Find Academic Supervisors

Nikolaos DeligiannisView profile

Associate Professor

• Interpretable Machine Learning
• Explainable AI
• Federated AI
• +5 more

Nikolaos Deligiannis is an Associate Professor at the Department of Electronics and Informatics (ETRO) of Vrije Universiteit Brussel (VUB). He holds a PhD in Engineering Sciences from VUB (2012) and a Diploma in Electrical & Computer Engineering from the University of Patras (2006). Previously, he was a Senior Researcher at University College London (2013-2015). His research focuses on interpretable machine learning, federated AI, and applications in image/video processing, computer vision, and natural language processing. He is an IEEE member and serves as an Associate Editor for the IEEE Transactions on Image Processing. He leads major projects such as the EU-funded 'Reinventing Multiterminal Coding for Intelligent Machines' (2025-2030) and 'ENACT: Environmental Effect on Health Care' (2025-2028). His work spans 202+ publications, including seminal papers on explainable AI and federated learning. Key awards include the EURASIP Best PhD Award (2017) and the Francqui Research Professorship (2024). Deligiannis has supervised 39 student theses, including master's works on distributed query systems, algorithmic trading, and water level forecasting. His research also addresses healthcare applications, such as developing a prognostic model for COVID-19 severity using thoracic CT scans. He actively participates in conferences and workshops, delivering talks on topics like graph-based explanations and deep learning optimization.

Christophoros NikouView profile

Professor

• Image Processing
• Computer Vision
• Pattern Recognition
• +12 more

Christophoros Nikou is a Professor in the Department of Computer Science and Engineering at the University of Ioannina, Greece. He holds a Ph.D. in Image Processing and Computer Vision from Université Louis Pasteur - Strasbourg I, France (1999), a DEA in Photonics and Image Processing from the same institution (1995), and a Diploma in Electrical Engineering from Aristotle University of Thessaloniki, Greece (1994). His research interests include: Image Processing Computer Vision Pattern Recognition Biomedical Image Analysis Medical Imaging Machine Learning His recent publications (2022–2024) reflect a strong trend toward deep learning, generative models, and multimodal analysis, particularly in document image analysis, super-resolution, and biomedical applications. He has made significant contributions to visual tracking, segmentation, and image registration, with recent work extending into virtual reality, hypercomplex neural networks, and model compression. Scientific awards include: Best paper award, IAPR/IEEE International Conference on Biometrics (ICB’16), 2016 Best paper award, Bayesian and Graphical Models for Biomedical Imaging (BAMBI’16), 2016 He has supervised numerous students, many of whom have co-authored publications with him, and his research has been supported by collaborations across multiple institutions. He has also co-edited a book on biomedical image processing and contributed to several book chapters. His work spans both theoretical and applied domains, with consistent publication in top-tier IEEE and Springer venues.

Weiming FengView profile

Assistant Professor

• Theoretical Computer Science
• Discrete Probability
• Sampling Algorithms
• +3 more

Dr. Weiming Feng is an incoming Assistant Professor at the School of Computing and Data Science of The University of Hong Kong. His research focuses on Theoretical Computer Science, particularly sampling and approximate counting algorithms, with applications in Statistics and Learning Theory. Prior to joining HKU, he held postdoctoral positions at The University of Edinburgh, UC Berkeley, and ETH Zürich. Education: PhD in Computer Science from Nanjing University (2021). Research interests include Discrete Probability, Markov Chain Monte Carlo (MCMC), and algorithmic developments for high-dimensional distributions. His work bridges theoretical foundations and practical applications, addressing challenges in computational efficiency and probabilistic modeling. Notable contributions include advancements in deterministic approximation of statistical distances, MCMC derandomization, and fast sampling techniques for combinatorial problems. His publications span top venues like SODA, FOCS, and STOC, reflecting contributions to algorithm design and computational theory. Lab and Team: While specific lab affiliations are not mentioned, his research is embedded within the broader computational and data science initiatives at HKU's School of Computing and Data Science.

Geoffrey J. GordonView profile

Professor

• Multi-agent planning
• Reinforcement learning
• Decision-theoretic planning
• +7 more

Geoffrey J. Gordon is a Professor in the Machine Learning Department at Carnegie Mellon University and affiliated with the Robotics Institute. His research spans multi-agent planning, reinforcement learning, decision-theoretic planning, statistical models of complex data, computational learning theory, and game theory. He leads the SELECT lab (SEnse, LEarn, and aCT), focusing on predictive state representations, spectral learning, and applications in robotics. His recent work integrates deep learning with controlled dynamical systems and optimization, as seen in publications at AAAI and AISTATS. Research Interests: Multi-agent systems and game theory Reinforcement learning and dynamical systems Statistical models for high-dimensional data Spectral learning and quantum Markov models Scientific Awards: Best paper award at ICML 2010 Teaching: 10-405/605: Machine Learning with Large Datasets (2023) 10-606/607: Mathematical/Computational Background for ML (2022, 2017) 10-701: Intro to Machine Learning (2021, 2014) Labs & Teams: SELECT Lab (SEnse, LEarn, and aCT) Collaborations with Stanford Robotics Lab, AUTON Lab, and others

• Scientific Visualization
• Computer Graphics
• Virtual Reality (VR)
• +5 more

Prof. Dr. rer. nat. Mario Hlawitschka is a Professor of Computer Graphics at the Faculty of Computer Science and Media, Leipzig University of Applied Sciences (HTWK Leipzig), where he has served as Dean since 2024. He previously held roles as a Junior Professor for Scientific Visualization at the University of Leipzig (2011–2015) and a Postdoctoral Researcher at the University of California, Davis (2008–2011). His research focuses on scientific visualization , integrating data processing, pattern recognition, and computer graphics with applications in virtual reality and interactive techniques .

• Computer Graphics
• Image Processing
• Scientific Visualization
• +2 more

Miquel Feixas is an Associate Professor in the Department of Computer Science, Applied Mathematics and Statistics at the University of Girona. He is a key member of the Graphics and Image Laboratory (GILab), where he contributes to cutting-edge research in computer graphics, image processing, and scientific visualization. His research focuses on the application of Information Theory to visual computing domains. This includes modeling visual attention, optimizing rendering pipelines, enhancing image quality assessment, and improving scientific data visualization through entropy and mutual information metrics. The analysis of his recent publications reveals a sustained focus on information-theoretic modeling across computer graphics and image analysis. His work bridges theoretical foundations with practical applications in medical imaging, 3D modeling, and data visualization, demonstrating consistent innovation over more than a decade. Scientific Contributions: Co-author of two books on information theory in graphics and image processing Over 100 peer-reviewed publications in top-tier venues Supervision of six doctoral theses Participation in over 20 publicly funded R+D projects Advising and Research Leadership: Miquel Feixas has directed six PhD theses and is actively involved in research management through GILab. His work is supported by multiple competitive grants, reflecting sustained funding and academic impact. He collaborates extensively within interdisciplinary teams focused on visual computing. Research Group: He is an integral member of the Graphics and Image Laboratory (GILab) at the University of Girona, a research group dedicated to advancing graphics, imaging, and visualization technologies through novel computational methods.

Taiji SuzukiView profile

Associate Professor

• Machine Learning
• Statistical Learning Theory
• Deep Learning
• +6 more

Prof. Taiji Suzuki is an Associate Professor at the University of Tokyo in the Department of Mathematical Informatics . He also serves as Team Leader of the "Deep Learning Theory" team at AIP-RIKEN , Japan. With a PhD in Information Science and Technology from the University of Tokyo (2009), he has held academic positions at the University of Tokyo (2009-2013) and Tokyo Institute of Technology (2013-2017) before returning to the University of Tokyo in 2017. University of Tokyo (2004: BEng in Mathematical Engineering) University of Tokyo (2006: MSc in Information Science and Technology) University of Tokyo (2009: PhD in Information Science and Technology) His research interests span statistical learning theory , deep learning , kernel methods , sparse estimation , and stochastic optimization . He investigates how neural networks adapt to function smoothness, avoid the curse of dimensionality, and achieve global optimization through mean-field dynamics. His work bridges theoretical guarantees (minimax optimality, convergence analysis) with practical implementations (transformers, graph neural networks, diffusion models). The 15 most recent articles focus on transformers' representation power, graph neural networks' limitations, diffusion models' convergence, and optimization theories for deep learning. Key themes include information-theoretic bounds , feature learning dynamics , and mean-field analysis . He explores applications in AI for medicine, federated learning, and biomedical modeling. Awards & Recognition: Outstanding Paper Award, ICLR 2021 MEXT Young Scientists’ Prize Outstanding Achievement Award, Japan Statistical Society 2017 Outstanding Achievement Award, Japan Society for Industrial and Applied Mathematics 2016 Best Paper Award, IBISML 2012 Best Paper Candidate, ICDM 2019 He has served as Area Chair for NeurIPS, ICML, ICLR, AISTATS, and as Program Chair for ACML. His scientific contributions include convergence theories for stochastic gradient methods, minimax analysis of deep learning vs kernel methods, and novel frameworks for distributional optimization in diffusion models.

• Statistics
• Machine Learning
• Probabilistic Graphical Models
• +2 more

Ori Shental serves as an Adjunct Associate Professor in the Department of Statistics within Columbia University's Faculty of Arts and Sciences, contributing to the institution's academic mission through specialized instruction in advanced statistical methodologies. His research expertise centers on computational statistics and machine learning, with particular emphasis on: Probabilistic Graphical Models Statistical Inference Systems Uncertainty Quantification Frameworks Bayesian Network Applications High-Dimensional Data Analysis Algorithmic Probability Structures He has taught graduate-level coursework including STAT GR5293: Introduction to Probabilistic Graphical Models during the Fall 2022 semester, focusing on theoretical foundations and practical implementations of graphical models for complex data systems.

• Causality
• Statistical Machine Learning
• Probabilistic Modeling
• +12 more

Bryon Aragam is an Associate Professor and Topel Faculty Scholar at the Booth School of Business , University of Chicago . His work bridges causality , statistical machine learning , and probabilistic modeling , with applications in AI systems like ChatGPT and DALL-E. Key research themes include: Causal Structure Learning : Extracting latent causal graphs from multimodal data using nonparametric methods. Deep Generative Models : Analyzing overparametrization and variational inference for representation learning. Latent Variable Discovery : Using Markov boundaries and convex subset lattices to uncover hidden dependencies. Algorithm Design : Developing scalable methods like DAGMA for DAG learning and theoretical guarantees for GES/PC algorithms. His paper trends reveal a focus on nonparametric statistics , graphical models , and neural network theory , with recent work on transformer memory dynamics and identifiability in deep latent models . Papers frequently appear in top venues like NeurIPS , JMLR , and AOS , emphasizing theoretical rigor and practical validation.

Jürgen SingerView profile

Professor

• Visual Computing
• Computer Graphics
• Computer Vision
• +7 more

Jürgen Singer is a Professor of Visual Computing at Harz University of Applied Sciences, coordinating the Media Informatics degree program. His academic career spans over two decades, including prior roles as Professor of Computer Graphics, Animation, and Virtual Reality (2006-2015) and senior research positions at institutions like MIT and the University of Texas. Education: PhD in Mathematics (1995), University of Houston Diploma in Theoretical Physics (1988), Friedrich-Alexander University Erlangen-Nuremberg Research Interests focus on visual computing, encompassing image processing, computer graphics, virtual reality, and machine learning. He explores applications in game development, 3D rendering, and web technologies, particularly emphasizing procedural generation, AI integration, and real-time visualization. Teaching Contributions include core courses in Java programming, software tools (Git, Docker, Jenkins), mathematics for computer graphics, and advanced topics like concurrency and distributed programming. His supervised theses reflect ongoing innovation in DevOps, metaverse content creation, and accessibility in UI design. Scientific Awards are not explicitly mentioned in the provided text. Labs & Teams: While specific lab details aren't provided, his work with student theses indicates collaboration in media informatics, game development, and visualization research groups.

Varish MulwadView profile

Researcher

• Information Extraction
• Knowledge Graph Population
• Semantic Web
• +4 more

Varish Mulwad is a Senior Scientist at GE Research with 14 years of experience in algorithm development and knowledge graph construction from structured/unstructured data. He holds a Ph.D. and M.S. in Computer Science from the University of Maryland, Baltimore County (UMBC), where he worked under Prof. Tim Finin and collaborated with Prof. Anupam Joshi, and a B.E. in Computer Engineering from University of Mumbai. Ph.D. & M.S. in Computer Science (UMBC) B.E. in Computer Engineering (University of Mumbai) His research focuses on semantic interpretation of tabular data through linked data frameworks, information extraction from unstructured text, and knowledge graph population using probabilistic reasoning and graphical models. He has pioneered domain-independent systems for table interpretation and developed novel methods for cloud SLA automation and cybersecurity threat detection via social media analysis. Recent work trends include: Context-aware web table annotation Relational table representation learning Linked data generation from spreadsheets Pre-training/fine-tuning paradigms for web tables Application of semantic web standards to cybersecurity He has led 3-4 member project teams in developing production-ready solutions, contributed to 19 peer-reviewed publications, and secured 7 patents with 900+ citations. During his academic tenure at UMBC's Ebiquity Research Lab, he co-developed the TABEL framework for table semantics inference and produced the first interactive system for meta-analysis report generation from linked data.

Nima AnariView profile

Assistant Professor

• Algorithms
• Probability
• Combinatorics
• +6 more

Nima Anari is an Assistant Professor of Computer Science at Stanford University , where he works on theoretical computer science with a focus on algorithms, probability, and combinatorics. He is a member of the Theory Group and has been hosted by Amin Saberi during his postdoctoral research. Ph.D. in Computer Science from UC Berkeley (2017), advised by Satish Rao B.Sc. in Computer Engineering and Mathematics from Sharif University of Technology His research primarily centers around: Sampling algorithms and Markov chains High-dimensional expanders Geometry of polynomials Parallel computing techniques Applications to determinantal point processes His recent publications indicate strong trends in: Parallel sampling methods (2024 STOC, COLT) High-dimensional mixing time analysis (2023 STOC, FOCS) Polynomial-based algorithm design (2021 STOC, 2020 FOCS) Scientific recognition includes: STOC Best Paper Award (2019) Google Faculty Research Award NSF CAREER Award Sloan Research Fellowship Michael and Sheila Held Prize

Nicolas MacrisView profile

Adjunct Professor

• Statistical Mechanics
• Information Theory
• Error Correcting Codes
• +3 more

Nicolas Macris is an Adjunct Professor at the École Polytechnique Fédérale de Lausanne (EPFL) in the School of Computer and Communication Sciences (IC). He is affiliated with multiple groups including the Information Processing group and the Lab for Statistical Mechanics of Inference in Large Systems . His academic career spans roles at the Faculty of Basic Science at EPFL and visiting appointments at institutions like the University College Dublin and ETH Zürich. Macris received his PhD in theoretical physics from EPFL and conducted postdoctoral research at the mathematics department of Rutgers University. His research bridges statistical mechanics , information theory , and quantum information , with a focus on error-correcting codes, graphical models, and learning theory. His work often employs methods from mathematical and statistical physics, probability, and discrete mathematics. His recent publications analyze phase transitions in high-dimensional models, quantum algorithms, and spatial coupling techniques. He has received recognition through IBM Quantum contest awards for his contributions. He actively teaches courses in quantum information processing and mentors PhD students in interdisciplinary research areas. 2019: 2nd place, IBM Quantum contest (Best Paper) 2018: 2nd place, IBM Quantum contest (Best Paper) Macris's work is supported by the Swiss National Foundation for Science , and he collaborates with labs such as the Communication Theories Laboratory and Information Processing group .

Harshit Jitendra MotwaniView profile

Research Fellow

• Computational Algebraic Geometry
• Formal Verification
• Tensors
• +5 more

Harshit Jitendra Motwani is a Postdoctoral Researcher at the Max Planck Institute for Software Systems (MPI-SWS) , Germany. Previously, he was a Postdoctoral Fellow at the Hong Kong University of Science and Technology (HKUST) (2023-2024), following doctoral research at Ghent University (2021-2023) and earlier engagements at HKUST, Ghent University, and the University of Bristol . Education : PhD in Mathematics: Algebra and Geometry from Ghent University (2021-2023), Thesis on Algebro-Geometric Algorithms for Program Synthesis; Integrated BSc and MSc in Mathematics and Computing from IIT Kharagpur (2015-2020). Research Focus : Integrates mathematics into computational domains, particularly Computational Algebraic Geometry , Formal Verification , and Tensors . His work spans program synthesis , tensor networks , conditional independence models , and control theory applications . Publications : Recent contributions include algorithmic advancements in formal methods (FM, AAAI, LAGOS), algebraic statistics (IMRN), and quantum computing (SIGMA). His research combines symbolic computation with practical software engineering challenges. Awards & Honors : IEEE Computer Society Larson Best Paper Award (2023) ACM SIGPLAN Distinguished Paper Award (2023) Young Researcher of the Heidelberg Laureate Forum (2023) INSPIRE Scholarship (2015-2020) Teaching : Guest Lecturer at HKUST, Teaching Assistant at RPTU Kaiserslautern-Landau and IIT Kharagpur. Mentored multiple bachelor's projects at Ghent University and IIT Kharagpur.

Pedram RooshenasView profile

Assistant Professor

• Artificial Intelligence
• Machine Learning
• Data Science
• +3 more

Pedram Rooshenas is an Assistant Professor in the Department of Computer Science at the University of Illinois at Chicago. His research focuses on artificial intelligence, machine learning, and probabilistic modeling. Contact: pedram@uic.edu , Office: CDRLC 5460, 850 W. Taylor St, MC 152, Chicago, IL 60607, Phone: 312.996.8833.