Find Academic Supervisors

Mohammad Mahdi KhaliliView profile

Assistant Professor

• Machine Learning
• Theoretical Machine Learning
• Applied Machine Learning
• +6 more

Mohammad Mahdi Khalili is an Assistant Professor in the Department of Computer Science and Engineering at The Ohio State University's College of Engineering. He also serves as a part-time Research Scientist at Yahoo! Research, focusing on theoretical and applied machine learning with emphasis on robustness, interpretability, and model compression for large-scale systems including LLMs. Dr. Khalili earned his Ph.D. in Electrical Engineering and Computer Science and MSc in Applied Mathematics from the University of Michigan, Ann Arbor. Prior to OSU, he was a research scientist at Yahoo Research and a postdoctoral researcher at UC Berkeley. His research spans mechanistic interpretability of foundation models , privacy-aware model compression , and fairness in sequential decision-making . Current projects include counterfactual reasoning for fair ML, physiological signal analysis for worker health monitoring, and corruption analysis in model mechanisms. His work bridges theoretical guarantees with practical healthcare and security applications. Recent publications reveal strong focus on model compression techniques (block-wise sparsity, quantization) and interpretability methods for LLMs, with growing emphasis on physiological signal processing applications. The 2024-2025 papers show increasing integration of healthcare domains like ECG analysis and construction worker monitoring. Dr. Khalili currently advises four PhD students: Zhiqun Zuo: Counterfactual Reasoning Zhongteng Cai: Privacy-Aware Model Compression (UAI travel grant recipient) Ding Zhu: Trustworthy Model Compression & Time Series Analysis Vishnu Chhabra: Mechanistic Interpretability His research is supported by two NSF grants (health monitoring systems and dynamic environment robustness), a Translational Data Analytics Institute grant for medical AI, and a College of Engineering grant for large-scale systems. The lab recently acquired a dedicated GPU server for intensive computations. He actively contributes to the ML community through invited talks (Midwest Machine Learning Symposium) and publications in top venues including NeurIPS, ICML, and UAI.

José María Guerrero RodríguezView profile

Professor

• Electronics
• Sensor Design
• Space Instrumentation
• +3 more

José María Guerrero Rodríguez serves as a Professor in the Department of Automation, Electronics, Architecture and Computer Networks Engineering at the University of Cadiz, Spain. His research is anchored within the TIC138 Electronic and Electromagnetic Design group under the PAIDI Areas for Information and Communication Technologies, focusing on advanced instrumentation systems for space and industrial applications. He completed his doctorate at the University of Cadiz in 2009 with the thesis A contribution to reconfigurability in intelligent instrumentation based on sensors and programmable devices , supervised by Dr. Diego Gómez Vela. His educational background forms the foundation for his expertise in sensor reconfigurability and programmable device integration. Guerrero Rodríguez's research spans Electronics, Embedded Systems, and Space Instrumentation, with significant contributions in magnetic measurement subsystems for CubeSats, low-frequency noise reduction in orbital environments, and neuromorphic sensor design. His work bridges theoretical electromagnetic modeling with practical embedded implementations, particularly in spiking neuron-based movement classification and optical flow algorithms for real-time tracking. Educational innovation is a secondary focus, evidenced by flipped classroom methodologies in analog electronics instruction. Analysis of his 2020-2024 publications reveals three dominant trends: (1) Space instrumentation for CubeSats emphasizing magnetic field measurement accuracy, (2) Novel sensor architectures using asynchronous vision and spiking neurons for flame detection and movement tracking, and (3) Educational technology integration in engineering pedagogy. These areas demonstrate consistent progression from fundamental sensor design to in-orbit validation. No scientific awards were documented in the provided source material. While the source references thesis supervision and funding sections, specific student names, grant details, or advising methodologies remain undisclosed. His research direction suggests ongoing collaboration with space technology initiatives, particularly in low-technology-readiness-level subsystem validation. Guerrero Rodríguez operates within the TIC138 research group, which specializes in electronic and electromagnetic design for aerospace applications. The group's work centers on advancing the technological maturity of measurement systems through CubeSat platforms, with recent focus on in-orbit demonstrators for magnetic field characterization in low-Earth orbit environments.

Marcus LiwickiView profile

Professor

• Machine Learning
• Artificial Intelligence
• Pattern Recognition
• +4 more

Marcus Liwicki is a Chair Professor at Luleå University of Technology (LTU) and Senior Assistant Professor at the University of Fribourg, where he leads research in Machine Learning at the Department of Systems and Space Engineering. He serves on LTU's Vice-Chancellor's Council for Artificial Intelligence. Education: MS in Computer Science (Free University of Berlin, 2004) PhD (University of Bern, 2007) Habilitation (Kaiserslautern University of Technology, 2011) His research focuses on core machine learning (pattern recognition, neural networks) and applied AI in document analysis, quantum computing, and human-computer interaction. Recent publications demonstrate strong emphasis on generative AI models, multi-task learning optimization, and AI applications in physics/health domains. Awards: ICDAR Young Investigator Award (2015) for pattern recognition research He leads the Machine Learning Group at LTU's EISLAB, supervising multiple courses including Advanced Deep Learning, Neural Networks, and AI fundamentals.

Olivia WilesView profile

Researcher

• Computer Vision
• Machine Learning
• Adversarial Robustness
• +4 more

Olivia Wiles is a Senior Researcher at DeepMind, focusing on adversarial robustness, distribution shift, and computer vision. She earned her DPhil from the University of Oxford under Andrew Zisserman in the Visual Geometry Group (VGG), following a Computer Science degree at the University of Cambridge. Her work spans view synthesis, self-supervised learning, and robust model design. Education : DPhil (Oxford), Computer Science (Cambridge) Key Collaborators : Georgia Gkioxari, Justin Johnson, Richard Szeliski (FAIR), Andrew Zisserman Current Role : Senior Researcher at DeepMind Her research emphasizes adversarial robustness , 3D reconstruction , and self-supervised learning , with notable contributions to view synthesis (SynSin), image matching (Co-Attention), and robustness under distribution shifts. Publications at CVPR, NeurIPS, and ECCV highlight her work in generative models, physical prediction, and multi-view geometry. Scientific Awards : Best Poster, BMVC 2017 Best Paper, NeurIPS ML Safety Workshop 2022 Outstanding Reviewer, ECCV 2020, ICCV 2020/2021 Olivia contributes to academia via community service, including roles as Area Chair (CVPR, ICCV) and reviewer for top-tier conferences (NeurIPS, SIGGRAPH) and journals (PAMI). Her Google Scholar profile reveals ongoing work in unsupervised physics modeling , GANs , and intuitive physics from visual data.

• Geometry
• Machine Learning
• Data Science
• +2 more

Vidit Nanda is a Professor in the Department of Mathematics at the University of Oxford, actively contributing to Geometry, Machine Learning, Data Science, and Topological Data Analysis. His work bridges discrete Morse theory, persistence modules, and computational topology with practical applications in data science and biology. Research Focus: Topological Data Analysis, Algebraic Structures, and Computational Topology Recent Publications: Focus on hyperquiver representations, stratification theory, and Wasserstein-based dimension estimation (2023–2025) Collaborations: Regularly works with researchers in applied mathematics, computer science, and computational biology

Ryan MarcusView profile

Assistant Professor

• Machine Learning
• Query Optimization
• Index Structures
• +4 more

Ryan Marcus is an Assistant Professor in the Department of Computer and Information Science at the University of Pennsylvania. His research focuses on integrating machine learning into data management systems to create adaptive tools that optimize hardware utilization, invent novel processing strategies, and interpret user intentions. Currently based in Office 407, Amy Gutmann Hall, he actively explores query optimization, index structures, intelligent clouds, programming language runtimes, program synthesis for data processing, and reinforcement learning applications to systems challenges. Key research themes include machine learning for databases , learned query optimization , intelligent cloud systems , and blockchain adaptability . Scientific achievements include the Best Paper Award at SIGMOD '21 for the Bao system and the development of AutoSteer, a cross-database learned query optimizer. Notable PhD advisees co-advised include Peizhi Wu (with Zack Ives), Jeffrey Tao (with Andrew Head), and Zixuan Yi (with Zack Ives). His recent work, presented at venues like VLDB and SIGMOD, emphasizes scalable LLM-augmented data systems (ScaleLLM), robust cardinality estimation, and adaptive Byzantine fault-tolerant consensus (BFTBrain). For full system evaluations, he created testing environments such as BFTGym. Contact: rcmarcus@seas.upenn.edu

Pavel ZemcikView profile

Visiting Professor

• Computer Graphics
• Computer Vision
• Machine Vision
• +7 more

Pavel Zemcik serves as a Visiting Professor in the Computational Engineering department at the School of Engineering Sciences, Lappeenranta University of Technology (LUT). His academic work spans multiple domains within computer science with a strong emphasis on visual computing technologies. Dr. Zemcik's research interests encompass a broad spectrum of visual computing disciplines, including computer graphics, computer vision, machine vision, and image processing. His work particularly focuses on light field rendering techniques, 3D display technologies, and advanced wavelet transform applications. He has made significant contributions to GPU acceleration methods for real-time visual processing and has explored applications in both industrial settings and medical imaging. Analysis of his recent publication trends reveals a concentrated research trajectory in light field technologies and 3D display systems over the past five years. His work demonstrates increasing sophistication in handling visual quality metrics, focus management, and compression techniques specifically tailored for 3D displays. The research shows strong interdisciplinary connections between computer graphics, signal processing, and human perception studies. His scholarly output demonstrates consistent productivity across multiple high-impact venues in computer graphics and computer vision. While specific grant information isn't detailed in the available materials, his publication pattern suggests sustained research funding supporting his work in visual computing technologies.

Giorgos BouritsasView profile

Research Fellow

• Geometric Deep Learning
• Graph Deep Learning
• Weight Space Learning
• +5 more

Giorgos Bouritsas is a machine learning scientist and postdoctoral fellow at the Archimedes AI unit / Athena Research Center, affiliated with the Department of Informatics and Telecommunications at the National and Kapodistrian University of Athens. He also serves as an adjunct lecturer at NCSR Demokritos. His research focuses on Geometric and Graph Deep Learning, with contributions spanning theoretical foundations of graph/geometric neural networks and generative modeling of graph/geometric data. His educational background includes a PhD in computer science from Imperial College London (2023), supervised by Prof. Michael Bronstein and Prof. Stefanos Zafeiriou, and an MEng in electrical and computer engineering from the National Technical University of Athens (2017). Dr. Bouritsas' research interests encompass Geometric Deep Learning, Graph Neural Networks, Weight Space Learning, Self-Supervised Learning, and Machine Learning applications in biology and chemistry. His work intersects with areas such as computer vision, network science, and physics, with publications in leading conferences (NeurIPS, CVPR, ICCV, ECCV) and journals (TPAMI). His recent publications demonstrate trends in geometric deep learning, graph neural networks, and applications in bioinformatics and computer vision. His research on Scale Equivariant Graph Metanetworks was accepted for an oral presentation at NeurIPS 2024, highlighting his contributions to advancing the theoretical foundations of graph neural networks. Outstanding reviewer award, NeurIPS '21 Outstanding reviewer award, NeurIPS '23 Outstanding reviewer award, ICML '22 Outstanding reviewer award, ICML '24 Dr. Bouritsas regularly engages in educational activities, teaching postgraduate courses such as Deep Learning at the MSc in AI program at NCSR Demokritos. He also provides academic service as a reviewer for major machine learning conferences and journals. His current work at Archimedes AI centers on weight space learning, with applications in automating machine learning processes and predicting ML model behavior.

Xiaoming HuoView profile

Professor

• Statistics
• Machine Learning
• Data Science
• +5 more

Xiaoming Huo is the A. Russell Chandler III Professor at the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Tech, where he also serves as Associate Director for Research at the Institute for Data Engineering and Science (IDEaS). He holds executive leadership positions including Director of the NSF-funded Transdisciplinary Research Institute for Advancing Data Science (TRIAD) and oversees Georgia Tech's Master of Science in Analytics program in Shenzhen. Education includes: Ph.D. in Statistics from Stanford University (1999) M.S. in Electrical Engineering from Stanford University (1997) B.S. in Mathematics from University of Science and Technology of China (1993) Dr. Huo's research integrates statistical theory with computational methods, focusing on: Foundational machine learning : Theoretical analysis of deep neural networks, adversarial training frameworks High-dimensional statistics : Sparse modeling, regularization techniques, and minimax optimization Data science applications : Anomaly detection, generative modeling, and domain adaptation methods His work consistently bridges theoretical rigor with practical implementations. Recent publications (2023-2025) demonstrate strong focus on: adversarial learning frameworks, neural network theory, anomaly detection systems, and high-dimensional statistical methods. Common themes include theoretical guarantees for deep learning architectures, optimization in statistical estimation, and robust model formulations. Significant scientific recognition includes: Golden Prize, International Mathematical Olympiad (1989) IEEE Senior Member (2004) Sigma Xi Young Faculty Award (2005) Emerging Research Fronts in Mathematics (2006) Multiple competitive fellowships during academic training Leadership in major NSF initiatives includes directing TRIAD and contributing to the NSF AI Institute: ACTION. Manages interdisciplinary teams across data engineering, statistical theory, and machine learning applications.

• Computer Architecture
• Memory Systems
• Multicore Architectures
• +3 more

Georgios Keramidas is an Assistant Professor in Computer Architecture at the Department of Informatics, Aristotle University of Thessaloniki . He also holds an Adjunct Professor position at the Hellenic Open University and collaborates with institutions like the University of Peloponnese and University of Patras . Research Interests : Computer Architecture, Memory Systems, Multicore/GPU Design, Low-Power Techniques, Fault-Tolerant Systems His work focuses on cache optimization , energy-efficient computing , and security-aware memory design . Key contributions include DVFS frameworks , reuse-distance prediction , and non-deterministic cache mechanisms . Recent article trends highlight innovations in computation-in-memory , IoT platform components , and security/low-power co-design . Patents on image compression and GPU optimization reflect practical applications of his research. Academic Network : Collaborates with institutions including University of Patras , University of Manchester , and TU Dresden

Marc ChaumontView profile

Associate Professor

• Visual Data Analysis
• Remote Sensing
• Steganography
• +10 more

Marc Chaumont is an Associate Professor at the University of Nîmes since 2005 and a senior researcher at LIRMM Montpellier. He holds an HDR (Habilitation à Diriger des Recherches) and is an IEEE Senior Member. Since October 2024, he has been an associate collaborator at IRISA laboratory in Vannes, France. His career spans academic research, teaching, and interdisciplinary collaborations with institutions like MARBEC, CIRAD, and CNRS. PhD in Computer Science from IRISA Rennes (2003) Engineer Diploma from INSA Rennes (1999) His research focuses on visual data analysis , remote sensing , and digital forensics , particularly in steganography and steganalysis . He has contributed to creating large-scale databases like LSSD , a 2 million JPEG image dataset for deep-learning steganalysis. His work extends to AI applications in marine ecology, medical imaging, and poverty estimation from satellite data. Recent publications highlight collaborations across disciplines, including transformer models for socioeconomic indicator prediction, 3D fish tracking in coral reefs, and self-supervised encoder pretraining for chronic wound segmentation. He has supervised interns like Ayman El Mannouy (2024) and Abir Zahi (2023) in projects related to weakly supervised segmentation and marine biodiversity. IEEE Senior Member (2020) Top-3% Best Reviewer at IEEE ICIP 2020 Marc has taught courses ranging from signal processing to image compression since 1999. His technical contributions include software tools for image databases and steganalysis algorithms. He actively participates in European projects like DFUC'2024 and ConvEntion for astronomical data classification.

Gokberk CinbisView profile

Associate Professor

• data-efficient machine learning
• few-shot learning
• zero-shot learning
• +6 more

Gökberk Cinbiş is an Associate Professor at the Department of Computer Engineering, Middle East Technical University (METU), leading research in data-efficient machine learning with minimal supervision. His work spans zero-shot, few-shot, weakly-supervised, and self-supervised learning, with applications in vision-language integration and large-scale image/video understanding. PhD from Université de Grenoble (2014) M.A. from Boston University (2010) His research focuses on generative models, meta-learning, and robust computer vision systems. Recent work explores sparsity in parameter-efficient fine-tuning, token embeddings for vocabulary extension, and domain-aware LoRA components for personalization. Notable trends in his publications include: Advancements in zero-shot and few-shot learning Applications in remote sensing (SAR2ET for evapotranspiration) Meta-learning and hybrid augmentation techniques Sign language recognition and industrial vision benchmarks Scientific honors include: Science Academy - Young Scientist Award (BAGEP 2024) Google Faculty Research Award (2019-2020) Best PhD Thesis Prize by AFRIF (2015) Alper Atalay Best Student Paper Award (2016) He has supervised MSc students Gencer Sumbul and Berkan Demirel, secured TUBITAK grants on meta-learning and any-shot learning, and organized workshops on industrial inspection at CVPR and ECCV. Cinbiş leads METU ImageLab, focusing on computer vision and machine learning.

Lily MengView profile

Senior Lecturer

• Machine Learning
• Computer Vision
• Pattern Analysis
• +2 more

Dr. Lily Meng is a Senior Lecturer at the University of Hertfordshire's School of Physics, Engineering & Computer Science. With over 15 years of academic work, she specializes in Machine Learning, Computer Vision, and Biometrics, focusing on face recognition systems and privacy-preserving technologies. Her research bridges theoretical innovation with real-world applications. Ph.D. in Pattern Recognition (University of Liverpool, 2002) M.Sc. in Microelectronic Systems & Telecommunications (University of Liverpool, 1998) Her research interests span: Face recognition algorithms for security control Real-time face de-identification in multimedia Conditional GANs for privacy-preserving image synthesis Biometric data governance and ethical AI Standardization of multimedia coding European COST Action IC1206 leadership Key article trends include computer vision, privacy technology, and biomedical applications. Notable awards: Best Research Guidance (2018) She leads the Networks and Security Research Centre and participates in industry collaborations including Santander UK and European COST networks.

• Information Retrieval
• Data Science
• Text Analytics
• +5 more

Christina Lioma is a Full Professor at the Department of Computer Science (DIKU), University of Copenhagen . She has held academic positions including Associate Professor (2014-2018) and Freja Fellow/Assistant Professor (2012-2013) at the same institution. M.Hons (University of Glasgow, 2001) M.Sc. (University of Manchester, 2003) Ph.D (University of Glasgow, 2007) Her research focuses on Information Retrieval , Text Analytics , and Recommender Systems within Applied Machine Learning and Natural Language Processing . Recent work examines fairness-relevance tradeoffs in recommendation systems and neural mechanisms for knowledge conflict tracing. Recent publications in Nature Communications and top conference proceedings (WWW, SIGIR) explore hybrid computation architectures, brain-based language generation, and fairness evaluation metrics. She actively participates in academic conferences as organizer and speaker, including the European Conference on Information Retrieval.

• Information Retrieval
• Machine Learning
• Evaluation
• +4 more

Maria Maistro is a Tenure Track Assistant Professor at the Department of Computer Science, Faculty of Science, University of Copenhagen. Her research focuses on Information Retrieval (IR) with emphasis on evaluation, reproducibility, click log analysis, learning to rank, expert search, and machine learning applications to IR. She contributes to the AMAOS project aiming to advance expert search methodologies. PhD in Computer Science (IR) from University of Padua (2017) MSc in Mathematics (probability, stochastic methods) from University of Padua (2014) Maria's research addresses critical challenges in IR evaluation through stochastic modeling and user signal analysis. She investigates fairness-relevance tradeoffs in recommender systems, cross-cultural retrieval frameworks, and explainability techniques for language models and recommendation algorithms. Her work combines theoretical foundations with practical applications in healthcare records, insurance domains, and culinary contexts. Recent publications (2024–2025) demonstrate her expertise in: Retrieval-Augmented Generation (RAG) for cross-cultural adaptation Fairness evaluation in recommender systems EEG-based semantic relevance analysis Session-based recommendation explainability Language model pruning consistency Reproducibility frameworks for IR experiments Maria actively participates in academic activities through conference organization roles, including: Organizer, CENTRE@CLEF 2019 Organizer, CENTRE@NTCIR 2019 Organizer, CENTRE@CLEF 2018 Organizer, LEARNER 2017