Find Academic Supervisors

Michael HouleView profile

Senior Lecturer

• Data Mining
• Machine Learning
• Dimensionality Reduction
• +5 more

Michael Houle is a Senior University Lecturer in the Department of Computer Science at New Jersey Institute of Technology (NJIT). He holds a PhD from McGill University (1989) in computational geometry and has held academic and research positions at institutions including the University of Melbourne, National Institute of Informatics (Tokyo), IBM Tokyo Research Laboratory, and universities in Australia and Japan. His research focuses on dimensionality reduction, scalability in AI, machine learning, data mining, and outlier detection. He has made significant contributions to local intrinsic dimensionality estimation and its applications in clustering, classification, and adversarial vulnerability analysis. Education: PhD, McGill University, Computer Science, 1989 BSc, McGill University, Mathematics and Computer Science, 1984 Research interests include algorithmics, relational visualization, and theoretical foundations of data analysis. He has been recognized with multiple awards for best research papers at conferences such as SIAM ICDM, SISAP, and WIMS. His work bridges theoretical insights and practical applications in high-dimensional data processing and AI systems. Key areas of contribution include the development of shared-neighbor clustering methods, analysis of adversarial attack vulnerability linked to high dimensionality, and methodologies for estimating intrinsic dimensionality in local data regions. He also explores applications of these concepts in anomaly detection and machine learning model interpretability.

• Machine Learning
• Computer Vision
• Artificial Intelligence
• +5 more

Eugene Belilovsky is an Assistant Professor in the Department of Computer Science and Software Engineering at Concordia University. His research focuses on machine learning, computer vision, optimization algorithms, and their applications in medical imaging and federated learning. He explores topics such as continual learning, model merging, and bias mitigation in deep learning systems. His work bridges theoretical advancements with practical applications, including healthcare diagnostics and efficient training strategies for large models. Belilovsky's recent publications emphasize innovative methods like MuLoCo for inner optimizer design, FairDropout for enhancing minority group generalization, and techniques to scale multi-task learning with sparse masks. His studies on federated learning explore incentive mechanisms for decentralized systems and robust pre-training of large language models. His contributions to 3D reconstruction and motion prediction highlight interdisciplinary applications in computer graphics and generative models. His research trends reflect a strong emphasis on improving model efficiency, fairness, and adaptability across diverse domains. While no scientific awards are explicitly listed, his prolific publication record underscores his impactful contributions to AI and machine learning.

Nils Murrugarra-LlerenaView profile

Assistant Professor

• Computer Vision
• Machine Learning
• Natural Language Processing
• +5 more

Nils Murrugarra-Llerena is a Teaching Assistant Professor at the University of Pittsburgh's School of Computing and Information, joining in Fall 2024. He holds a PhD from the same institution. His research focuses on computer vision, machine learning, and natural language processing, with emphasis on attribute recognition, deep learning, gaze prediction, transfer learning, reinforcement learning, and metric learning. Education: PhD, University of Pittsburgh His research interests span advanced topics like visual embeddings, multimodal systems, and NLP applications in social media analysis. Recent work includes improving visual embeddings for e-commerce search engines, probabilistic models for feature selection, and analyzing weather impacts on social sentiment. Publications highlight interdisciplinary approaches, blending computer vision with applications in education technology and sketch-based retrieval. No scientific awards are mentioned in the provided information. No advisees or grant details are listed. While no specific labs or teams are noted, his work intersects with computational models and data-driven methods.

• Biomathematics
• Network Science
• Dynamical Systems
• +7 more

Mauricio Barahona is a Professor of Biomathematics and Director of the EPSRC Centre for Mathematics of Precision Healthcare at Imperial College London. He holds appointments in the Department of Mathematics within the Faculty of Natural Sciences. His research integrates dynamical systems, network science, and machine learning to address challenges in healthcare, biological systems, and complex networks. He obtained his PhD in Theoretical Physics from MIT, followed by postdoctoral fellowships at Stanford and Caltech. Key roles include leading the EPSRC Centre since 2016 and contributing to interdisciplinary initiatives such as the Biomathematics Group and the Artificial Intelligence Network. His work spans disease clustering analysis, healthcare system optimization, and applications of AI in precision medicine. He has pioneered methods for analyzing complex networks in biological and clinical contexts, including protein dynamics, antimicrobial resistance spread, and multimorbidity patterns. Research focuses on network-based models for healthcare integration, disease co-occurrence patterns, and machine learning techniques for biomedical data. His lab develops tools like RamanSPy for spectroscopic analysis and HCGA for network phenotyping. Collaborations involve diverse fields from physics to clinical medicine, emphasizing translational applications.

• Computer Vision
• Machine Learning
• 3D Reconstruction
• +5 more

Iaroslav Melekhov is a Postdoctoral Researcher at Aalto University's Department of Computer Science, affiliated with the Professorship Kannala Juho. His work focuses on advancing computer vision techniques, particularly in camera relocalization, 3D reconstruction, semantic segmentation, and autonomous systems. He has contributed to high-impact datasets like ECLAIR and developed methods for memory-efficient visual localization and medical image analysis. Melekhov holds a Nokia Foundation Scholarship (2018) and has engaged in collaborative research with institutions such as Wayve Technologies and ETH Zurich. Research Interests: 3D Reconstruction and Gaussian Splatting Camera Relocalization and Visual Localization Semantic Segmentation and Dataset Development Deep Learning for Autonomous Systems Self-Supervised Learning and Feature Descriptors Key Contributions: Co-developed the ECLAIR aerial LiDAR dataset for semantic segmentation. Advanced memory-efficient camera relocalization via differentiable product quantization. Explored medical image segmentation using SAM-generated annotations. Grants & Awards: Nokia Foundation Scholarship, 2018 Labs & Collaborations: Associated with the imedslab research group, contributing to open-source tools like SOLT. Collaborative efforts include projects with Wayve Technologies and ETH Zurich, focusing on autonomous driving and robotics.

Muhammad AwaisView profile

Senior Lecturer

• Artificial Intelligence
• Trustworthy AI
• Self-Supervised Learning
• +5 more

Dr Muhammad Awais is a Senior Lecturer in Trustworthy and Responsible AI at the University of Surrey. He leads research on foundation models and self-supervised learning, with affiliations to the Surrey Institute for People-Centred Artificial Intelligence (PAI) and the Centre for Vision, Speech and Signal Processing (CVSSP). His expertise spans AI ethics, audio processing, medical AI, and biometric systems. Education: PhD in AI, MSc in AI, BSc Computer Engineering, BSc Mathematics and Physics. His research focuses on advancing AI through self-supervised learning techniques, with applications in healthcare (e.g., Parkinson’s Disease rehabilitation), transportation, and security systems. He has published extensively on topics like masked autoencoders, audio event classification, and age-invariant face recognition. Key contributions include DailyMAE (fast autoencoder pretraining), ASiT (audio-spectrogram transformers), and AiCareGaitRehabilitation (AI-driven gait rehabilitation). His work emphasizes ethical AI deployment and cross-modal learning.

Sara Atito Ali AhmedView profile

Research Fellow

• Computer Vision
• Machine Learning
• Medical Imaging
• +5 more

Dr. Sara Atito Ali Ahmed is a Surrey Future Fellow at the University of Surrey's Faculty of Engineering and Physical Sciences , specifically within the Centre for Vision, Speech and Signal Processing (CVSSP) . She holds a PhD in Computer Science and specializes in advanced machine learning techniques, with a focus on computer vision, medical imaging, and audio signal processing. Her research emphasizes self-supervised learning, multimodal data fusion, and deep learning ensembles for robust decision-making. Her academic journey includes contributions to healthcare AI through projects like SS-CXR for medical image pretraining and DeepChest for multi-task learning in chest X-ray diagnostics. She has also developed innovative models such as the ASiT audio-spectrogram transformer and DailyMAE for efficient masked autoencoder training. Her work spans diverse domains including robotics perception, SAR target recognition, and plant species identification via ensemble methods. Awards and recognitions are not explicitly mentioned in the provided texts, but her prolific publication record highlights her impact in top-tier venues. She has collaborated on interdisciplinary projects ranging from biomedical applications to environmental sensing, demonstrating a commitment to bridging theoretical research with real-world applications.

Siyu HuangView profile

Assistant Professor

• Computer Vision
• Deep Learning
• Generative Models
• +3 more

Siyu Huang is an Assistant Professor in the School of Computing at Clemson University, leading the Vision and Learning Lab (ViL). His research focuses on 2D/3D vision, generative models, and data-efficient learning with applications in biomedical and AI-driven systems. Huang holds a Ph.D. from Zhejiang University (2014–2019), a visiting scholar position at Carnegie Mellon University (2018–2019), and prior industry experience at Baidu Research and Harvard University's Visual Computing Group. He teaches advanced courses like Machine Learning-based Image Synthesis and Applied Computer Vision. Education: Ph.D., Information Science & Electronic Engineering, Zhejiang University (2014–2019) Visiting Scholar, Carnegie Mellon University (2018–2019) Bachelor's, Zhejiang University (2010–2014) Research Interests: Generative AI, 3D reconstruction, biomedical image analysis, and scalable unpaired translation. His work bridges vision and generative models for small-data scenarios. Publications: Over 30+ peer-reviewed papers in top venues like CVPR, ICCV, ICLR, and TPAMI, focusing on generative models, active learning, and medical imaging. Awards: Includes Baidu Research’s Outstanding Research Award (2020), ACM MM Travel Award (2018), and multiple scholarships from China’s Ministry of Education. Lab & Team: The ViL lab emphasizes interdisciplinary research, with current students focusing on 3D vision and generative models. Collaborations include Harvard, NTU, and industry partnerships.

Sachith SeneviratneView profile

Research Fellow

• Machine Learning
• Computer Vision
• Deep Learning
• +9 more

Dr. Sachith Seneviratne is a Research Fellow at the University of Melbourne's Melbourne School of Design, specializing in Computer Vision and Health. His research bridges Machine Learning, Urban Design, and Public Health, with a focus on Deep Learning, Contrastive Representation Learning, and Agent-Based Modelling. He holds a PhD in Machine Learning from Monash University, exploring automated parallelized machine learning models. His work has collaborations with NASA, Harvard University, and Currnt Research Hub. He is affiliated with the Transport, Health and Urban Design (THUD) research group, focusing on 'Data and Value,' 'Future Cities,' and 'Healthy Communities and Infrastructure.' His recent publications span facial deepfake detection, urban design impacts on health, and automated architecture generation using LLMs. Research interests include generative design, automated infrastructure planning, and the ethical implications of facial recognition under privacy constraints (e.g., masked faces). He has pioneered methods for collecting population-level bicycling data via smartphones/Bluetooth beacons and developed novel architectures like Arch-LLM for neural architecture generation. His work on subgrid-informed flood mapping and physics-informed neural networks demonstrates cross-disciplinary innovation. Consulting work includes machine learning projects for NASA and Harvard. His lab teams focus on creating interpretable AI systems for environmental and health applications, such as Ginn-kan for physics simulations and Ginn-lp for symbolic equation discovery. Current projects aim to quantify urban design's impact on non-communicable diseases and improve walkability through micro-scaled spatio-temporal analysis.

• Big Data Analytics
• Text Mining
• Machine Learning
• +6 more

Dr. Wei Zhang is a Senior Lecturer and Associate Head of People and Culture at the University of Adelaide's School of Computer and Mathematical Sciences, with a secondary appointment as Honorary Lecturer at Macquarie University. She holds a PhD in Computer Science from the University of Adelaide (2017) and leads research in big data analytics, text mining, machine learning, and IoT. Her work has resulted in over 100 peer-reviewed publications, including top-tier journals like ACM Computing Surveys and IEEE Communications Surveys. Dr. Zhang currently holds an ARC Early Career Industry Fellowship (IE230100119) and leads an ARC Discovery Project (DP240103070), with total funding exceeding AUD $3M from ARC, Google, and DST over five years. Her research focuses on text summarization, AIoT systems, adversarial attacks on neural networks, and medical information extraction. Professional roles include Program Coordinator, Course Coordinator, and outreach contact at her school. She actively contributes to academic governance as Associate Head of People & Culture and serves on conference committees (ACL, KDD, WWW) and journal editorial boards. Industrial collaborations span six years with roles in project leadership and technical advisory roles across multiple sectors. Dr. Zhang is a member of ACM, IEEE, and ACS, and her work has been recognized by prestigious awards such as top 100 global researchers in Network Security (SciVal). Her lab develops AI-driven solutions for IoT-enabled agriculture (e.g., mushroom cultivation monitoring) and smart construction systems, with applications in energy optimization, healthcare, and environmental monitoring.

Nyamsuren EnkhboldView profile

Lecturer

• Artificial Intelligence
• Cognitive Science
• Software Engineering
• +5 more

Dr. Nyamsuren Enkhbold is a Lecturer in Computer Science (Software Engineering) at the School of Computer Science and Information Technology, University College Cork. He holds a PhD from the University of Groningen (Cognitive Modeling), an MSc from KAIST (Computer Science), and a BSc from Huree University (Computer Science). His research focuses on intelligent software development at the intersection of AI, Cognitive Science, and GIS, with notable contributions to geo-analytical question-answering systems and EU-funded projects like RAGE (serious games) and QuAnGIS (GIS workflow automation). Current interests include GenAI applications via fine-tuning and prompt engineering. He teaches CS3062 - Computing in Society CS6403 - Case Studies in Computing Entrepreneurship and previously contributed to courses at Utrecht University and KAIST. His work has been supported by a School of Computer Science Starter Fund (€10k). Research highlights include developing reusable AI components for serious games and advancing GIS systems that automatically generate workflows from user queries. His publications span cognitive modeling, spatial semantics, and NLP-driven geo-analytical tools.

Mitch MarcusView profile

Professor

• Statistical natural language processing
• Cognitively plausible models
• Linguistic structure acquisition

Mitch Marcus is a Professor Emeritus in the Department of Computer and Information Science at the University of Pennsylvania's School of Engineering and Applied Science. He earned his Ph.D. from MIT in 1978 and joined Penn in 1987 after working at AT&T Bell Laboratories. His research focuses on statistical natural language processing and cognitively plausible models for automatic acquisition of linguistic structure. Dr. Marcus created and led the Penn Treebank Project, which revolutionized natural language parsing accuracy. He has served as PI on multiple major projects including DARPA LORELEI and GAILA AIX, focusing on unsupervised morphology acquisition and child language acquisition simulations. Awards: Fellow of American Association for Artificial Intelligence (1992) Founding Fellow of Association for Computational Linguistics (2011) Advising: His former PhD students hold positions at institutions including MIT, Johns Hopkins, Google, and Microsoft Research. Research groups: Directed the Penn Treebank Project and co-led the OntoNotes Project. Currently collaborates on natural language understanding for human-robot interaction.

Florentin WörgötterView profile

Professor

• Computational Neuroscience
• Artificial Neural Networks
• Experimental Neuroscience
• +3 more

Prof. Dr. Florentin Wörgötter is a Professor of Physics at Georg-August University Göttingen, specializing in Computational Neuroscience and Biophysics. He holds affiliations with the Bernstein Center for Computational Neuroscience and the Computational Neuroscience Group (CNS) . His career includes roles as a visiting professor at institutions like the Academia Sinica (Beijing, China) and KTH (Stockholm, Sweden), and directorships such as leading the INCITE Institute. Research focuses on computational models of neural systems, synaptic plasticity, and visual system dynamics. Active in interdisciplinary fields including brain-machine interfaces and developmental neuroscience. His work bridges experimental and theoretical approaches, with recent publications addressing dynamical systems modeling, unsupervised learning, and infant motor behavior analysis. Notably, he has contributed to frameworks for smart environment control via neural interfaces. Awards section: No specific scientific awards listed in the provided text. Advising/Grants: The text does not explicitly list advised students or grants, though his extensive collaborations suggest active mentorship and funding. Labs/Teams: Leads the CNS Group at Göttingen, affiliated with the Physics of Biological and Complex Systems (IMPRS) and Theoretical and Computational Neuroscience research clusters.

• Probabilistic Graphical Models
• Machine Learning
• Deep Generative Models
• +7 more

Thomas Dyhre Nielsen is a Professor (MSO) in the Department of Computer Science at Aalborg University . He is a member of the Distributed, Embedded and Intelligent Systems (DEIS) research group and contributes to the Artificial Intelligence and Machine Learning team at the university. His primary research interests lie in the theoretical and applied aspects of probabilistic graphical models , machine learning , and deep generative models . His work spans from foundational methods for learning and inference to the development of frameworks for solving complex decision problems. He is the co-author of the authoritative textbook Bayesian Networks and Decision Graphs . His recent research output reveals a strong trend towards interdisciplinary applications. His 15 most recent publications demonstrate significant work in bioinformatics , using graph neural networks and variational autoencoders for metagenomic binning, and in urban infrastructure , applying reinforcement learning and probabilistic models to optimize stormwater and wastewater management systems. He also has impactful research in healthcare , developing Bayesian network models for clinical risk prediction. Senior area editor for the International Journal of Approximate Reasoning . Principal or Co-Investigator on research projects such as the AMIDST project (developing a Java toolbox for scalable probabilistic machine learning) and PGM 2020 (organizing the International Conference on Probabilistic Graphical Models). Actively supervising research, as evidenced by a current opening for a PostDoc position in probabilistic machine learning. Professor Nielsen leads a research lab focused on probabilistic machine learning, which is part of the larger DEIS and AI/ML teams at Aalborg University. His group develops and applies advanced models to real-world problems in environmental science, healthcare, and intelligent systems.

Simon LeglaiveView profile

Assistant Professor

• Audio Signal Processing
• Machine Learning
• Speech Enhancement
• +7 more

Simon Leglaive is a tenured Assistant Professor at CentraleSupélec in Rennes, France, and a researcher in the AIMAC team at the IETR laboratory (CNRS UMR 6164). He holds a PhD in Audio Signal Processing from Télécom Paris (2017), and previously served as a postdoctoral researcher at Inria Grenoble Rhône-Alpes. His academic affiliations include CentraleSupélec, Télécom Paris, and CNRS, with research collaborations across institutions including Inria, GIPSA-lab, and Sorbonne University. His research focuses on the intersection of signal processing and machine learning, particularly for audio and speech applications. Key areas include probabilistic generative models, deep learning, low-dimensional representation learning, and weakly or semi-supervised learning. His work enables advanced multimodal machine perception tasks such as speech enhancement, audiovisual speech analysis, and human mesh recovery. He teaches machine learning, deep learning, and audio signal processing at CentraleSupélec. The 15 most recent publications highlight a strong trend in deep generative modeling, especially using variational autoencoders (VAEs) and masked autoencoders, for tasks like speech enhancement, source separation, emotion recognition, and human pose recovery. There is a clear emphasis on disentangled and interpretable latent representations, multimodal fusion, and unsupervised or weakly supervised methods. Applications span from speech technology to computer vision, reflecting a cross-disciplinary approach centered on fundamental representation learning. Coordinator and Principal Investigator, DEGREASE project (ANR-23-CE23-0009) Partner, DEESSE project (ANR-24-CE23-2229) Elected member, IEEE AASP Technical Committee (2023–2025) Organizing committee, CHiME-7 UDASE challenge (2023) Conference area chair, ICASSP (2024, 2025), WASPAA (2023, 2025) Simon Leglaive advises multiple PhD students and has served on the IETR laboratory council since 2022. His academic service includes extensive reviewing for top journals and conferences in signal processing and machine learning. His research is supported by competitive grants from the French National Research Agency (ANR). He is actively involved in collaborative research through the AIMAC team at IETR and partnerships with Inria and industry labs.