James Zheng // #SISeminarSeries​​ // May 13, 2026

From Foundation Models to Neuro-Symbolic Architectures: Toward Safety Assurance of Learning-Enabled CPS ABSTRACT—Learning-enabled cyber-physical systems (CPS), such as autonomous driving and UAVs, are increasingly deployed in safety-critical settings, yet their reliance on foundation models poses challenges for testing and assurance. This seminar presents recent advances in using foundation models and LLMs for safety testing, including specification mining from rules and accident data, and automated scenario generation for conformance testing. It then highlights a transition toward neuro-symbolic architectures via NeuroStrata, integrating neural perception with symbolic reasoning for interpretable, verifiable assurance. A UAV landing-site case study demonstrates symbolic world models, differential rule engines, and human-in-the-loop validation. Insights from Shonan Seminar 235 outline a roadmap for trustworthy CPS. BIO—Prof. Xi Zheng is an ARC (Australian Research Council) Future Fellow at Macquarie University. His research focuses on trustworthy AI and neuro-symbolic systems for safety assurance of learning-enabled cyber-physical systems. He has secured over $2.4M in competitive funding, including the ARC Future Fellowship (2024), the only award in Software Engineering in Australia that year. He plays an active international leadership role as Founding Director of the Australian Institute for Learning and Reasoning Systems (AILARS) and Co-Founder of the Trustworthy Autonomous Cyber-Physical Systems (TACPS) initiative, and has chaired major initiatives including Shonan, Dagstuhl, and the AAAI-26 Bridge Program. He is keen to build collaborations and contribute to research activities across academia and industry worldwide. ℹ️ https://si.usi.ch/seminars