Find Academic Supervisors

Dr. Francesco Belardinelli is a Senior Lecturer at the Department of Computing, Imperial College London, and co-director of the UKRI CDT in Safe and Trusted AI. His research focuses on Safe AI through formal methods, emphasizing strategic reasoning in multi-agent systems and reinforcement learning safety. He leads the EPSRC-funded project on abstraction-based techniques for safe RL. PhD from Scuola Normale Superiore (2005-2009) under the IEFP Marie Curie Fellowship. Co-directs the Safe and Trusted AI CDT, organizing summer schools and workshops. Developed abstraction frameworks for verifying strategic properties in systems with imperfect information. Research Interests Pioneering work in formal verification of multi-agent systems, including: Safe RL via abstraction techniques Epistemic and strategic logics Verification of artifact-centric systems Active in outreach, organizing FMAI seminars and international conferences (e.g., AAMAS, IJCAI).

• Safe Artificial Intelligence
• Formal Methods
• Reinforcement Learning
• +5 more

ZHANG Jiaheng is an Assistant Professor in the Department of Computer Science at the National University of Singapore (NUS), School of Computing. His work bridges cryptography, artificial intelligence, and system security, with a focus on scalable and privacy-preserving technologies. He teaches CS3235 – Computer Security and leads research in zero-knowledge proofs, LLM safety, and trustworthy AI. Research Interests: His research spans Cryptography , Security , Machine Learning & AI , Privacy , and Algorithms & Theory . He specializes in making zero-knowledge proofs practical at scale and securing large language models against jailbreaking, backdoors, and privacy leaks. His recent projects include zkGPT, BatchZK, and Guardreasoner, highlighting his dual focus on theoretical foundations and real-world applications. The recent publications show a strong trend toward scalable zero-knowledge systems and AI security , particularly in verifying and protecting LLMs. These works integrate cryptographic rigor with modern AI challenges, reflecting a cohesive research vision at the frontier of trustworthy computing. Scientific Contributions: Developed scalable collaborative zk-SNARKs for efficient proof generation. Pioneered techniques for secure LLM inference and jailbreak detection. Advanced GPU-accelerated and distributed zero-knowledge proof systems. Advising & Grants: While specific students and grants are not listed, his active publication record in top-tier venues suggests ongoing research supervision and external funding in cybersecurity and AI. He is likely involved in advising PhD and Master’s students in cryptography and AI security. Labs & Teams: He is part of the NUS School of Computing research ecosystem, potentially affiliated with cybersecurity or AI labs, contributing to Singapore’s leadership in privacy-preserving technologies.

• Cryptography
• Security
• Artificial Intelligence
• +7 more

Wei GAO is an Associate Professor of Computer Science at Singapore Management University's School of Computing and Information Systems (SCIS), where he serves as full-time faculty. His research focuses on artificial intelligence applications in social computing, misinformation analysis, and natural language processing. Professor GAO leads research on large language models, rumor detection, and social media analytics through computational approaches. Research Focus Professor GAO's expertise spans several interconnected domains: AI & Data Science : Developing advanced machine learning models for complex data analysis Social Media Analytics : Studying misinformation propagation and user behavior patterns Natural Language Processing : Creating novel methods for text understanding and generation Computational Social Science : Quantifying psychological and social phenomena through AI Publication Trends Recent works demonstrate strong emphasis on enhancing large language models for: misinformation detection (rumor verification, fake news debunking), social computing (stance classification, moral reasoning), and efficient AI (model compression, transfer learning). Multimodal approaches and explainable AI frameworks appear consistently across publications. Academic Activities Professor GAO supervises PhD students including LAI Yibin, with mentorship focus on NLP and social computing research. He teaches courses on Natural Language Communication and contributes to SMU's research initiatives in digital transformation and AI safety.

• Artificial Intelligence and Data Science
• Data Management & Mining
• Decision Making & Optimization
• +5 more