  • Completed my training as a Mental Health First Aider with MHFA England. Incredible learning experience! 2022. 06. 30.
  • Our paper "Verification-friendly Networks: the Case for Parametric ReLUs" has been accepted at WFVML @ ICML 2022. 2022. 06. 20.
  • Fantastic news: I have been awarded an Imperial College Research Fellowship starting in 2022! 2021. 12. 15.
  • Our paper "Repairing Misclassifications in Neural Networks Using Limited Data" has been accepted at SAC 2022! Read the paper here. 2021. 12. 14.
  • Invited to serve as a member of the PC for KR 2022. 2021. 12. 07.
  • Joined the Centre for Explainable AI at Imperial! 2021. 11. 26.
  • Invited to give a talk on AI safety at the 1st International Workshop on Formal Methods for AI-Controlled Systems. Looking forward to attending my first in-person event in a long time! 2021. 09. 20.
  • Thrilled to serve as PC member for the Learning and Adaptation area at AAMAS 2022. 2021. 09. 18.
  • I will be serving as a member of the PC for AAAI 2022. 2021. 08. 11.
  • Paper accepted at FM 2021! Great collaboration with Boeing on verification of neural networks for safe avionics. Read the paper here. 2021. 07. 17.
  • Serving as a member of the PC for IJCAI-ECAI 2022. 2021. 07. 09.
  • Invited to serve as a member of the PC for KR 2021. 2021. 02. 01.
  • Joining the 2021 cohort of Techcelerate innovators. Thank you Imperial for the amazing opportunity. 2021. 01. 14.
  • I will be serving as a Senior PC member for IJCAI 2021. Can't wait to read your best submissions! 2020. 12. 10.
  • New paper out! The ARCH-COMP report on AI and Neural Network Control Systems is now available here - see post below for more details. 2020. 09. 27.
  • Invited to serve as a member of the PC for AAAI 2021! 2020. 09. 01.
  • Elena and I competed in the AI and Neural Network Control Systems track of the ARCH-COMP20. The track focuses on safety verification of closed-loop systems governed by neural controllers. Challenging problem with some really cool applications! Results out soon(ish), stay tuned. 2020. 07. 12.
  • Fantastic news! Our paper on "Optimal Planning Modulo Theories" has been accepted at IJCAI20. Read the paper here. 2020. 04. 20.
  • Coventry here I come. Invited to the Automata in the Wild workshop at the University of Warwick. Postponed due to the COVID19 pandemic. 2020. 02. 27.
  • Just came back from Italy, where I successfully defended my PhD! 2020. 01. 26.
  • New year, new paper: "Verification of Neural Networks: Enhancing Scalability through Pruning" accepted at ECAI20. Read the paper here. 2020. 01. 15.
  • Joined Imperial College London, exciting times ahead! 2019. 10. 27.
  • Great news: invited to speak at FMAIL in Bergen next Dec. 2019. 10. 03.
  • New website online. 2019. 09. 16.