Find Academic Supervisors

Anisa RulaView profile

Assistant Professor

• Data Management
• Knowledge Graphs
• Data Quality Assessment
• +4 more

Anisa Rula is an Assistant Professor in Computer Science at the Department of Information Engineering, University of Brescia since 2021. Previously, she was a researcher at the University of Bonn's SDA group (2017–2019). She holds a PhD in Computer Science from the University of Milano-Bicocca (2014). Her research focuses on data management and exploration, particularly in data quality assessment for Information Systems and Knowledge Graphs. Key interests include semantic data enrichment, large datasets, and knowledge extraction. Education: PhD in Computer Science, University of Milano-Bicocca (2014) Prior academic and research roles at University of Bonn (2017–2019) Research Interests: Data Quality Assessment for Knowledge Graphs and Information Systems Large-Scale Dataset Management & Exploration Procedural Knowledge Extraction from Text Ontology-Driven Semantic Enrichment Human-in-the-Loop Data Annotation Systems Publications reflect her expertise in Knowledge Graph lifecycle management, quality assessment tools like KGHeartBeat, and LLM applications for schema mining and data discovery. Her work emphasizes practical implementations such as MantisTable for semantic table interpretation and K-hub ontology for industrial knowledge extraction. Awards: None explicitly mentioned in text. Advising & Grants: No student advisees listed. Active in developing open-source tools and collaborative frameworks for data quality and semantic web applications. Labs/Teams: Involved in Knowledge Graph validation and quality initiatives, including contributions to the EU Business Graph platform and cross-institutional workshops on Linked Data Quality.

• Artificial Intelligence
• Multiagent Systems
• Social Computing
• +5 more

Munindar P. Singh is a Professor affiliated with North Carolina State University. His research focuses on multiagent systems, normative systems, cybersecurity, and ethical AI. He has contributed extensively to the development of protocols for decentralized systems, computational governance, and the application of AI in socially responsible contexts. Key Roles: Leading research in multiagent systems, norms, and sociotechnical systems. Affiliations: North Carolina State University. His work spans theoretical frameworks for agent collaboration, practical applications like microtransit optimization, and ethical considerations in AI. Recent studies include analyzing social media dynamics, deception strategies in cybersecurity, and moral reasoning in narratives. Publications reflect interdisciplinary impact across AI, computer science, and social computing. Notable areas include norm emergence, cyber deception via hypergame theory, and ethical frameworks for autonomous systems.

• Artificial Intelligence
• Business Process Management
• Machine Learning
• +3 more

Lior Limonad is a Researcher at IBM Research, Haifa, Israel, specializing in the intersection of artificial intelligence (AI), business process management (BPM), and ontology engineering. His work focuses on leveraging large language models (LLMs) for explainable business processes, causal reasoning in AI systems, and enhancing decision-support mechanisms through advanced analytics. Research Interests: AI-driven process optimization Explainability in machine learning Cybersecurity for IoT systems Ontology development for enterprise systems Human-AI collaboration in education and motor skill acquisition Publications highlight trends in applying LLMs to business processes, causal inference frameworks, and hybrid systems integration. Collaborations include institutions like the University of New Brunswick and industry partners like Siemens.

Debasmita LoharView profile

Research Fellow

• Program Analysis
• Approximate Computing
• Probabilistic Analysis
• +5 more

Debasmita Lohar is a Postdoctoral Researcher at Karlsruhe Institute of Technology (KIT), working with Bernhard Beckert in the Application-oriented Formal Verification group at KASTEL — Institute of Information Security and Dependability. She is set to join the IT University of Copenhagen as an Assistant Professor starting December 2024. Her educational background includes: PhD from Saarland University in collaboration with the Max Planck Institute for Software Systems (MPI-SWS), Saarbrücken, advised by Eva Darulova Graduate studies at the Indian Institute of Technology (IIT) Kharagpur, advised by Soumyajit Dey Dr. Lohar's research focuses on the intersection of program analysis, approximate computing, and probabilistic analysis, with applications spanning embedded systems, scientific computing, and machine learning. Her work addresses critical challenges in numerical error analysis, particularly in the context of finite-precision arithmetic and its implications for system reliability and safety. She has made significant contributions to sound static program analysis techniques for neural networks and cyber-physical systems, developing novel approaches for mixed-precision tuning and quantization that balance computational efficiency with numerical accuracy guarantees. Her recent publications demonstrate a strong trajectory in formal methods for numerical programs, with increasing focus on neural networks and cyber-physical systems. The research shows a clear progression from fundamental numerical error analysis to practical applications in machine learning systems, reflecting the growing importance of formal verification in AI safety-critical domains. Her scientific recognition includes: Selected to participate in the 10th Heidelberg Laureate Forum, 2023 Best Presentation Award (iFM PhD Symposium), 2019 Dr. Lohar has extensive teaching experience across multiple institutions, having taught courses on Floating-Point Analysis, LLMs in Formal Verification, Neural Networks in Formal Verification at KIT, Advanced Program Analysis and Program Analysis at Saarland University, and Fault Tolerant Systems, Theory of Computation, and Computer Organization and Architecture Lab at IIT Kharagpur. Her research is supported through her position at KASTEL and likely through competitive research grants given her publication record in top-tier venues. She leads research in the Application-oriented Formal Verification group at KASTEL, collaborating with researchers like Bernhard Beckert, Eva Darulova, and others. Her work on the Aster project demonstrates her leadership in developing practical tools for sound mixed fixed-point quantization of neural networks.

Khaled Ali SlhoubView profile

Associate Professor

• Software Engineering
• Software Testing
• Software Measurements
• +4 more

Khaled Ali Slhoub is an Associate Professor and Program Chair of Computer Information Systems & Human-Centered Design at the Department of Electrical Engineering and Computer Science , College of Engineering and Science, Florida Institute of Technology. He contributes to academia through research in software engineering and agent-based systems. Ph.D. in Computer Science from Florida Tech M.Sc. from University of New Brunswick (Canada) B.Sc. from Benghazi University (Libya) His research focuses on software requirements, testing, quality assurance , and multi-agent systems . Current projects include developing frameworks for: Unified agent-oriented development methodologies Quality analysis of industrial agent-oriented methodologies Detecting disruptive behavior in distributed social agents (bots) Testing approaches for autonomous systems

• Graphics and visualization
• Measuring technique
• Computer graphics
• +5 more

Samir Lemeš serves as Dean of the Polytechnic Faculty at the University of Zenica (2022-2026), where he was elected as full professor in both Graphics and Visualization (November 2023) and Measuring Techniques (May 2022). Previously, he held significant leadership roles including Head of the Department of Software Engineering (2020-2023), Vice-Dean for Scientific Research (2015-2022), and Head of the Department of Civil Engineering and Building Structures (2015-2019). His research spans graphics and visualization, measuring techniques, computer graphics, CAD applications, digital image processing, and environmental monitoring systems. His work bridges theoretical computer science with practical engineering applications, particularly in Industry 4.0 contexts where he explores AI image generators, blockchain technologies, and IoT-enabled embedded systems. His research demonstrates a consistent focus on applying computational methods to solve engineering and environmental challenges. Analysis of his recent publications (2023-2025) reveals a strong emphasis on Industry 4.0 technologies, with significant contributions in computer vision applications, AI prompt engineering, digital image processing using OpenCV, and blockchain implementations. His work shows increasing interdisciplinary collaboration, particularly between computer science, environmental science, and industrial engineering. Professor Lemeš has been instrumental in several international environmental projects including the Network of Aarhus Centers for the Green Agenda and Environmental Protection (2024-2026), Reindustrialisation Following the Brownfield is Better than Greenfield Principle (2024-2026), and the Healthy Urban Environment Erasmus+ project (2018-2021). His grant portfolio demonstrates consistent funding from EU programs, UNESCO, OSCE, and international environmental organizations. He teaches across multiple engineering disciplines including Introduction to Information Technology, Computer Graphics, CAD in Construction, and Standardization, serving both undergraduate and doctoral students at the Polytechnic Faculty. His courses bridge theoretical computer science with practical engineering applications, particularly in the context of Industry 4.0 technologies.

Alin StefanescuView profile

Professor

• Software Engineering
• Cybersecurity
• Artificial Intelligence
• +3 more

Alin Stefanescu is a Professor and Head of the Computer Science Department at the University of Bucharest , Romania. He is also a founding member of the Institute for Logic and Data Science (ILDS) . His research focuses on software engineering, cybersecurity, and artificial intelligence, with contributions to formal methods, model-based testing, and distributed systems. Education: PhD (2006) in Computer Science, University of Stuttgart Habilitation Thesis (2017) in Formal Methods for Software Testing, University of Bucharest MSc (2000), BSc (1998) in Computer Science, University of Bucharest Research Interests: Formal verification of distributed systems Model-based testing and software quality assurance AI-driven tools for cybersecurity and testing (e.g., RobustCheck, CyberGuardian) Blockchain applications in AI and identity management Reinforcement learning for fuzz testing and automation Recent Trends in Publications: Recent work emphasizes AI integration in testing frameworks, blockchain for secure AI systems, and adaptive cybersecurity tools. He has pioneered open-source tools like RiverFuzzRL and EBLT, addressing challenges in automated testing and vulnerability analysis. Awards: Best Paper Award at ICSOFT'23 (2023) 10-Year Most Influential Paper Award (2023, for 2013 work) Best Student Paper Award (2010) Grants & Labs: Active in EU-funded projects like DYNABIC (AI techniques) and MEASURE (metrics modeling). Leads the ILDS institute, focusing on logic and data science research.

Sebastian SchusterView profile

Lecturer

• Computational Linguistics
• Natural Language Processing (NLP)
• Large Language Models Evaluation
• +5 more

Sebastian Schuster is a Lecturer in Computational Linguistics at University College London (UCL), effective January 2024. He will transition to the University of Vienna in mid-2025 to lead a WWTF-funded research group. Previously, he held postdoctoral positions at Saarland University and NYU (via the 2020 Computing Innovation Fellowship), and completed his PhD in Linguistics at Stanford University, affiliated with the ALPS Lab and Stanford NLP Group. His research focuses on evaluating large language models (LLMs), computational semantics, and pragmatics. Key themes include improving NLU systems through entity tracking analysis, understanding scope ambiguities, and modeling pragmatic inferences. Recent work explores how pretraining affects LLM capabilities and how context influences scalar implicature processing. Notable contributions include datasets like SIGA for scalar implicatures and SpreadNaLa for code generation evaluation. He has presented at ETH Zurich, Oxford, and served as Area Chair for *SEM2023's psycholinguistics track. His fellowship and invited talks reflect recognition of his interdisciplinary work bridging computational and experimental linguistics. Professional activities include contributions to Universal Dependencies projects, software tools like Open Linguistics, and collaborations on child language development. His work integrates methodologies from NLP, experimental psychology, and cognitive science to advance both theoretical and applied linguistic research.

Ying ZouView profile

Professor

• Software Engineering
• Software Maintenance and Evolution
• Empirical Studies
• +7 more

Dr. Ying Zou is a Professor and Canada Research Chair (Tier II) in Software Evolution at Queen’s University’s Department of Electrical and Computer Engineering, with a cross-appointment to the School of Computing. She is a Visiting Faculty Fellow at IBM Centers for Advanced Studies (CAS) and a member of IEEE. Her research focuses on software engineering, maintenance, empirical studies, and service-oriented computing, with notable contributions to refactoring patterns, performance analysis, and developer tooling. Education: BEng from Beijing Polytechnic University (China), MEng from Chinese Academy of Space Technology (China), and PhD from the University of Waterloo (Canada). Research interests include software evolution dynamics, code clone analysis, and optimizing developer workflows. Notable achievements include the 2014 IBM CAS Research Faculty Fellow of the Year and two IBM Faculty Awards (2007, 2008). Her work bridges empirical software engineering with practical industrial applications. Awards: Canada Research Chair, IBM Faculty Awards, IBM CAS Fellow Grants: IBM CAS collaborations, cross-disciplinary research funding Labs/Teams: Active contributor to the Software Evolution and Analysis Lab (SEAL), focusing on empirical studies and tool development for software maintenance challenges.

Yutian TangView profile

Assistant Professor

• AI+SE (Large-language Model+SE)
• Program Analysis
• Empirical Software Engineering
• +4 more

Dr. Yutian Tang is an Assistant Professor at the University of Glasgow's School of Computing Science. He holds a Ph.D. from The Hong Kong Polytechnic University and a B.Sc. from Jilin University. His research focuses on AI-driven software engineering, program analysis, and mobile app security, with over 40 publications in top venues like ESEC/FSE and IEEE TSE. He has received awards including the ISSRE'18 Best Industry Paper and Shanghai Pujiang Talent Program. Current research emphasizes automated testing, bug localization, and LLM applications in software engineering. Education: Ph.D., Department of Computing, The Hong Kong Polytechnic University B.Sc., Computer Science, Jilin University Research Interests: His work spans AI+SE (Large Language Models in Software Engineering), automated testing, privacy protection, and malware detection. Notable contributions include XDebloat (app debloating) and tools for analyzing Android vulnerabilities. He actively explores LLM applications for code generation and test suite optimization. Grants & Funding: EPSRC Peer Review College member National Natural Science Foundation of China (NSFC) grant (2023-2025) OpenAI API Researcher Access Program (2024) Google Cloud Research Credits (2024) Service & Leadership: Editorial Board Member of Frontiers in Computer Science , PC member of ICSE, ESEC/FSE, ASE, and other top conferences. Active in reviewing for IEEE Transactions and ACM journals. Future Directions: Tool support for automated bug detection, LLM integration in software lifecycle, and large-scale binary code analysis.

Jake RenzellaView profile

Senior Lecturer

• Computer Science Education
• Educational Technology
• Learning Analytics
• +3 more

Dr Jake Renzella is a Senior Lecturer at the University of New South Wales' School of Computer Science and Engineering (CSE), where he serves as Co-Head of the Computing and Education research group and Director of Studies for Computer Science. His work focuses on Pedagogical Generative AI and education technology, with a particular emphasis on compiler tools like the Debugging C Compiler (DCC) and its AI debugger, as well as the Formatif teaching platform. Research: Premier computer science education conferences (SIGCSE TS, ICSE), AI-driven educational tools, learning analytics Collaboration: Key role in Day of AI Australia initiative Scientific Awards: 2024 Australian Financial Review Higher Education Innovation Award 2023 UNSW Engineering Faculty Education Award 2022 UNSW Teaching Excellence Award Associate Fellow of the Higher Education Academy Grants: $2,165,000 total including Google.org Generative AI Accelerator ($1.5M), NVIDIA Academic Grant (cloud GPU hours), and multiple Google/UNSW grants for inclusion research and teaching innovation.

Jim BuckleyView profile

Professor

• Software Engineering
• Software Evolution
• Artificial Intelligence for Software Engineering
• +5 more

Jim Buckley is a Professor in the Computer Science and Information Systems Department at the University of Limerick, Ireland, and a Principal Investigator in Lero. He leads the ARC research group focused on software evolution and legacy system modernization, with significant industry collaborations including Huawei, IBM, and Fidelity. Education: BSc in Biochemistry, University of Galway (1989) MSc in Computer Science, University of Limerick (1994) PhD in Computer Science, University of Limerick (2002) Research Focus: His work centers on AI-enhanced software engineering (AI4SE/SE4AI), featuring breakthroughs in clone detection, software architecture evaluation, and feature location. He has developed industry-adopted tools for software comprehension and evolution, with recent emphasis on explainable AI (XAI) and scalable neural network applications for industrial codebases. His research consistently bridges academic rigor with industrial implementation. Publication Trends: Recent articles (2022-2025) reveal a dominant shift toward AI-driven software engineering solutions, particularly in clone detection and architecture recovery. Key themes include industrial scalability, developer experience optimization, and responsible AI integration, with strong representation in top-tier venues like IEEE Transactions and ACM Computing Surveys. Scientific Awards: No awards specified in source material. Grants & Industry Impact: Leads the Huawei-funded TREES Programme and maintains active partnerships with 9+ companies. His research has yielded licensed tools (e.g., for legacy system evolution), two IP assignments from LLM-based clone detection work, and practical frameworks adopted by seven Irish enterprises. Research Infrastructure: Directs the ARC group within Lero, which combines academic researchers and industry practitioners to address real-world software maintenance challenges through empirical studies and tool prototyping.

Dejan LavbičView profile

Associate Professor

• Intelligent agents
• Multi-agent systems
• Ontologies
• +7 more

Assoc. Prof. Dejan Lavbič is an Associate Professor at the University of Ljubljana, Faculty of Computer and Information Science with 15+ years of academic experience. His research focuses on intelligent agents, multi-agent systems, ontologies, and blockchain-based smart contracts , particularly in semantic web technologies, AI services ecosystems, and information quality assessment . Doctor of Philosophy in Computer Science, University of Ljubljana (2010) Bachelor of Science in Computer Systems and Informatics, University of Ljubljana (2004) His scientific contributions span semantic web frameworks, blockchain applications, and machine learning systems, with 20+ peer-reviewed publications. Recent works include: Smart contract classification with AI Cardano blockchain identity systems Information quality metrics with gamification Awards include Cambridge CAE certification and multiple industry certifications. He mentors students in decentralized applications, AI development, and smart city ecosystems , having guided 6+ diploma/master theses on topics like automated essay grading and air quality data collection.

Chao PengView profile

Part-Time Lecturer

• Software Testing
• Program Analysis
• Programming Languages
• +5 more

Chao Peng is a Principal Research Scientist at ByteDance where he leads the Trae Research team (ByteDance Software Engineering Lab), conducting cutting-edge research on AI agents for software engineering. He also serves as a Part-time Postgraduate Student Mentor at Fudan University's School of Computer Science, bridging industry research with academic mentorship. PhD in Informatics (2021), University of Edinburgh, UK MSc in High Performance Computing and Data Science (2017), University of Edinburgh, UK BEng in Computer Science and Technology (2016), Xuzhou University of Technology, China Dr. Peng's research focuses on the intersection of software testing, program analysis, and large language models. His work explores how AI agents can revolutionize software engineering practices, with particular emphasis on automated bug detection, code generation, and testing frameworks. He has pioneered approaches for evaluating LLM performance in software engineering contexts and developing agent-based systems that enhance developer productivity while maintaining code quality and security. His recent publications demonstrate a clear trend toward integrating large language models with traditional software engineering practices. The research spans code generation evaluation, security vulnerability detection, automated bug reproduction, and issue localization. These works collectively advance the field of AI-assisted software development by addressing practical challenges in reliability, security, and efficiency of AI-generated code. Distinguished Reviewer for FSE'25 School of Informatics Scholarship (fully-funded PhD scholarship) Outstanding Graduate Scholarship at Xuzhou University of Technology Multiple China National Scholarships Honours Spot Bonus at ByteDance Certificate of Achievement for HPCAC Student Cluster Competition Dr. Peng actively mentors students through his role at Fudan University and previously at the University of Edinburgh, where he served as sub-supervisor for MSc projects and teaching assistant for software testing courses. His research has attracted significant industry attention, leading to multiple collaborations between ByteDance and academic institutions. He frequently serves on program committees for major software engineering conferences including ASE, FSE, and ICSE, demonstrating his leadership in the field. As leader of the Trae Research team at ByteDance Software Engineering Lab, Dr. Peng oversees research on AI agents for software engineering, including the application and evaluation of AI agents and training LLMs for agent-based systems. The lab's work focuses on practical systems that predict, detect, diagnose, and fix bugs across various software systems, with particular emphasis on real-world applications and measurable impact on developer productivity.

Yasutaka KameiView profile

Professor

• Empirical Software Engineering
• Software Reliability
• Software Testing
• +8 more

Yasutaka Kamei is a Full Professor at Kyushu University's Graduate School and Faculty of Information Science and Electrical Engineering, where he leads the POSL Lab (Process-Oriented Software Laboratory). He was promoted from Associate Professor to Full Professor in January 2024 after serving as Associate Professor from March 2015 to December 2023. He is also an InaRIS Fellow (2023-2033), receiving 10 million yen annually for his research on 'New paradigm for software development styles based on machine-human interaction.' Dr. Kamei's research focuses on Empirical Software Engineering (ESE) and Open Source Software Engineering (OSSE), with particular expertise in software reliability, testing, defect prediction, code review analysis, and mining software repositories. His work bridges empirical methods with practical software engineering challenges, emphasizing how data-driven approaches can improve software quality assurance processes. His recent publications demonstrate a strong trend toward understanding human factors in software development processes, analyzing modern code review practices, investigating technical debt, and exploring the application of large language models in software engineering tasks. His research spans both traditional software engineering challenges and emerging AI-driven approaches to software development. IPSJ/ACM Award for Early Career Contribution to Global Research (2019) Best industry paper award at ESEM 2018 Distinguished Paper Award at MSR 2014 InaRIS Fellow (2023-2033) Dr. Kamei actively serves the software engineering community as Tutorials Chair for ASE 2025 and has been a program committee member for numerous top-tier conferences including ICSE, FSE, ASE, ESEC/FSE, SANER, and MSR. He has secured multiple competitive grants from MEXT (Ministry of Education, Culture, Sports, Science and Technology) to support his research on test case generation, automated software testing for deep learning systems, technical debt engineering, and mining software repositories. His POSL Lab at Kyushu University serves as a hub for empirical software engineering research, focusing on data-driven approaches to improve software development processes and outcomes through rigorous analysis of software repositories and developer activities.