Zhenya Zhang
Scholar

Zhenya Zhang

Google Scholar ID: 4CtRW_MAAAAJ
Kyushu University
Formal methodsHybrid systemsTemporal logicNeural network verification
Citations & Impact
All-time
Citations
959
 
H-index
18
 
i10-index
27
 
Publications
20
 
Co-authors
18
list available
Resume (English only)
Academic Achievements
  • RTSS'25b: 'Control Synthesis of Cyber-Physical Systems for Real-Time Specifications through Causation-Guided Reinforcement Learning'
  • RTSS'25a: 'On Synthesis of Timed Regular Expressions'
  • TCAD'25: 'Automated Generation of Benchmarks for Falsification of STL Specifications'
  • DATE'25: 'Adaptive Branch-and-Bound Tree Exploration for Neural Network Verification'
  • TOSEM'25: 'SpectAcle: Fault Localisation of AI-Enabled CPS by Exploiting Sequences of DNN Controller Inferences'
  • ASE'24: 'LeGEND: A Top-Down Approach to Scenario Generation of Autonomous Driving Systems Assisted by Large Language Models'
Research Experience
  • 2022.07–present: Assistant Professor, Kyushu University, Japan
  • 2021.09–2022.06: Research Fellow, Nanyang Technological University, Singapore
  • 2020.10–2021.06: Research Fellow, Kyushu University, Japan
  • 2019.04–2020.09: JSPS Research Fellow DC2, Japan
  • 2017.10–2020.10: Research Assistant, ERATO MMSD Project, National Institute of Informatics, Japan
  • 2015.09–2017.07: Research Assistant, State Key Laboratory of Computer Sciences, Institute of Software, Chinese Academy of Sciences, China
  • 2019.09–2019.12: Intern, University of Waterloo, Canada; Host: Prof. Krzysztof Czarnecki
  • 2016.10–2016.11: Intern, Royal Holloway University of London, UK; Host: Prof. Zhaohui Luo
Background
  • Assistant Professor at the Intelligent Software Engineering Laboratory, Faculty of Information Science and Electrical Engineering, Kyushu University, Japan
  • Cross-appointed Project Researcher at the Research Center for Mathematical Trust in Software and Systems, National Institute of Informatics, Japan
  • Research interests center on quality assurance of safety-critical complex systems using formal methods
  • Core problem: given a system model M and a specification φ, verify whether M ⊨ φ or M ⊭ φ
  • System models include classical software, hybrid systems (Cyber-Physical Systems), and AI-based systems such as autonomous driving systems
  • Specifications are formally expressed using logical languages like temporal logic
  • Focuses on verification, testing, and monitoring—bridging theoretical foundations with real-world applications