Find Academic Supervisors

Bruce DraperView profile

Professor

• Artificial Intelligence
• Machine Learning
• Visual Learning
• +7 more

Bruce Draper is a Professor and Chair of the Department of Computer Science in the College of Natural Sciences at Colorado State University. His work bridges artificial intelligence, machine learning, and computer vision, with a strong emphasis on real-world applications involving visual data and intelligent systems. Research Interests: Draper's research centers on machine learning with a focus on visual learning, adversarial AI, and visual agents. He investigates how AI systems can perceive, interpret, and interact with visual environments through technologies like facial recognition, object tracking, augmented reality, and automated visual communication. His work addresses both the capabilities and vulnerabilities of modern AI, particularly in defending systems against adversarial attacks. Publication Trends: His recent scholarly output reflects a consistent trajectory in advancing computer vision and AI robustness. The articles span topics from adversarial defense mechanisms and visual agent autonomy to scalable learning frameworks and real-time video analysis. Collectively, they emphasize secure, efficient, and context-aware visual intelligence systems grounded in deep learning and representation learning. Scientific Awards: No specific awards mentioned in the provided text. Advising and Grants: While no students or grants are explicitly listed, his leadership role as department chair and prior experience as a DARPA program manager suggest extensive involvement in research funding, mentorship, and high-impact project direction. His background indicates likely supervision of graduate students and management of federally funded research initiatives in AI and computer vision. Labs and Teams: Although no specific lab or research group is named, his research scope implies leadership or affiliation with interdisciplinary teams working on AI security, computer vision, and augmented reality systems within the Department of Computer Science at CSU.

• Control Theory
• Real-Time Systems
• Embedded Systems
• +7 more

Anton Cervin is a Senior Lecturer at the Department of Automatic Control, Faculty of Engineering, Lund University. He is currently on leave of duty but remains actively involved in research and supervision. His work spans real-time systems, event-based control, cloud computing, and embedded systems, with strong ties to industrial applications and sustainable technologies. His research interests include: Event-Based and Stochastic Control Networked and Embedded Control Systems Cloud-Based Control and Resource Management Real-Time Scheduling and Performance Analysis Digital Twins and Fluid Modeling in Cloud Environments He has led major research projects funded by the Swedish Research Council, WASP, and ELLIIT, focusing on robust and secure cloud control, self-adaptive systems, and distributed learning. His software tools—TrueTime, Jitterbug, and TinyRealTime—are widely used in academia and industry for simulating and analyzing real-time control systems. The most recent publications highlight a shift toward intelligent, adaptive control using reinforcement learning, fluid modeling for microservices, and timing-robust cloud control—indicating a strong trend in merging traditional control theory with modern computing paradigms. His scientific contributions have been recognized with multiple Best Paper Awards: Best Paper Award - ECRTS 2021 Best Paper Award - RTNS 2016 Best Paper Award - RTCSA 2004 Best Paper Award - ECRTS 2003 Best Student Paper Award - RTCSA 1999 Anton Cervin has supervised numerous PhD students, including Max Nyberg Carlsson, Nils Vreman, and Claudio Mandrioli, and has served in key academic roles such as Director of PhD Studies and Deputy Head of Department. He has also led educational initiatives like doctoral study circles on programming languages and the history of control. He is affiliated with research environments such as WASP and ELLIIT and contributes to UN Sustainable Development Goals through advancements in smart systems and sustainable automation.

Daniel HöllerView profile

Researcher

• AI Planning
• Hierarchical Task Network (HTN) Planning
• Lifted Planning
• +12 more

Daniel Höller is a researcher in the Foundations of Artificial Intelligence (FAI) Group at the Department of Computer Science, Saarland University, Germany. He joined the group in January 2020, having previously worked at the Institute of Artificial Intelligence at Ulm University from November 2013 to December 2019. He holds an M.Sc. in Computer Science from Bonn-Rhein-Sieg University, where he studied from 2007 to 2013. Ph.D., Computer Science, Ulm University M.Sc., Computer Science, Bonn-Rhein-Sieg University (2013) Daniel Höller's research lies at the intersection of theoretical and practical aspects of AI planning. His primary focus is on Hierarchical Task Network (HTN) planning, where he has made significant contributions to expressivity analysis, solver development, and the use of classical planning heuristics to guide HTN search. He also works on lifted planning, plan repair, plan recognition, and the integration of planning with deep reinforcement learning. His work often involves formal analysis, heuristic development, and the creation of practical planning systems. He is particularly interested in how planning can be made more efficient, reliable, and applicable to real-world problems, including human-aware applications. His recent publications demonstrate a consistent trend in advancing HTN planning through novel formalisms (e.g., HDDL), sophisticated solving techniques (e.g., progression search, SAT-based approaches), and the development of robust software frameworks (e.g., PANDA, TOAD, LiSAT). His work increasingly bridges planning with learning, exploring how learned models can inform planning and how planning can provide structure for learning. The subfields span formal methods, search algorithms, knowledge representation, and system building. ICAPS 2024 Best Dissertation Award for his thesis on hierarchical planning SoCS 2024 Best Student Paper Award (co-authored) Winner in 4 out of 6 tracks in the 2023 IPC HTN competition ICAPS 2018 Best Student Paper Award ICTAI 2018 Best Paper Award TCTS 2018 Best Paper Award Shortlisted for Best Paper at KI 2020 Daniel Höller has been actively involved in teaching and mentoring, having taught courses on Artificial Intelligence and AI Planning at Saarland University, and previously served as a teaching assistant for a wide range of AI and computer science courses at Ulm and Bonn-Rhein-Sieg Universities. He has received funding through his involvement in the Transregional Collaborative Research Center SFB/Transregio 62 at Ulm University. He has organized and contributed to numerous workshops and conferences, demonstrating strong service to the academic community. Daniel Höller is a core developer of the PANDA planning framework, the TOAD HTN solver, and the LiSAT system for lifted planning. These systems are state-of-the-art tools that implement his research on heuristic search, model transformation, and SAT-based compilation. His work is conducted within the FAI group at Saarland University, a leading research group in automated planning.

• Machine Learning
• Optimization
• Deep Learning Theory
• +7 more

Prof. Dr. Aurelien Lucchi is an Assistant Professor in the Department of Mathematics and Computer Science at the University of Basel, Faculty of Science. His research group focuses on the intersection of optimization and machine learning, particularly in advancing theoretical understanding and algorithmic design for deep learning systems. His research interests include: Stochastic and non-convex optimization Deep learning theory and generalization Kernel methods and spectral analysis Transformer architectures and training dynamics Batch Normalization and initialization effects Modeling optimization via stochastic differential equations (SDEs) The recent publications (2023–2025) highlight a strong focus on theoretical machine learning, especially in characterizing optimization landscapes, generalization in kernel methods, and the role of noise and adaptive methods in training. There is a clear trend toward using advanced mathematical tools—such as random matrix theory, SDEs, and curvature analysis—to explain phenomena in deep learning. His group actively publishes in top venues including NeurIPS, ICML, ICLR, and AISTATS. Scientific awards and recognitions include: SNF Consolidator Grant (1.7M CHF) Prof. Lucchi leads an active research group with postdoctoral fellows and ongoing projects, including work on quantum machine learning and noise-adaptive optimization. He has secured competitive research funding and mentors early-career researchers. His group has received recent paper acceptances at ICLR 2025, AISTATS 2025 (oral), and NeurIPS 2024, indicating strong momentum in theoretical and algorithmic machine learning. He previously held a scientific research position at ETH Zurich (2014–2021) and earned his PhD from EPFL. The group is currently involved in two major ongoing projects: Designing and Training Hybrid Hierarchical Quantum Neural Networks with Quantum Advantage Noise-Adaptive Optimization Methods and their Robustness Properties

Damek DavisView profile

Visiting Associate Professor

• Optimization
• Machine Learning
• Signal Processing
• +4 more

Damek Davis is a Visiting Associate Professor at the Wharton Department of Statistics and Data Science at the University of Pennsylvania and an Associate Professor of Operations Research at Cornell University (currently on leave). He held NSF Postdoctoral Fellowships and completed his PhD in Mathematics at UCLA under Wotao Yin and Stefano Soatto. His research bridges optimization , machine learning , statistics , and signal processing , with a focus on convergence guarantees for stochastic and nonsmooth optimization methods. He has developed accelerated gradient descent algorithms, characterized SGD behavior in nonconvex settings, and formalized avoidance of strict saddle points in proximal methods. Key publications include exponential accelerations of gradient-based techniques and first guarantees for SGD on weakly convex functions. His work has been recognized by the Sloan Research Fellowship INFORMS Optimization Society Young Researchers Prize NSF CAREER Award SIAM Activity Group on Optimization Best Paper Prize Davis actively advises Penn graduate students and serves as an associate editor at Mathematical Programming and Foundations of Computational Mathematics . He emphasizes clear technical writing and public communication, maintaining a blog and lecture notes on optimization theory.

• Deep Learning
• Computational Mathematics
• Phase Retrieval
• +7 more

Philipp Grohs is a Professor at the Faculty of Mathematics, Department of Mathematics (University of Vienna). His research spans Deep Learning , Computational Mathematics , and Applied Harmonic Analysis . Research Areas: Phase Retrieval, Neural Network Approximation, High-Dimensional PDEs, Manifold-Valued Data, Signal Processing Projects: 5 active projects (2021-2025) including deep learning for quantum chemistry and phaseless sampling He has authored 109 peer-reviewed publications (2007-2025) with significant contributions to Gabor Phase Retrieval , Deep Neural Network Approximation , and Nonlinear Data Analysis on Manifolds . Recent work focuses on overcoming the curse of dimensionality in PDE approximations. Scientific Prizes: Recipient of 2 undisclosed scientific awards (2021-2025) Collaborations include institutions like MIT, ETH Zurich, and University of Vienna. His work appears in top venues (Nature Computational Science, Foundations of Computational Mathematics) and involves interdisciplinary applications in quantum physics and biomedical imaging.

• Communications Engineering
• Positioning Technologies (GNSS)
• Embedded Processor Systems
• +4 more

Jari Nurmi is a Full Professor at Tampere University's Faculty of Information Technology and Communication Sciences, Department of Electrical Engineering. With over 30 years of experience in academia and industry, he specializes in communications engineering, positioning technologies, embedded systems, and reconfigurable computing. His roles include Director of the national DELTA doctoral training network, head of the European Joint Doctorate A-WEAR program, and coordinator of APROPOS MSCA ITN. He has supervised 32 PhD dissertations and over 160 MSc theses. His research focuses on embedded processor systems, reconfigurable computing, approximate computing, and positioning technologies (especially GNSS receiver architectures). He is actively involved in organizing international conferences like IEEE Nordic Circuits and Systems Conference and serves on editorial boards of three journals. His recent work includes advancements in neural network inference on FPGAs, 5G NR localization, and energy-efficient edge AI for autonomous systems. Nurmi has been recognized for his contributions to conference organization and innovation. His publications span topics such as FPGA optimization, GNSS error modeling, and machine learning for healthcare applications. He leads initiatives like the EWOk dataset compression framework and the Hard SyDR benchmarking environment for GNSS algorithms.

Igor KononenkoView profile

Professor

• Artificial Intelligence
• Machine Learning
• Neural Networks
• +3 more

Prof. Igor Kononenko serves as a Professor at the Faculty of Computer and Information Science, University of Ljubljana, where he heads the Laboratory for Cognitive Modeling and teaches core courses including Algorithms and Data Structures 1, Artificial Intelligence, Intelligent Systems, and Machine Learning. Education: Ph.D. in Computer Science, University of Ljubljana (1990) Research Focus: His work centers on Artificial Intelligence , Machine Learning , and Cognitive Modeling , with recent emphasis on explainable AI and prediction reliability . He has pioneered techniques in feature contribution explanation, graph-based data mining, and archetypal analysis for complex datasets, resulting in approximately 210 publications and 10 textbooks . Publication Trends: Analysis of his 15 most recent articles reveals a decisive shift toward interpretable machine learning—particularly reliability estimation in data streams (2012-2014), graph mining for oceanographic/spatial data (2013-2019), and medical applications of explanation methods (2011-2018). His 2013-2016 work on archetypal analysis for multi-document summarization remains highly influential in NLP. Research Leadership: As principal investigator, he secured major funding including: Two ARRS programmes on Artificial Intelligence (2009-2014, 2015-2020) EU's AGROIT project for farming efficiency (2014-2016) Bilateral projects on imbalanced data learning (2010-2011), bioinformatics for cancer classification (2014-2015), and disease dataset analysis (2020-2021) Laboratory: The Laboratory for Cognitive Modeling under his direction drives innovation in AI theory and applications, with recent work spanning basketball analytics, coronary artery disease diagnostics, and hemodynamic simulation modeling.

Mohammad RastegariView profile

Adjunct Assistant Professor

• Computer Vision
• Efficient Machine Learning
• Model Compression
• +3 more

Mohammad Rastegari serves as a senior technical manager in Apple's AI/ML organization and holds an affiliate assistant professor position in the Computer Science and Engineering Department at the University of Washington. Previously, he was a research scientist at the Allen Institute for AI (AI2) where he contributed to the PRIOR team, and co-founded XNOR.ai as Chief Technology Officer. He completed his Ph.D. at the University of Maryland under the supervision of Professor Larry S. Davis, focusing on computer vision and machine learning. His research centers on efficient deep learning with major contributions in binary neural networks (notably XNOR-Networks for resource-constrained devices) and model compression . Current work extends to large language model efficiency through weight clustering, token pruning, and memory optimization while maintaining strong foundations in computer vision. Analysis of his recent publications reveals a strategic shift toward optimizing transformer-based architectures across vision and language domains, with consistent emphasis on deployable solutions for edge computing and real-world applications. He co-founded XNOR.ai (acquired by Apple) and contributed to AI2's PRIOR initiative, demonstrating a career trajectory bridging academic innovation and industrial implementation in efficient AI systems.

Alexandre Sébastien Julien LevisseView profile

Lecturer

• Computer Architecture
• VLSI Design
• Low-Power Electronics
• +4 more

Alexandre Sébastien Julien Levisse is a Lecturer at the Institute of Electrical Engineering within EPFL's School of Engineering, with additional roles as System Specialist in PAT/SEL departments and Scientist in IEM. His work centers on energy-efficient hardware architectures for edge computing and AI applications. Research focuses on: Computer Architecture & VLSI Design Low-Power Electronics for edge devices Emerging Memory Technologies (RRAM, OxRAM) Neuromorphic & Approximate Computing In-Memory/ Near-Memory Computing Edge AI Hardware Acceleration His 2022-2025 publications reveal strong emphasis on specialized edge AI hardware, including near-DRAM architectures (SideDRAM), RISC-V microcontrollers for healthcare (HEEPOcrates), and overflow-free memory systems. Key innovations involve hardware-software co-design for energy efficiency, variable precision computation, and novel memory hierarchies targeting wearable sensors and edge inference. Levisse teaches Fundamentals of VLSI Design and Lab in Advanced VLSI Design at EPFL. He actively contributes to digital education as a member of EPFL's Centre for Digital Education (CCE), developing curricula for next-generation hardware engineers.

• Artificial Intelligence
• Business Informatics
• Semantic Technologies
• +6 more

Prof. Dr. Ralph Bergmann is a full professor at the University of Trier since 2004 and leads the Experience-Based Learning Systems research group. Since 2020, he serves as topic-field leader for experience-based learning systems at the Trier Branch of the German Research Center for Artificial Intelligence (DFKI) . He has directed approximately 35 EU/DFG/BMBF-funded projects and authored over 200 papers (h-index 40) with four books and 13 edited proceedings. Academic Rank: Professor (Business Information Systems II) Key Collaborations: DFKI, KI-AIM, KIAFlex, DZW (Digital Twins), myRPA, SPELL Ralph Bergmann's research focuses on hybrid AI systems that combine data-driven methods (machine learning, case-based reasoning) with semantic technologies (ontologies, knowledge graphs). His work addresses knowledge-intensive processes like emergency call handling, healthcare discharge management, smart factory automation, and political argumentation analysis. He explores similarity assessment, workflow flexibility, and context-sensitive reasoning through frameworks like ProCAKE and CBRkit . Recent publications highlight IoT data integration (SensorStream, DataStream XES), large language models for knowledge engineering, and graph neural networks for similarity ranking. Application domains span Industry 4.0 , oncology decision support, water resource management, and clinical guideline conformance checking. His teaching includes courses on Data Mining , Semantic Technologies , and Research Internships in business informatics, with consultation hours held both in-person and online. Current projects like KI-AIM and SPELL emphasize AI anonymization in medicine and semantic platforms for control centers .

• Bioinformatics
• Machine Learning
• Neural Networks
• +5 more

Ole Winther is a Professor at the Department of Biology , University of Copenhagen , and a Professor at the Section for Cognitive Systems , DTU Compute , Technical University of Denmark . He specializes in high-dimensional biological data analysis, machine learning, and data science. Academic Affiliations: University of Copenhagen (Computational and RNA Biology), DTU Compute (Cognitive Systems) Leadership Roles: Chief Research Officer at raffle.ai, CTO at FindZebra, Head of ELLIS Unit Copenhagen, co-PI of Machine Learning for Life Science (MLLS) Center Research Interests Bioinformatics: Protein sequence analysis (SignalP, DeepLoc, DeepTMHMM), single-cell gene expression, RNA/DNA level regulation Latent Variable Models: Variational autoencoders, diffusion models, deep generative models, structured mean-field, matrix factorization Natural Language Processing: Enterprise search applications, medical context LLMs, joint retrieval/generation models AI for Science: Surrogate models for physical models (density functional theory), fast scientific dataset generation Publication Trends His research focuses on deep learning methods for bioinformatics and AI applications, with a strong emphasis on variational inference, generative models, and probabilistic architectures. Publications span top venues like Bioinformatics , NeurIPS , ICML , and JMLR , addressing both theoretical and applied challenges. Teaching He teaches courses on deep learning at both institutions ( 02456 Deep Learning at DTU and NDAK24002U Deep Learning at University of Copenhagen). Research Group His current group includes PhD/postdoc researchers like Panagiotis Antoniadis, Felix G. Teufel, and Irene R. Rodriguez. Former advisees include Casper Kaae Sønderby, Marco Fraccaro, and Lars Maaløe, many of whom now hold prominent industry/academic positions.

Earl T. BarrView profile

Professor

• Software Engineering
• Program Analysis
• Type Systems
• +6 more

Earl T. Barr is a Professor of Software Engineering at University College London (UCL), where he heads the System Software Engineering Group and is a member of the Centre for Research on Evolution, Search and Testing (CREST). His academic journey began with a Ph.D. in Computer Science from the University of California, Davis in 2009, after which he joined UCL as faculty. His research spans multiple domains within software engineering, with particular focus on program analysis, type systems, automated program repair, and the emerging field of dual channel analysis that examines the interplay between natural language and formal programming language in source code. Barr's work on the 'naturalness of software' has been influential in understanding how code differs from natural language while exhibiting statistical regularities. Barr's publication record shows a strong trend toward integrating machine learning with traditional software engineering techniques, particularly in type inference (Typilus), program repair, and code understanding. His recent work increasingly focuses on dual channel analysis, exploring how the natural language elements in code (identifiers, comments) interact with the formal programming language to create a richer communication channel for developers. MSR 2019 Most Influential Paper Award Multiple ACM SIGSOFT Distinguished Paper Awards Best Paper Award at IEEE Conference on E-Commerce Technology (2005) Barr actively supervises numerous Ph.D. students and postdocs, with current projects focusing on dual channel program analysis, AI for code, and software security applications. He has established long-term collaborations with researchers at institutions including Royal Holloway and the University of Luxembourg. His teaching portfolio at UCL includes core courses in Malware, Compilers, and Validation and Verification, reflecting his broad expertise across the software engineering spectrum. Barr leads the System Software Engineering Group at UCL, which focuses on practical applications of software engineering research with strong connections to industry problems. The group's work bridges theoretical foundations with real-world software development challenges, particularly in the areas of program analysis and automated software maintenance.

Sonia-Florina HorchidanView profile

Researcher

• Graph Databases
• Machine Learning on Graphs
• Stream Processing
• +3 more

Sonia-Florina Horchidan is a doctoral researcher at the KTH Royal Institute of Technology in Stockholm, Sweden. She is affiliated with the Division of Software and Computer Systems within the School of Electrical Engineering and Computer Science (EECS), working under the supervision of Associate Professor Paris Carbone in the Data Systems Lab . Her academic activities include teaching assistant roles for courses in distributed systems and data storage paradigms. Research Focus: Graph Databases Machine Learning on Graphs Stream Processing Federated Learning with Privacy Guarantees Approximate Query Processing via ML Serverless Streaming Graph Analytics Scientific Contributions: Her recent publications at venues like EDBT, VLDB, and AI4DB explore intersections between graph data management and machine learning. Key themes include ML inference optimization in streaming systems, privacy-preserving health data forecasting, and innovative graph query execution models. Honors & Service: Co-authored Best Paper at DEEM 2022 Best Paper Award at VLDB 2023 PhD Workshop Program Committee Member, aiDM 2024 Reproducibility Committee Member, ACM SIGMOD/PODS

Patrick BasView profile

Research Professor

• Steganography
• Steganalysis
• Digital Watermarking
• +2 more

Patrick Bas serves as Research Director and Thematic Group Facilitator for the Data Intelligence Group (DatInG) at the University of Lille, France, where he leads the Signal and Images team within the CRISTAL laboratory. His office is located at ESPRIT in Lille's Scientific City, and he holds membership on the institution's Scientific Council. Bas earned his Electrical Engineering degree (1997) and Ph.D. in Signal and Image Processing (2000) from the Institut National Polytechnique de Grenoble. His academic journey includes postdoctoral work at Université Catholique de Louvain, CNRS research at Gipsa-Lab (2001-2009), and a visiting position at Helsinki University of Technology (2005-2008). His primary research centers on steganography, steganalysis, and digital watermarking, with significant contributions to image manipulation detection and neural network applications in multimedia security. He has organized major initiatives including the BOSS steganalysis contest (2010) and served as co-coordinator for the Ecrypt European NoE's watermarking virtual lab (2004-2008). While his Google Scholar profile indicates recent publications in graph theory and combinatorics (2021-2025), these appear inconsistent with his documented research focus on multimedia security as evidenced by his thesis supervision and professional activities. Bas has supervised seven doctoral theses including Rony Abecidan's work on robust image manipulation detection (2024) and Solène Bernard's research on neural network steganography (2021). He has held editorial roles for the Eurasip Journal on Information Security (since 2011) and IEEE Transactions on Information Forensics and Security (2013-2016), and co-organized the International Workshop on Information Hiding (IH07).