Dr. Mitsuoka, S. is a nuclear physics researcher at GSI Helmholtzzentrum für Schwerionenforschung GmbH in Darmstadt, Germany, specializing in heavy-ion induced fission processes and heavy element synthesis. Their research focuses on how nuclear orientation affects fission fragment mass distribution and the measurement of evaporation residue cross-sections at subbarrier energies. Dr. Mitsuoka's research interests center on experimental nuclear physics, particularly heavy-ion collision experiments involving uranium targets. Their work investigates fundamental reaction mechanisms that are critical for understanding nuclear fission dynamics and the synthesis pathways for heavy elements. The research has significant implications for both basic nuclear science and potential applications in nuclear energy. Dr. Mitsuoka has published multiple research papers between 2006 and 2014, primarily in Physical Review C and the European Physical Journal series. Their work shows a consistent focus on experimental measurements of nuclear reaction cross-sections, particularly for systems relevant to heavy element production. As a member of the Heavy Ion Nuclear Physics Research Group at GSI, Dr. Mitsuoka collaborates with leading researchers in the field including Nishio, K., Ikezoe, H., and Hofmann, S. Their experimental work contributes to GSI's broader mission in advancing nuclear physics research and developing new techniques for studying exotic nuclear systems.
Dr. Mark Hudson is a prominent researcher at the Max Planck Institute for the Science of Human History in Jena, Germany, where he leads work in the Language and the Anthropocene Research Group. He is also affiliated as Chercheur associé with the Institut d'Asie Orientale at ENS de Lyon in France. His research bridges archaeology, environmental humanities, and linguistic studies with a particular focus on East Asian prehistory. Max Planck Institute for the Science of Human History, Jena Institut d'Asie Orientale, ENS de Lyon (Chercheur associé) Hudson's research interests focus on the intersection of archaeology, environmental change, and human cultural development, particularly in Japan and East Asia. His work examines the Jōmon period, the Anthropocene, language dispersal patterns, and the relationship between agricultural development and linguistic evolution. He investigates how human societies have adapted to environmental changes over millennia and challenges notions of Japanese exceptionalism in pre-industrial environmental impact. His approach combines archaeological evidence with linguistic and genetic data to provide interdisciplinary insights into human history. Analysis of Hudson's recent publications reveals a strong focus on interdisciplinary approaches connecting archaeology, linguistics, and genetics. His work frequently examines the relationship between agricultural development and language dispersal in East Asia, with particular attention to the Transeurasian language family. Hudson's research consistently challenges simplistic narratives about human-environment interactions, demonstrating through archaeological evidence that pre-industrial Japan experienced significant anthropogenic impacts comparable to global patterns. His work on the 3000-year-old shark attack victim represents innovative bioarchaeological methods combining skeletal analysis with 3D modeling. Hudson has published extensively in top-tier journals including Nature, iScience, and Journal of World Prehistory. His research has been widely cited, with his Nature paper on Transeurasian languages receiving over 6,200 views. He has contributed to major reference works including the Cambridge World History of Violence and Routledge Handbook of the Bioarchaeology of Climate and Environmental Change. As a researcher at the Max Planck Institute, Hudson collaborates with numerous international scholars across disciplines. His work involves significant data collection efforts, such as the ARCHIPELAGO Archaeological Isotope Database for the Japanese Islands, which compiles 1476 entries of human bone and hair carbon and nitrogen stable isotopes from Japanese archaeological sites spanning from the Upper Palaeolithic to the mid-nineteenth century. His research often involves fieldwork in Japan and China, examining sites from the Jōmon period through later historical periods. Hudson's work connects with broader themes of environmental sustainability and resilience, examining how ancient societies navigated environmental challenges. His research group, Language and the Anthropocene, explores the deep historical roots of human impacts on Earth systems, challenging conventional periodizations of the Anthropocene that focus solely on the Industrial Revolution or post-1945 'Great Acceleration'.
Cătălin Hrițcu is a tenured faculty member and head of the Formally Verified Security group at the Max Planck Institute for Security and Privacy (MPI-SP) in Bochum, Germany. He also serves as Adjunct Professor in the Faculty of Computer Science at Ruhr University Bochum (RUB), where he is affiliated with HGI and the CASA Cluster of Excellence. His educational background includes: PhD from Saarland University in Saarbrücken, Germany Habilitation from ENS Paris Hrițcu's research focuses on developing rigorous formal techniques for security. His primary interests span three interconnected areas: Formal methods for security: secure compilation, compartmentalization, memory safety, speculative execution defenses, information flow control, and security protocols Programming-languages techniques: program verification, machine-checked proofs, dependent types, formal semantics, and property-based testing Design and verification of security-critical systems: compilation chains, reference monitors, tagged hardware architectures, and high-assurance cryptography His recent publications reveal a strong trajectory toward addressing real-world security challenges through formal methods, with increasing emphasis on hardware security aspects like speculative execution vulnerabilities and memory safety. Hrițcu has received significant scientific recognition: ERC Starting Grant on formally secure compilation Distinguished Paper Award at CSF 2025 for FSLH: Flexible Mechanized Speculative Load Hardening Distinguished Paper Award at CSF 2021 for SSProve As an advisor, Hrițcu has mentored numerous PhD students and postdoctoral researchers who have gone on to successful academic careers. His group receives substantial funding through projects like ERC SECOMP. He has co-authored volumes of the Software Foundations textbook series and actively teaches courses at RUB. Hrițcu leads the Formally Verified Security research group at MPI-SP, which includes PhD students, postdocs, and research interns working on cutting-edge problems at the intersection of programming languages and security. The group has made significant contributions to verification tools including F* and Coq, with applications in secure compilation and cryptographic verification.
Dr. Manuel Behrendt is a Research Fellow at the Ludwig-Maximilians-Universität München, where he serves as a staff scientist at the University Observatory in the CAST-group led by Prof. Andreas Burkert. He also holds a position with the Physics of Galactic Nuclei (PGN) group at the Max-Planck-Institute for Extraterrestrial Physics in Garching, Bavaria. His primary research focuses on the structure-formation and evolution of galactic discs in the early universe, utilizing high-resolution hydrodynamic simulations within the framework of gravitational disc instability. Dr. Behrendt's work addresses fundamental questions about: The formation and evolution mechanisms of giant clumps and small-scale structures in high-redshift galaxies The hierarchical organization of clumps, including whether observed kpc-scale clumps are composed of sub-clump clusters The role of stellar feedback in shaping galactic structure formation and kinematics The energetic sources driving high random motions observed in young galaxies A significant contribution to the field is his development of MERA.jl, a high-performance Julia package designed for analyzing large-scale astrophysical simulation data. This tool provides: Efficient numerical performance through Julia's JIT compilation Unified API for handling multi-resolution AMR grids and particle datasets Interactive development capabilities that scale from notebooks to production scripts Memory-conscious design for processing large datasets Multi-threaded I/O operations for improved performance Dr. Behrendt's publication record demonstrates a consistent research trajectory focused on galaxy formation processes, particularly examining clump structures in high-redshift galaxies. His work bridges theoretical astrophysics with practical computational methods, making important contributions both to our understanding of galaxy evolution and to the development of advanced analysis tools for the broader astrophysics community. As an educator, Dr. Behrendt actively supervises students, teaches tutorials and astrophysical laboratory courses, and serves as a substitute lecturer for Prof. Burkert's courses. His dual commitment to research excellence and educational mentorship highlights his comprehensive contribution to the academic community.
Shing-Chi Cheung is a Professor of Computer Science and Engineering at the Hong Kong University of Science and Technology (HKUST), School of Engineering. He founded the CASTLE research group and co-founded the International Workshop on Automation of Software Testing (AST) in 2006. His leadership includes serving as General Chair of FSE 2014 and chairing multiple APSEC conferences. His research focuses on software quality enhancement through program analysis, testing, debugging, and AI techniques, targeting Android apps, open-source software, deep learning systems, smart contracts, and spreadsheets. Current projects include metamorphic testing frameworks, binary analysis tools, and vulnerability detection systems for emerging technologies. His publication portfolio demonstrates consistent contributions to software engineering since 2016, with recent work emphasizing AI-integrated testing methodologies, smart contract security, and deep learning system reliability. Key trends show increasing focus on cross-language analysis, data visualization quality, and compiler-level verification for modern software stacks. Distinguished Member of the ACM Fellow of the British Computer Society Editorial board member: Science of Computer Programming (SCP), Journal of Computer Science and Technology (JCST) Former editorial board member: IEEE Transactions on Software Engineering (2006-2009), Information and Software Technology (2012-2015) Four patents in China and the United States Cheung actively mentors through the CASTLE research group and serves on program committees for major conferences including ICSE, ESEC/FSE, and ISSTA. His work bridges academic research with practical applications through industry collaborations and tool development. He has contributed to numerous workshops and symposia as steering committee member and program chair.
Chao Zhang is a Tenured Associate Professor at Tsinghua University, specializing in software security, system security, data security, and AI security. He leads the VUL337 research group and serves as the coach of the Blue-Lotus CTF team. His educational background includes a Ph.D. in Computer Science from Peking University (2008-2013), a B.S. in Mathematical Science from Peking University (2004-2008), and a postdoctoral position at UC Berkeley (2013-2016). Dr. Zhang's research focuses on Software Security , System Security , Data and AI Security , Program Analysis , and Vulnerability Discovery . His work spans binary code analysis, fuzzing techniques, blockchain security, and AI security. His recent publications demonstrate a strong emphasis on developing novel frameworks for vulnerability detection, binary code analysis, and securing AI systems against adversarial attacks. His publication trends show a consistent focus on practical security solutions with increasing attention to AI security challenges. Over the past decade, he has published extensively in top security conferences including IEEE S&P, USENIX Security, CCS, NDSS, and ISSTA, with a significant acceleration in publications since 2020. Tencent CSS TSec Professional Prize (2nd place, 2019) Tencent CSS TSec Breakthrough Prize (1st place, 2018) DARPA Cyber Grand Challenge CFE, 2nd in exploiting (2016) DARPA Cyber Grand Challenge CQE, 1st in defense (2015) Microsoft BlueHat Prize Contest's Special Recognition Award (2012) 5th place in Defcon CTF 2017 2nd place in Defcon CTF 2016 5th place in Defcon CTF 2015 Dr. Zhang leads the VUL337 research group at Tsinghua University, which focuses on vulnerability discovery and security analysis. He also serves as the coach of the Blue-Lotus CTF team and is a member of the V group of LiST. His research has received significant attention in the security community, with numerous publications in top-tier security venues and practical contributions to vulnerability discovery and mitigation techniques.
Shangwen Wang is an Assistant Professor in the School of Computer Science at National University of Defense Technology (NUDT) in Changsha, China. He earned his Bachelor's degree in June 2017, Master's degree in December 2019, and Ph.D. in December 2023, all from NUDT. During his graduate studies, he was supervised by Professor Xiaoguang Mao. From May 2022 to July 2023, he was a visiting student at Southern University of Science and Technology under Professor Yepang Liu. His educational background includes: Ph.D. in Software Engineering, NUDT (2020.3-2023.12), supervised by Prof. Xiaoguang Mao Visiting Scholar, SUSTech (2022.5-2023.7), supervised by Prof. Yepang Liu M.A. in Software Engineering, NUDT (2017.9-2019.12), supervised by Prof. Xiaoguang Mao B.A. in Software Engineering, NUDT (2013.9-2017.6) Wang's research focuses on program repair, program comprehension, mining software repositories, software maintenance and evolution, software testing, and AI for Software Engineering. His work bridges traditional software engineering techniques with modern AI approaches, particularly leveraging large language models for various software engineering tasks. He has made significant contributions to automated program repair, fault localization, vulnerability detection, and code generation. His research demonstrates a strong emphasis on empirical validation and practical applicability to real-world software development challenges. His recent publications show a clear trend toward integrating large language models with traditional software engineering tasks. The 15 most recent articles reveal a focus on applying LLMs to program repair, fault localization, vulnerability detection, and code generation, while maintaining strong empirical foundations. His work spans both theoretical advancements and practical tool development, with applications in software security, testing, and maintenance. His notable achievements include: CCF Outstanding Doctoral Dissertation (CCF优博) 2024 Outstanding Doctoral Graduates, NUDT, 2023 Multiple distinguished paper awards including ACM SIGSOFT Distinguished Paper Award (ISSTA'24) and IEEE TCSE Distinguished Paper Awards (ICSME'22, SANER'22) Prestigious scholarships from NUDT throughout his academic career As an active member of the software engineering community, Wang serves on numerous program committees for top conferences including ICSE, ASE, ESEC/FSE, and ISSTA. He has also contributed to teaching as a teaching assistant for courses such as Compiler, Python Programming, Discrete Mathematics, and C++ Programming. His research group appears to be actively mentoring students, as evidenced by his role as corresponding author on multiple student-led publications. Wang maintains an active research presence with collaborations across multiple institutions in China. His work demonstrates a clear trajectory from traditional program analysis techniques toward integrating cutting-edge AI approaches, particularly large language models, into software engineering practices.
Zhou Yang is an Assistant Professor at the University of Alberta and Fellow at the Alberta Machine Intelligence Institute (Amii), with research focusing on the intersection of software engineering and artificial intelligence. His academic journey includes a Ph.D. from Singapore Management University, an M.Sc. in Software System Engineering from University College London, and undergraduate studies at Yangzhou University. His research interests span Software Engineering, Artificial Intelligence, AI for Software Engineering (AI4SE), Software Engineering for AI (SE4AI), Large Language Models, and Cybersecurity. Yang's work explores how human and AI collaboration can improve code writing, how AI impacts open-source communities, and how developers build software in emerging environments like VR/AR. His recent publications demonstrate strong trends in code language models, with significant contributions to ASE, ICSE, ISSTA, and top journals like TOSEM and TSE. His research addresses critical challenges including token efficiency in code generation, user perception of AI coding assistants, privacy preservation in code models, and fairness in AI systems. 2024 IEEE Computer Society Best Paper Award (1 out of 183 submissions) ACM Distinguished Paper Award from ISSTA 2024 Distinguished Reviewer Award from Internetware 2024 SMU Research Staff Excellence Award (1 of 4 university-wide) SMU Presidential Fellowship Award SMU Dean's List Award 1st Place in ACM Student Research Competition at ICSE 2024 Yang actively mentors graduate students with regular one-on-one meetings, constructive feedback, and support for top-venue publications. He provides full funding through teaching assistantships and research grants, including travel support for conferences. His lab focuses on responsible research conduct and societal implications of AI work. Though early-career, he actively builds professional networks for students through collaborations and supports diverse career paths in academia and industry. He leads research in the Alberta Machine Intelligence Institute, focusing on practical applications where software engineering principles enhance AI systems and where AI techniques solve real-world software engineering challenges.
Marian Lingsch-Rosenfeld is a researcher at the Department of Computer Science, Ludwig-Maximilians-Universität München (LMU Munich), affiliated with the Software and Computational Systems Lab. Based in Office Room F 012 at Oettingenstraße 67, Munich, they actively contribute to software verification research and mentor graduate students through thesis projects. Research interests focus on software verification , program analysis , and model checking , with specific expertise in predicate abstraction, constrained horn clauses, and deductive verification techniques. Their work bridges theoretical foundations with practical verification tools, particularly CPAchecker. Recent publications demonstrate significant contributions to verification witnesses, program transformations, and loop abstraction techniques. Conference participation includes active roles in ASE, ECOOP, and VMCAI as both author and committee member for artifact evaluation. As a thesis supervisor, they guide students through advanced topics including: Constrained-Horn-Clause export for CPAchecker BMC algorithm performance improvements Software Verification Witnesses extensions Deductive verifier development Compiler optimizations impact analysis Available for consultation via office hours by appointment through meet.lrz.de, with communication primarily via university email channels.
Xiaoning Du is a Senior Lecturer (equivalent to U.S. Associate Professor) at the Department of Software Systems and Cybersecurity within the Faculty of Information Technology at Monash University, Australia. She was promoted to this position effective July 1, 2025, having previously served as a Lecturer (Assistant Professor) since joining Monash in February 2021. Her research bridges the gap between theory and practical applications of program analysis and formal methods in evaluating traditional and AI-assisted software systems. Dr. Du's educational background includes: PhD from Nanyang Technological University (2020) Bachelor's degree from Fudan University (2014) Dr. Du specializes in software engineering, artificial intelligence, and cybersecurity , with particular focus on SE4AI (Software Engineering for AI), software analysis and testing . Her research has made significant contributions to the security and quality assurance of intelligent software systems, especially intelligent software engineering tools. She is best known for her work on Devign , BigCodeBench , DeepStellar , and SimPy , which have advanced the fields of code generation, program analysis, and AI security. Her approach consistently bridges theoretical foundations with practical applications to improve software quality and security. Dr. Du's recent publications demonstrate a strong focus on the intersection of software engineering and AI, particularly examining how large language models interact with source code. Her work addresses critical challenges in code generation efficiency, security vulnerabilities in AI-assisted development, and fairness in AI systems. She has made significant contributions to benchmarking frameworks like BigCodeBench and has pioneered research on watermarking techniques to protect code datasets from misuse by neural code completion models. Dr. Du has received numerous prestigious awards and recognitions: 2024 Google Research Scholar Award in Software Engineering ACM SIGSOFT Distinguished Paper Award (ISSTA'24) ICLR Oral presentation (2025) 2024 FIT Dean's Early Career Researcher of the Year Award Multiple FIT ECR Seed Grants (2021-2023) Dr. Du actively mentors PhD students, with notable successes including Terry (2024-2025 IBM PhD Fellowship Award recipient) and Zhensu (2024 Bytedance Scholarship Award recipient). She is currently seeking self-motivated PhD students with strong programming skills and relevant research experience, offering full scholarship support. Her research has been supported by multiple grants including the Google Research Scholar Program award and several FIT ECR Seed Grants that have enabled her team to pursue innovative research in software security and AI-assisted development. Dr. Du leads a research group focused on intelligent software systems security and quality assurance. Her team has developed several influential tools and benchmarks including Devign, BigCodeBench, DeepStellar, and SimPy. These resources have become important assets for researchers and practitioners working at the intersection of software engineering and artificial intelligence, particularly in the areas of code generation, program analysis, and security testing of AI systems.
Zhiyun Qian is the Everett and Imogene Ross Professor in the Department of Computer Science and Engineering at the University of California Riverside. His research bridges academic security research with practical hacking techniques, focusing on vulnerability discovery and analysis across operating systems, networks, and mobile platforms. His primary research interests include: System security: Automated cyber attacks/defenses, kernel vulnerability discovery, and security tool development Network security: TCP side channels, multi-path TCP flaws, and firewall evasion techniques AI/ML applications for security: LLM-integrated static analysis and reinforcement-learning-based fuzzing His work has led to critical discoveries including unfixable TCP side channel vulnerabilities (CVE-2016-5696) recognized with GeekPwn awards. His research methodology combines program analysis, reverse engineering, fuzzing, model checking, and machine learning to build practical security systems. Notable scientific awards include: GeekPwn 2016 most creative idea award Geekpwn 2017 winner award Applied Networking Research Prize Professor Qian actively mentors students in security competitions including Pwn2Own and GeekPwn. He serves on prestigious program committees including IEEE Security and Privacy (Oakland), ACM CCS, and USENIX Security. His teaching portfolio includes graduate courses CS 254 (Network Security) and CS 255 (Computer Security), along with undergraduate courses CS 153 (Operating Systems) and CS 165 (Computer Security). He leads the SecLab research group at UCR (GitHub: seclab-ucr, 3824★) developing security tools for kernel and Android ecosystems. Current projects focus on LLM-enhanced static analysis, precise vulnerability detection, and automated patch testing.
Gang (Gary) Tan is a Professor in the Computer Science and Engineering Department at Pennsylvania State University, co-directing the Institute for Networking and Security Research (INSR). His research bridges computer security, formal methods, and programming languages to develop practical solutions for software vulnerabilities and AI fairness. Education: B.E. in Computer Science from Tsinghua University Ph.D. in Computer Science from Princeton University Dr. Tan specializes in applying compiler techniques and formal verification to security challenges, with seminal work on cache side-channel attacks and fairness in machine learning. His Security of Software (SOS) Group develops frameworks that integrate theoretical guarantees into real-world systems, emphasizing measurable security outcomes and ethical AI. Recent projects focus on quantifying bias in neural networks and mitigating speculative execution vulnerabilities. Analysis of his 2021-2025 publications reveals a strategic pivot toward AI security, where he pioneers methods for fairness testing (e.g., information-theoretic debugging) and repair (e.g., NeuFair). Concurrently, his security work evolves from foundational side-channel research (SpecSafe, 2021) toward hardware-software co-design solutions, demonstrating consistent innovation across theoretical and applied domains. Scientific Awards: James F. Will Career Development Professorship NSF CAREER Award Google Research Award (two instances) Distinguished Reviewer Award at 2018 IEEE Symposium on Security and Privacy Outstanding Research Award at Penn State Ruth and Joel Spira Excellence in Teaching Award Best Paper Award at PLDI 2024 Dr. Tan leads the SOS Group with funding from NSF (including CAREER), DARPA (ISAT study group membership), and industry partners like Google. His grants support interdisciplinary projects spanning secure compilation, fairness engineering, and hardware security, while his teaching excellence award reflects commitment to pedagogy in core systems courses. He co-directs Penn State's Institute for Networking and Security Research (INSR), fostering collaboration between systems, security, and AI researchers. The SOS Group maintains active partnerships with industry security teams and contributes to open-source tools for vulnerability detection, with recent work expanding into fairness certification for machine learning pipelines.
Jie Lu is an Associate Professor at the Institute of Computing Technology of the Chinese Academy of Sciences (ICT, CAS), where he leads research in software security and program analysis. His work focuses on developing advanced program analysis techniques to improve software reliability and security, with applications in cloud systems, distributed environments, and modern web applications. Dr. Lu's research interests include: Software Security: Focusing on vulnerability detection and prevention in open-source software Program Analysis: Specializing in static/dynamic analysis techniques and context-sensitive pointer analysis Cloud Systems: Researching distributed system security, crash-recovery, and concurrency bug detection His recent publications demonstrate a strong focus on practical security solutions for real-world systems. The research spans Kubernetes ecosystems, PHP applications, Linux kernel security, Java web applications, and Windows IPC systems. A notable trend is the development of precise static analysis techniques that balance efficiency with accuracy, addressing the longstanding challenge in program analysis. His work often bridges theoretical advances with practical implementations that have been adopted by industry. Dr. Lu has received several prestigious awards: ACM SIGSOFT Distinguished Paper Award 2025 Best Paper Honorable Mention at CCS 2022 Chinese Academy of Sciences Outstanding Doctoral Dissertation 2021 Chinese Academy of Sciences President's Special Award 2020 ICT New Hundred Stars 2020 Dr. Lu actively mentors students and researchers, recruiting PhD candidates, Master students, and research interns interested in software security and program analysis. His research has been supported by the National Natural Science Foundation of China, CCF-Huawei Innovation Research Plan, and CCF-Ant Research Fund. The Program Analysis Group (ICT-PAG) at the National Key Laboratory of Processor has successfully identified numerous errors and vulnerabilities in popular open-source applications, with over 200 severe bugs confirmed by the open-source community and assigned more than 100 CVE numbers. His research group, the Program Analysis Group (ICT-PAG), is based in the National Key Laboratory of Processor at ICT, CAS. The group has achieved significant impact through both academic publications in top venues (SOSP, CCS, USENIX Security, NDSS, OOPSLA, ISSTA, FSE, ASE, TSE) and practical applications in leading IT companies and government organizations.
Tristan Coignion is a researcher at University of Lille affiliated with Inria (French National Institute for Research in Digital Science and Technology), actively contributing to software engineering and artificial intelligence research. His work bridges theoretical AI advancements with practical software development challenges, particularly through conference publications at ASE and EASE. His research interests center on Large Language Models in programming contexts , with specific focus on code optimization efficiency , environmental impacts of AI-generated code , and empirical performance validation . Coignion investigates critical trade-offs between computational speed and energy consumption in LLM-optimized code, while also analyzing real-world effectiveness of AI-generated solutions through platforms like Leetcode. Recent publications reveal two interconnected research thrusts: the 2025 ASE paper exposes hidden energy costs in LLM-based optimization, challenging assumptions about computational efficiency, while the 2024 EASE study establishes empirical baselines for LLM code performance in competitive programming environments. Together, these works form a cohesive investigation into the sustainability and practicality of AI-assisted software development, highlighting previously overlooked environmental dimensions in the field.
Yao Wan is an Associate Professor at the School of Computer Science and Technology, Huazhong University of Science and Technology (HUST) in Wuhan, China. He leads the ONE Lab, focused on empowering machines to interact with the physical world through unified natural language interfaces (Language + X paradigm). He obtained his Ph.D. from Zhejiang University and has research visiting experience at Chinese University of Hong Kong, University of Technology Sydney, and University of Illinois Chicago. His research bridges Artificial Intelligence and Software Engineering, with core interests in: Natural Language Processing for code intelligence Large Language Model applications Multimodal learning across code, vision, and UI domains Program analysis and code generation Software engineering automation His publications demonstrate strong focus on applying transformer-based models to software engineering challenges, with recent work expanding into multimodal applications. Research spans code model security, GUI generation, data visualization, and compiler understanding, predominantly using deep learning approaches. Awards: IEEE TCSE Distinguished Paper Award for SANER 2025 publication He actively mentors students through the ONE Lab and serves on program committees for top conferences including ASE, ISSTA, and ICSE. He is seeking highly-motivated undergraduate researchers to join his team. The ONE Lab conducts cutting-edge research at the intersection of programming languages and artificial intelligence, with ongoing projects in code intelligence, multimodal learning, and LLM applications for software engineering.
