Large Language Model Based Recommendation Professors and Supervisors

Jun Wangمشاهده پروفایل

استاد

University College LondonUnited Kingdom

Jun Wang is a Professor of Information and Data Science in the Department of Computer Science at University College London. He serves as the Founding Director of the MSc Web Science and Big Data Analytics program and is the Co-founder and Chief Scientist of MediaGamma Ltd (acquired), a UCL startup focused on AI for intelligent audience decision-making. His educational background includes: Doctor of Philosophy from Technische Universiteit Delft (2007) Master of Science from National University of Singapore (2003) Bachelor's degree from Southeast University Nanjing (1997) Professor Wang's primary research focuses on AI and intelligent systems, with particular expertise in multiagent reinforcement learning, deep generative models, and their applications across several domains. His work spans information retrieval, recommender systems and personalization, data mining, smart cities, bot planning, and computational advertising. His research has practical implications in healthcare, robotics, and intelligent systems for decision-making, aligning with Sustainable Development Goal 3 (Good Health and Well-Being). His recent publications demonstrate a strong trend toward integrating large language models with reinforcement learning techniques to create more efficient and capable systems. The research spans healthcare applications, robotics, information systems, and strategic decision-making, with an emphasis on privacy preservation, efficient computation, and multi-agent coordination. Professor Wang has received several prestigious awards: Beyond Search – Semantic Computing and Internet Economics award from Microsoft Research Yahoo! FREP Faculty award UCLB One-to-Watch award 2016 for MediaGamma First place in global real-time bidding algorithm contest (80+ participants worldwide) Multiple Best Paper awards With over 15 years of experience, Professor Wang has advised numerous startups including Last.Fm, Passiv Systems, Massive Analytic, Context Scout, and Polecat. He has also collaborated with major industry players such as BT, Microsoft, Yahoo!, Alibaba, and Didi. His knowledge transfer activities bridge academic research with practical industry applications. Professor Wang has developed the Information Retrieval and Data Mining MSc module and the MSc/MRes programme on Web Science and Big Data Analytics. He also teaches a multiagent AI MSc module, sharing his expertise in cutting-edge AI techniques with the next generation of computer scientists.

پروفایل رسمی دانشگاه

Keng-Chi Changمشاهده پروفایل

استادیار

Dartmouth CollegeUnited States

Keng-Chi Chang is an Assistant Professor in the Department of Quantitative Social Science at Dartmouth College. His research employs computational tools including AI and Large Language Models to investigate how technology and media shape political processes. Specific interests include censorship circumvention, online image-sharing behavior, and algorithmic recommendation systems for short-form video content. Education: • Ph.D. Political Science (Computational Social Science), University of California San Diego • M.S. Computer Science, University of California San Diego • B.A. Economics, National Taiwan University Research Focus: Chang explores the intersection of digital technology and political behavior, with emphasis on visual media analysis, censorship dynamics, and social media algorithms. His work examines how crises like COVID-19 trigger information-seeking behaviors and how platform features like live-stream chats influence political perceptions. Publications: Recent works demonstrate a strong focus on computational methods applied to political communication, including neural network interpretability, meme propagation patterns, and image-based credibility assessment. Publications span PNAS, Journal of Communication, and premier CS conferences. Funding & Awards: • NSF/APSA Dissertation Grant • Rapoport Family Foundation Research Grant

پروفایل رسمی دانشگاه

Xin Xiaمشاهده پروفایل

استاد

Max Planck Institute for Security and PrivacyGermany

Xin Xia is a Qiushi Distinguished Professor at the College of Computer Science and Technology, Zhejiang University. Previously, he served as the Chief Expert and Director of the Software Engineering Application Technology Lab at Huawei Technologies, China from 2021 to 2025. His academic career spans software engineering research with a focus on AI applications in the field. Ph.D. from Zhejiang University (2014) Supervised by Prof. Xiaohu Yang and Prof. Jianling Sun Visiting student at Singapore Management University (2012-2014) under Prof. David Lo Xin Xia's research primarily focuses on applying data science techniques to software engineering problems. His work spans AI for Software Engineering, Mining Software Repositories, Empirical Software Engineering, and Large Language Models for code understanding and generation. He employs data mining, information retrieval, natural language processing, search-based algorithms, and program analysis to transform software engineering data into automated tools and insights. His recent publications show a strong trend toward leveraging Large Language Models for various software engineering tasks, including code generation, vulnerability detection, and test generation. He has been exploring how to make these models more effective, reliable, and practical for real-world software development scenarios, with a particular focus on Java and Python ecosystems. ACM SIGSOFT Early Career Researcher Award (2022) ACM Distinguished Member 16 best or distinguished paper awards, including nine ACM SIGSOFT Distinguished Paper Awards Recipient of the IEEE Transactions on Software Engineering 2021 Best Paper Award Runner-Up Xin Xia has advised numerous students who have gone on to publish in top software engineering venues. His research has been supported by grants from both academic institutions and industry partners, particularly during his time at Huawei. He actively collaborates with researchers worldwide, especially with David Lo at Singapore Management University. At Zhejiang University, Professor Xia leads research in the intersection of AI and Software Engineering. His work has practical applications in improving developer productivity through automated tools that analyze software repositories and provide actionable insights.

پروفایل رسمی دانشگاه

Hui Liuمشاهده پروفایل

استاد

Max Planck Institute for Security and PrivacyGermany

Hui Liu is a Professor in the School of Computer Science and Technology at Beijing Institute of Technology, where he leads research in AI-based software development with a focus on LLM applications. His work spans software refactoring, quality improvement, and maintenance, funded by the National Natural Science Foundation of China and the National Key Research and Development Program of China. PhD from Peking University (2008) Former graduate student at Software Engineering Institute, Peking University Distinguished member of China Computer Federation Secretary-General of CCF Technical Committee on Software Engineering Professor Liu's research centers on LLM-based program generation, evaluation and testing of large language models, software refactoring techniques, and automatic construction of software engineering datasets. His work bridges artificial intelligence and software engineering, with particular emphasis on improving code quality through empirical studies and machine learning techniques. Current projects include code contamination detection, context-aware naming recommendations, and refactoring validation using LLMs. His research has evolved from traditional code smell detection to cutting-edge applications of large language models in software development. Liu's publication record shows a strong trend toward LLM applications in software engineering, with recent work focusing on code review generation, commit message generation, and refactoring validation using large language models. His research combines empirical methods with machine learning approaches, often analyzing large code corpora from open-source projects. The work spans both theoretical foundations and practical tool development, with several contributions merged into Eclipse as part of the open-source community. ACM Distinguished Paper Award (ESEC/FSE 2023) ACM Distinguished Paper Award (ICSE 2022) RE'2021 Best Research Paper Award IET Software Premium Award (2018) New Century Excellent Talents in University (2013) Beijing Higher Education Young Elite Teacher (2013) Professor Liu actively mentors PhD and Master's students, with recent graduates including Waseem Akram (awarded Outstanding Graduate) and several students publishing at top venues. His research is supported by major Chinese funding agencies, and he serves on program committees for leading software engineering conferences including ASE, ICSE, and FSE. He maintains strong industry connections through contributions to Eclipse and studies of open-source ecosystems like Rust. Liu leads a research group focused on AI for software engineering, with active projects on code generation, refactoring, and quality improvement. The group collaborates extensively with international researchers and contributes directly to open-source tools, particularly in the Eclipse ecosystem where multiple refactoring improvements have been merged.

پروفایل رسمی دانشگاه

Matthes Fleckمشاهده پروفایل

استاد

University of Applied Sciences and Arts LucerneSwitzerland

Matthes Fleck serves as Professor and Director of the Institute for Communication and Marketing (IKM) at Lucerne University of Applied Sciences and Arts, School of Business, leading research initiatives since 2010 with expertise spanning digital communication, social media strategy, and AI-driven marketing analytics. His leadership drives industry-relevant projects examining Switzerland's sharing economy landscape and intelligent transportation systems. Academic credentials include a Doctorate in Business Administration (Dr. oec.) from University of St. Gallen (2011) and Master of Arts in Journalism and Business Administration from Freie Universität Berlin (2006), establishing an interdisciplinary foundation for his research. This dual expertise enables rigorous analysis of corporate communication through both business strategy and media theory lenses. Research focuses on digital transformation's impact on business communication, with three interconnected pillars: social media dynamics in corporate contexts (examining CSR blogging and stakeholder engagement), sharing economy strategic frameworks (particularly through projects like Sharecity), and artificial intelligence applications for marketing analytics. Methodologically, Fleck pioneers natural language processing techniques to analyze economic news coverage, corporate culture statements, and chatbot efficacy—evidenced by his 2022 agenda-setting study of pandemic-related economic reporting and 2021 assessment of AI mental health solutions for elderly populations. Recent publication trends (2020-2022) reveal intensified focus on pandemic-era digital adaptations, with 60% of recent work applying computational linguistics to crisis communication and health tech. Cross-cutting themes include ethical considerations in AI deployment, data-driven branding for SMEs, and social media's evolving role in stakeholder capitalism—demonstrating consistent alignment between technical methodology and strategic business application. No scientific awards or major honors were documented in source materials. Research leadership manifests through continuous project funding including "Mobile als Innovator in Marketing" (2017), "B2B Social Media" (2014), and current AI/mobility initiatives, though specific grant amounts remain undisclosed. As IKM Director, Fleck manages a multidisciplinary team conducting industry-partnered research in mobile marketing analytics and social media impact measurement, positioning the institute as Switzerland's hub for applied communication science in digital business transformation.

پروفایل رسمی دانشگاه

Huaming Chenمشاهده پروفایل

مدرس ارشد

Max Planck Institute for Security and PrivacyGermany

Dr. Huaming Chen is a Senior Lecturer in the School of Electrical and Computer Engineering at The University of Sydney, Australia. His work focuses on trustworthy machine learning systems, software engineering, and software security. With numerous publications in top-tier conferences and journals, Dr. Chen has established himself as a significant contributor to the fields of AI security and software engineering. Dr. Chen's primary research interests lie at the intersection of software engineering and artificial intelligence, with a strong emphasis on trustworthy AI systems. His work spans several key areas including: Software Security for AI-enabled systems Trustworthy and Responsible AI development Computational biology applications Industrial 4.0 implementations Federated learning and privacy-preserving techniques Large language model verification and uncertainty analysis His research addresses critical challenges in ensuring AI systems are secure, reliable, and ethically sound. Dr. Chen's recent publications demonstrate a strong trend toward addressing security and trustworthiness challenges in AI systems. His work spans multiple domains including software security (particularly for AI systems), trustworthy AI development, and applications in computational biology. A significant portion of his recent work focuses on large language models, examining their vulnerabilities, verification methods, and uncertainty analysis. He also maintains active research in federated learning, adversarial machine learning, and software security techniques. Dr. Chen has received several notable awards and recognitions: 2020 IEEE CIS Student Grant for IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE (WCCI) 2017 Student and Early Career Travel Fellowship for The 16th International Conference on Bioinformatics (InCoB 2017) 2017 Student Travel Award for 2017 IEEE World Congress on Services Dr. Chen actively supervises multiple research students working on cutting-edge projects related to trustworthy AI and software security. His current students are exploring topics ranging from blockchain-based governance frameworks to open-source AI security and digital twin platforms. He also serves in numerous committee roles at top conferences including area chair for ACM MM, and PC member for ACM CCS, IJCAI, KDD, and many others. His service as a Guest Editor for journals like Computers & Security and as a Grant Reviewer for UKRI demonstrates his standing in the research community. Dr. Chen organizes workshops focused on Trustworthy and Responsible AI, reflecting his commitment to advancing the field. His research group appears to focus on practical applications of AI security techniques, with projects spanning multiple domains including healthcare, finance, and industrial systems. He maintains active collaborations with researchers across multiple institutions, as evidenced by his co-authorship on diverse publications.

پروفایل رسمی دانشگاه

Thomas Degueuleمشاهده پروفایل

پژوهشگر

Max Planck Institute for Security and PrivacyGermany

Thomas Degueule is a researcher at CNRS (Centre National de la Recherche Scientifique) in France, actively contributing to software engineering research since 2015. He serves on program committees for major conferences including ASE, ICSE, and SLE, with primary research interests in Software Evolution, Empirical Software Engineering, and Domain-Specific Languages. His work focuses on breaking change analysis in APIs and libraries, client-library compatibility testing, and dependency management. He develops practical tools like Roseau for source-based breaking change detection and investigates semantic versioning impacts in ecosystems like Maven Central. His empirical approach leverages large-scale repository analysis to address real-world software maintenance challenges, particularly in Java ecosystems. Recent publications (2023-2025) show consistent contributions to breaking change analysis and compatibility testing, appearing in top venues like ASE, ICSE, and ISSTA. His research bridges theoretical insights with practical tooling for software evolution challenges, demonstrating strong empirical methodology and tool-oriented contributions. No scientific awards are documented in the available information. Degueule has advised no publicly listed students and holds no mentioned research grants. His organizational roles include Program Co-Chair for SLE 2023 and committee positions across multiple conferences, reflecting significant service to the software engineering community.

پروفایل رسمی دانشگاه

Hongyu Zhangمشاهده پروفایل

استاد

Max Planck Institute for Security and PrivacyGermany

Hongyu Zhang is a Professor and Dean of the School of Big Data and Software Engineering at Chongqing University, China, and an Honorary Professor at The University of Newcastle, Australia. Previously, he served as a Lead Researcher at Microsoft Research Asia and an Associate Professor at Tsinghua University, China. He received his PhD from the National University of Singapore in 2003. His academic journey spans prestigious institutions, combining industry research experience with academic leadership. Dr. Zhang's research interests focus on intelligent software engineering, software analytics, data-driven software engineering, software fault management, testing and debugging, and software maintenance and reuse. His work centers on improving software quality and productivity by mining and analyzing vast amounts of software data. Over the years, he has developed innovative methods that apply data mining, machine learning (including deep learning), and information retrieval techniques to extract knowledge from software data and solve complex software engineering problems. His research spans three major areas: intelligent programming (code search, code summarization, code generation), intelligent quality prediction (defect prediction, cloud failure prediction, performance prediction), and intelligent fault detection and diagnosis (log-based fault detection, crash-based fault localization, bug report analytics). His recent publications demonstrate a clear trend toward integrating large language models and deep learning techniques with traditional software engineering practices. The research spans intelligent programming assistance, code security, UI automation, distributed systems optimization, and performance analysis. His work increasingly focuses on practical applications of AI in software engineering, with emphasis on real-world impact in industrial settings, particularly in microservices, cloud systems, and large-scale software development environments. 8 ACM Distinguished Paper Awards Best Paper Award: How Long Will it Take to Mitigate this Incident for Online Service Systems? David Lorge Parnis Fellowship Senior Member of IEEE Distinguished Member of ACM Distinguished Member of CCF Fellow of Engineers Australia (FIEAust) Recognized in The Australian's Top Researchers special edition as leading researcher in Software Systems World's Top 2% Scientists (career-long) Dr. Zhang has successfully advised numerous PhD and Master's students who have gone on to prominent positions at leading technology companies and academic institutions worldwide. His research has been supported by significant grants including Australian Research Council Discovery Projects (as Lead CI) and multiple National Science Foundation of China projects. His work has made tangible impacts in industry, most notably through the Microsoft Developer Assistant project which received over 450K downloads in 2016. He leads research groups focused on intelligent software engineering and software analytics, with strong collaborations between Chongqing University, The University of Newcastle, and Microsoft Research. His teams develop practical tools for code intelligence, log analysis, and fault diagnosis that are deployed in real-world online service systems.

پروفایل رسمی دانشگاه

Song Wangمشاهده پروفایل

دانشیار

Max Planck Institute for Security and PrivacyGermany

Song Wang is an Associate Professor in the Department of Electrical Engineering and Computer Science at York University's Lassonde School of Engineering since May 2024. Previously, he served as an Assistant Professor at the same institution from July 2019 to May 2024. He earned his Ph.D. in Computer Engineering from the University of Waterloo in December 2018 under Prof. Lin Tan, an MS degree from the Chinese Academy of Sciences in June 2014 under Profs. Ye Yang and Wen Zhang, and BE and BHRM degrees from Sichuan University in June 2011. Dr. Wang's research focuses on the intersection of Software Engineering and Artificial Intelligence, with two main thrusts: 1) leveraging AI technologies to address software reliability challenges (AI for SE), and 2) developing software reliability techniques to improve AI infrastructure systems (SE for AI). His specific interests include software testing, program analysis, software reliability, and machine learning applications in software engineering. His research has led to tools that have detected hundreds of true bugs across various open-source projects. His recent publications reveal a strong focus on applying large language models to software engineering tasks, analyzing vulnerabilities in deep learning libraries, and developing techniques for software testing and reliability. The research spans multiple subfields including API testing, vulnerability detection, bias analysis in generated code, and automated assurance case generation. TOSEM Distinguished Reviewer Award 2023 APSEC'23 Distinguished Paper Award ACM SIGSOFT Distinguished Paper Award (ICPC 2022) ACM SIGSOFT Distinguished Paper Award (ICSE 2020) Best Paper Award at PROMISE 2019 Dr. Wang actively mentors students at all levels, currently supervising multiple PhD and MASc students. His research group has produced numerous publications in top-tier software engineering venues, including ICSE, FSE, ASE, and TOSEM. He also serves on the editorial board of ACM TOSEM and has been involved in organizing major conferences like ASE and CASCON.

پروفایل رسمی دانشگاه

Kijung Shinمشاهده پروفایل

دانشیار

University of MadeiraPortugal

Kijung Shin is an Associate Professor at KAIST (Korea Advanced Institute of Science and Technology), holding dual appointments in the Kim Jaechul Graduate School of AI and the School of Electrical Engineering (Computer Division). He leads the Data Mining Lab and teaches multiple courses including Graph Mining and Social Network Analysis, Data Mining and Search, and other foundational courses in electrical engineering and AI. Education Ph.D. in Computer Science, Carnegie Mellon University (February 2019) M.S. in Computer Science, Carnegie Mellon University (December 2017) B.S. in Computer Science and Engineering, Seoul National University (August 2015) B.A. in Economics (Double Major), Seoul National University (August 2015) Research Interests Professor Shin's research primarily focuses on data mining, graph algorithms, and network science, with particular expertise in hypergraph analysis, tensor decomposition, and graph neural networks. His work bridges theoretical foundations with practical applications, developing algorithms that can efficiently analyze complex real-world networks. His recent research has expanded into multimodal learning, integration of large language models with graph neural networks, and applications in recommendation systems, satellite imagery analysis, and biological data analysis. His approach combines rigorous mathematical analysis with practical implementation, resulting in numerous open-source software tools that have been widely adopted in both academia and industry. His research has significant implications for social network analysis, fraud detection, recommendation systems, and scientific discovery in various domains. Research Trends Professor Shin's recent publications show a clear trajectory toward more complex network structures, particularly hypergraphs that capture higher-order interactions beyond simple pairwise relationships. His work increasingly integrates traditional graph algorithms with deep learning approaches, especially focusing on how graph neural networks can be improved and made more interpretable. There's also a growing emphasis on practical applications in areas like satellite imagery analysis, medical data, and recommendation systems that address real-world challenges. Scientific Awards Received the PAKDD Best Survey Paper Award for 'Multi-Behavior Recommender Systems: A Survey' (2025) Selected as one of the best short paper candidates of ACM RecSys 2024 (top 7) for 'Revisiting LightGCN' (2024) Selected for oral presentation (2.6% of accepted papers) at AAAI 2024 for 'VITA: 'Carefully Chosen and Weighted Less' Is Better in Medication Recommendation' (2024) Received the IEEE ICDM Best Student Paper Runner-up Award for 'TensorCodec: Compact Lossy Compression of Tensors without Strong Data Assumptions' (2023) Received the SIGKDD Best Research Paper Award and CogX Award for Best Student Paper in AI for 'FRAUDAR: Bounding Graph Fraud in the Face of Camouflage' (2016) Received the Best Senior Thesis Award from Seoul National University (2015) Received the Samsung Humantech Paper Award (1st in Computer Science) (2015) Teaching and Mentoring Professor Shin has taught multiple graduate and undergraduate courses at KAIST since 2019, including Graph Mining and Social Network Analysis, Data Mining and Search, and foundational courses in electrical engineering. He has also co-organized tutorials at major conferences including AAAI, KDD, ICDM, and CIKM on advanced topics in hypergraph neural networks and real-world hypergraph analysis. As the leader of the Data Mining Lab, he mentors numerous graduate students and postdoctoral researchers, fostering a collaborative research environment that has produced significant contributions to the field of data mining and network analysis. Research Leadership Professor Shin leads the Data Mining Lab at KAIST, which focuses on developing novel algorithms for analyzing complex networks and high-dimensional data. The lab has produced numerous influential software tools including D-Cube, M-Zoom, CoreScope, and DenseAlert, which are widely used in both academic research and industry applications. His research group maintains active collaborations with institutions worldwide and has received funding from various sources to support their innovative work in data mining and network analysis.

پروفایل رسمی دانشگاه