Unlearning Support Systems Professors and Supervisors

Ashia Wilsonمشاهده پروفایل

استادیار

University of California, BerkeleyUnited States

Ashia Wilson is an Assistant Professor at the Massachusetts Institute of Technology (MIT) in the Department of Electrical Engineering and Computer Science (EECS) . She is affiliated with the MIT Laboratory for Information and Decision Systems (LIDS) and the MIT Statistics and Data Science Center (SDSC) . Wilson earned her Ph.D. in Statistics from UC Berkeley (2018) and holds a B.A. in Applied Mathematics with a minor in Philosophy from Harvard University. Ph.D. in Statistics, UC Berkeley (2018) B.A. in Applied Mathematics, Harvard University Her research focuses on the intersection of machine learning, statistics, and algorithmic fairness , with emphasis on optimization algorithms, differential privacy, and ethical AI. She investigates how machine learning systems can be designed to align with clinical priorities, ensure equitable resource allocation, and maintain robust data unlearning mechanisms. Wilson's recent publications demonstrate trends in adaptive optimization , privacy-preserving algorithms , and fairness-aware machine learning . She explores challenges in clinical evaluation frameworks, adversarial relearning, and the ethical implications of algorithmic decision-making systems. ACM Conference on Fairness, Accountability and Transparency (FAccT) Best Paper Award (2024) Wilson teaches graduate-level courses in data science, machine learning, and AI ethics at MIT, including 6.036 - Introduction to Machine Learning and 6.3950 - AI, Decision Making and Society . Her work bridges theoretical advances with practical applications in healthcare, judicial systems, and algorithmic economics.

پروفایل رسمی دانشگاه

Amin Alipourمشاهده پروفایل

دانشیار

University of HoustonUnited States

Amin Alipour is an Associate Professor in the Department of Computer Science at the University of Houston, where he directs the Software Engineering Research Group. He holds a Ph.D. from Oregon State University and multiple advanced degrees from institutions in Iran and the U.S. His work focuses on improving safety and user experience of AI-assisted software engineering tools, with funding from NSF and IARPA. Prior to joining the U.S., he taught at the University of Kashan and Shiraz University in Iran. Education: Ph.D. in Computer Science, Oregon State University (Advisor: Alex Groce) M.S. in Computer Science, Michigan Technological University M.S. in Computer Engineering, Tarbiat Modares University B.S. in Computer Engineering, Petroleum University of Technology (Iran) Research interests include: Secure AI systems, particularly in code LLMs Trojan detection and mitigation in neural models Educational impacts of AI tools in programming education Formal methods for software verification Human-AI collaboration in programming tasks His recent articles explore cybersecurity in AI, student interactions with LLMs, and adversarial attacks on code models. He currently serves on program committees for ICER 2025 and ICSME 2025. His research group develops tools like FeatureExtractor and ProgramTransformer for analyzing neural code intelligence models.

پروفایل رسمی دانشگاه

Michał Woźniakمشاهده پروفایل

استاد

Wrocław University of Science and TechnologyPoland

Michał Woźniak is a Professor at the Department of Systems and Computer Networks, Wrocław University of Science and Technology. He serves as Head of the Department and leads the Machine Learning Research Team. His research spans machine learning, pattern recognition, data stream mining, and imbalanced data classification. He actively supervises MSc theses and leads multiple research projects including those on continual learning, classifier ensembles, and fake news detection. Research Interests: Machine learning, particularly inductive and continual learning Pattern recognition and classifier ensembles Data stream mining under concept drift Imbalanced data classification Fake news and disinformation detection Cybersecurity and medical decision support His recent publications (2024–2025) focus on continual learning under concept drift, deep learning for image fusion and forgery detection, ensemble methods for imbalanced data, and AI applications in network optimization. These works reflect strong trends in adaptive machine learning, robust classification, and real-world AI deployment. Scientific Awards: BEST PAPER AWARD FOR CLVISION CVPR WORKSHOP 2024 He supervises numerous students and collaborates extensively on interdisciplinary projects. He has been involved in projects such as LM LDS (2021–2024), MOO (2020–2025), IDStream (2018–2022), and others. He is also a project manager and active in academic service, including membership in the Committee on Informatics of the Polish Academy of Sciences. His research group maintains a strong presence in AI and machine learning applications. Laboratory and Teams: He leads the Machine Learning Team and is involved in multiple research groups including the Advanced Data Analysis Methods Team and Metaheuristics Team . His lab focuses on developing robust, adaptive AI models for real-world challenges.

پروفایل رسمی دانشگاه

Zachary Liptonمشاهده پروفایل

استادیار

Carnegie Mellon UniversityQatar

Zachary Lipton is an Assistant Professor at Carnegie Mellon University (CMU) jointly appointed in the Tepper School of Business and the Machine Learning Department. He holds courtesy affiliations with the Heinz School of Public Policy and Societal Computing. His research bridges core ML methods, healthcare applications, natural language processing, and critical analysis of AI's societal impacts. Tepper School of Business Machine Learning Department Heinz School of Public Policy (courtesy) Societal Computing (courtesy) Dr. Lipton leads the Approximately Correct Machine Intelligence (ACMI) Lab, focusing on robust ML systems, causal representation learning, and ethical AI development for clinical medicine. He co-founded Abridge, a healthcare AI company, and authored the interactive textbook Dive into Deep Learning . His work emphasizes clear scientific communication through expository efforts like literature reviews and the Approximately Correct blog. Recent publications highlight ACMI Lab's contributions to synthetic data quality, causal fairness analysis, diffusion model hallucinations, and medical LLM adaptation. Key research themes include distribution shift, human-AI alignment, and empirical evaluation of AI's societal impacts. Contact: zlipton@cmu.edu

پروفایل رسمی دانشگاه

Philipp Kurthsمشاهده پروفایل

پژوهشگر

University of HildesheimGermany

Philipp Kurths serves as a Researcher at the University of Hildesheim within the Department of Information Systems and Enterprise Modeling (ISUM), part of the Faculty of Mathematics, Natural Sciences, Economics and Computer Science. He works under Professor Dr. Ralf Knackstedt, who leads the department. His research focuses on information systems and enterprise modeling, with particular relevance to digital transformation initiatives. The department specializes in design science research methodology, developing socio-technical artifacts to address organizational challenges. Recent departmental work has explored unlearning support systems, conversational AI interfaces, and digital choice environments. The department has been active in numerous research projects including HULLS and Digi Hoch X, with publications appearing at major conferences such as ECIS, WI, and ICIS. While the department has produced significant research output on topics like anthropomorphic conversational agents and informal care applications, specific publications directly attributed to Kurths are not mentioned in the available information. As part of the university's 'IT for Caring Society' initiative, the department has developed a new study focus on technology applications for aging populations and informal care settings, though Kurths' specific role in this initiative isn't detailed.

پروفایل رسمی دانشگاه

Esmaeil Nadimiمشاهده پروفایل

استاد

University of Southern DenmarkDenmark

Esmaeil Nadimi is a Professor and Head of Unit at The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, where he leads the Applied AI and Data Science research unit. He holds multiple concurrent positions including Visiting Professor at Harvard University, Chair of Data Analytics at SDU eScience Center, and research roles with Innovationsfonden and Swiss National Science Foundation (SNSF) in Medicine & Biology and Health & Well-being domains. His educational background includes a Ph.D. in Electrical and Computer Engineering from Aalborg University (2008) and an M.Sc. in Electrical Engineering (Control Theory) from Sharif University of Technology (2004). Research focuses on foundational AI methodologies including Physics-Infused Learning, Meta & Transfer Learning, with applied research in healthcare (medical imaging, cancer detection, diabetic neuropathy), energy systems, and optical technologies. Core expertise spans machine learning, computer vision, statistical modeling, and medical AI systems development. Publications demonstrate strong emphasis on AI applications in medical diagnostics, particularly capsule endoscopy, cervical/colorectal cancer detection, and diabetic complication screening. Recent work increasingly addresses explainable AI frameworks and practical implementation pathways for clinical adoption. Leadership includes supervision of industrial PhD/postdoc programs and development of academic courses in AI/Data Science. Current grants involve Innovationsfonden and SNSF-funded projects. Leads multiple research teams focused on medical AI systems at SDU Applied AI and Data Science unit.

پروفایل رسمی دانشگاه

Aryan Mokhtariمشاهده پروفایل

دانشیار

University of Texas at AustinUnited States

Aryan Mokhtari is an Associate Professor in the Department of Electrical and Computer Engineering at The University of Texas at Austin, holding the Jack Kilby/Texas Instruments Endowed Faculty Fellowship and William W. Hagerty Fellowship. He serves as a Core Member of two NSF AI Institutes: the Institute for Foundations of Machine Learning (IFML) and the Institute for Future Edge Networks & Distributed Intelligence (AI-EDGE). His academic journey includes a B.Sc. in Electrical Engineering from Sharif University of Technology (2011), followed by advanced degrees from the University of Pennsylvania: M.Sc. (2014), Ph.D. in Electrical and Systems Engineering (2017), and A.M. in Statistics from the Wharton School (2017). Post-PhD, he was a Research Fellow at UC Berkeley's Simons Institute and a Postdoctoral Associate at MIT's Laboratory for Information and Decision Systems. Professor Mokhtari's research pioneers optimization theory for machine learning, with dual focus on algorithmic innovation (convex/nonconvex, minimax, and bilevel methods) and AI foundations (multi-task learning, in-context learning, machine unlearning). His work provides theoretical guarantees for large-scale data science problems while addressing practical constraints in modern AI systems. His scientific achievements are recognized through: Penn’s Joseph and Rosaline Wolf Award for Best Doctoral Dissertation Simons-Berkeley Fellowship NSF CAREER Award (CCF-2338846) Google Research Scholar Award ARO Early Career Program Award Current research is supported by multiple high-impact grants including NSF CAREER, NSF Grants (CCF-2007668, ECCS-2127697), ARO ECP, Google Research, and leadership roles in NSF AI Institutes. This funding enables exploration of adaptive optimization frameworks and next-generation learning paradigms. Students benefit from his affiliation with UT Austin's Machine Learning Laboratory and NSF AI Institutes, gaining access to collaborative networks spanning academia, industry, and government labs. His group emphasizes mathematical rigor while tackling deployment challenges in edge computing and distributed intelligence through the AI-EDGE Institute.

پروفایل رسمی دانشگاه

Zhou Yangمشاهده پروفایل

استادیار

Max Planck Institute for Security and PrivacyGermany

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.

پروفایل رسمی دانشگاه