About me

This is Xiyue Zhang’s homepage! I am a Research Associate, working in the QAVAS group of Prof. Marta Kwiatkowska, in the Department of Computer Science, University of Oxford (August 2022-). I obtained my Ph.D. degree in June 2022 advised by Prof. Meng Sun, and I obtained my B.Sc. degree in June 2017 from Peking University. My current research mainly focuses on trustworthy deep learning, formal modeling and verification.


  • [August 2023 - Paper]: Our paper “Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Tasks” is accpeted by Journal of Logical and Algebraic Methods in Programming.
  • [August 2023 - Paper]: Our paper “When to Trust AI: Advances and Challenges for Certification of Neural Networks” is accepted by FedCSIS 2023.
  • [August 2023 - Event]: I am selected as Future Digileader ‘23 by Digital Futures. (Future Digileaders is a yearly event to offer professional development and provide opportunities to meet inspiring role models and network for early career researchers.)
  • [April 2023 - Paper]: Our paper “Using Z3 for Formal Modeling and Verification of FNN Global Robustness” is accpeted by SEKE 2023.
  • [December 2022 - Paper]: Our paper “kProp: Multi-Neuron Relaxation Method for Neural Network Robustness Verification” is accpeted by FSEN 2023.
  • [October 2022 - News]: I will serve on the Program Committee of TASE’23, to be held in Bristol, UK, on 04-06 July 2023. Welcome submissions!
  • [September 2022 - Event]: I give a talk at the ICTAC 2022 conference speaking on A Unifying Logical Framework for Neural Networks.
  • [August 2022 - Paper]: Our paper “Towards a Unifying Logical Framework for Neural Networks” is accepted by ICTAC 2022.
  • [June 2022 - Paper]: Our paper “Extracting Weighted Finite Automata from Recurrent Neural Networks for Natural Languages” is accpeted by ICFEM 2022.