Find Academic Supervisors

Jens BehleyView profile

Lecturer

• Robotics
• Computer Vision
• 3D Perception
• +4 more

Jens Behley is a Lecturer (Privatdozent) at the Institute of Geodesy and Geoinformation, University of Bonn, where he actively teaches graduate courses in robotics and computer vision while leading cutting-edge research in 3D perception. His work bridges theoretical advances with real-world agricultural and automotive applications, focusing on robust algorithms for unstructured environments. Behley's research centers on 3D point cloud processing, semantic segmentation, and SLAM systems, with specialized expertise in agricultural robotics for crop phenotyping and autonomous vehicle navigation. He develops novel techniques for plant organ-level analysis, fruit shape completion, and radar-based localization, emphasizing solutions that function under real-field conditions with sensor noise and dynamic changes. His methodologies frequently integrate deep learning with geometric computer vision to achieve precision in challenging outdoor settings. Analysis of his recent publications reveals a dominant trend toward neural implicit representations (e.g., Gaussian Splatting) and diffusion models for 3D scene understanding, alongside continued innovation in LiDAR processing for agricultural robotics. Key thematic clusters include plant phenotyping (18% of recent work), neural mapping techniques (24%), and robust sensor fusion for autonomous systems (31%), with growing emphasis on generative models for data synthesis. Scientific Awards Outstanding Reviewer at IEEE Robotics and Automation Letters (RA-L), 2024 Outstanding Reviewer at European Conference on Computer Vision (ECCV), 2024 Best Agri-Robotics Paper Award for “BonnBeetClouds3D...” at IROS, 2024 Best Paper Award in Workshop “Agricultural Robotics for Sustainable Futures” at IROS, 2024 Best Paper Award Second Place in Workshop “AI and Robotics For Future Farming” at IROS, 2024 Outstanding Reviewer at CVPR, 2024 Finalist Best Paper Award in Service Robotics at ICRA, 2024 Best Paper for “KISS-ICP...” by RA-L, 2023 Honorable Mention for “High Precision Leaf Instance Segmentation...” by RA-L, 2023 Outstanding Reviewer at CVPR, 2023 Outstanding Reviewer at ECCV, 2022 Finalist IROS Best Paper Award on Agri-Robotics, 2022 Outstanding Reviewer at RA-L, 2022 Outstanding Reviewer at ICRA, 2022 Outstanding Reviewer at ICCV, 2021 Faculty Award for Geodesy from Agricultural Faculty of University of Bonn, 2021 Outstanding Reviewer at CVPR, 2021 Finalist Best System Paper at RSS, 2020 Diplomarbeitspreis der Bonner Informatik Gesellschaft e.V., 2009 Behley actively mentors students through advanced coursework including “Machine Learning for Robotics and Computer Vision” and “Techniques for Self-Driving Cars,” though specific advisees aren't documented. His research is supported by extensive collaborations with Prof. Cyrill Stachniss's robotics group at Bonn, with publications appearing in top venues like RA-L, ICRA, and CVPR. Current projects focus on neural scene representations for agricultural robotics and robust localization in changing environments, with datasets like BonnBeetClouds3D establishing new benchmarks in plant phenotyping.

Jan E. GerkenView profile

Assistant Professor

• Geometric Deep Learning
• Equivariant Neural Networks
• Neural Tangent Kernels
• +6 more

Jan E. Gerken is an Assistant Professor leading a research group focused on the mathematical foundations of artificial intelligence, supported by the Wallenberg AI, Autonomous Systems and Software Program. His work bridges theoretical physics and machine learning, with a PhD in string theory where he computed genus-one scattering amplitudes. Currently, he investigates wide neural networks, neural tangent kernels, and their connections to quantum field theory, alongside mathematical aspects of geometric deep learning and spherical computer vision. His research spans equivariant neural networks , geometric deep learning , neural tangent kernels , and topological physics applications . Recent publications demonstrate emergent equivariance in deep ensembles, gauge-equivariant models for Chern number prediction, and HEALPix-based transformers for spherical data. Key collaborations include work on modular graph forms in string theory and diffeomorphic counterfactuals for explainable AI. Articles highlight trends in symmetry-driven architectures , spherical data processing , and theoretical physics-motivated deep learning . Gerken’s contributions include open-source implementations like HEAL-SWIN and theoretical frameworks for equivariant training dynamics. His work addresses both foundational mathematical questions and practical applications in medical imaging, autonomous systems, and climate modeling.

Zuzana KukelovaView profile

Assistant Professor

• Minimal problems in computer vision
• Algebraic geometry
• Camera geometry problems
• +5 more

Zuzana Kukelova is an Assistant Professor and Researcher in the Department of Cybernetics at the Faculty of Electrical Engineering, Czech Technical University in Prague. She leads research in minimal problems for computer vision with applications in camera geometry and distortion modeling. Education: PhD in Mathematical Engineering (Computer Vision), Czech Technical University, Prague (2006-2013) Master Degree (Mgr.) in Computer Science, Comenius University, Bratislava (2000-2005) Rigorous thesis (RNDr.) in Mathematics - Computer Graphics and Geometry Her research focuses on minimal problems in computer vision , specializing in algebraic geometry approaches to solve camera geometry problems. She develops methods for solving systems of polynomial equations using Gröbner basis techniques, with particular expertise in radial distortion calibration and rolling shutter camera models. Her work bridges theoretical mathematics with practical computer vision applications, enabling robust solutions to challenging geometric vision problems. Analysis of her 15 most recent publications reveals dominant trends in minimal solvers for camera geometry (80% of works), with heavy emphasis on radial distortion (65%) and rolling shutter models (45%). Key subfields include polynomial equation solving (100%), camera pose estimation (75%), and homography estimation (40%). Her research consistently demonstrates mathematical innovation applied to real-world vision challenges. Scientific Awards: Saburo Tsuji Best Paper Award (ACCV 2018) Cor Baayen Award (2015) from ERCIM ACCV 2014 Best Paper Honourable Mention CSKI prize for best PhD dissertation (2013) IEEE TPAMI Spotlight paper (2012) As a principal investigator in the Visual Recognition Group, she has secured significant research funding through competitive grants. Her leadership includes co-organizing major conferences (ICCV 2021 Tutorial, CVPR 2019 Tutorial) and serving as Program Chair for 3DV 2020. She maintains active collaborations with leading vision researchers across Europe and North America, evidenced by her extensive publication record in top-tier venues.

Björn OmmerView profile

Professor

• Computer Vision
• Machine Learning
• Deep Learning
• +7 more

Björn Ommer is a full Professor at Ludwig Maximilian University of Munich (LMU) where he heads the Computer Vision & Learning Group. Previously, he was a full professor at Heidelberg University and served as a director of the Interdisciplinary Center for Scientific Computing (IWR) and the Heidelberg Collaboratory for Image Processing (HCI). He is affiliated with multiple prestigious institutions including the Bavarian AI Council, ELLIS unit Munich, the Helmholtz Foundation, and the Munich Center for Machine Learning (MCML). Dr. Ommer received his PhD from ETH Zurich where he was awarded the ETH Medal for his dissertation 'Learning the Compositional Nature of Objects for Visual Recognition.' After completing his doctoral studies, he held a post-doctoral position in the Computer Vision Group of Jitendra Malik at UC Berkeley. His primary research interests span all aspects of semantic image and video understanding based on deep machine learning, with particular emphasis on generative approaches for visual synthesis (including Stable Diffusion), invertible deep models for explainable AI, deep metric and representation learning, and self-supervised learning paradigms. His work has significant interdisciplinary applications in digital humanities and neurosciences. His extensive publication record demonstrates a clear progression toward increasingly sophisticated generative models, culminating in the development of Stable Diffusion. His recent work focuses on improving diffusion models, exploring flow matching techniques, and developing more controllable generative systems with applications across multiple domains. German AI-Prize 2024 Technology-Prize of Eduard-Rhein-Foundation 2024 Nominated for German Future Prize of the President of Germany ELLIS Fellow ETH Medal for Dissertation Best Paper Award at CVPR'21 AI for Content Creation Workshop Professor Ommer serves as an associate editor for IEEE T-PAMI and has held significant leadership roles in major computer vision conferences including program chair for GCPR and Senior/Area Chair for CVPR, ICCV, ECCV, and NeurIPS. He delivered the opening keynote at NeurIPS'23 and has supervised numerous PhD students who have gone on to positions at leading technology companies including Amazon, Facebook, and Apple. His research group is located in downtown Munich and actively recruits talented students and researchers for cutting-edge work in computer vision and machine learning.

• Tissue Engineering
• Biofabrication
• Computer Vision
• +3 more

Dr. Hao Liu is a Researcher in the Department of Tissue Technology and Biofabrication at ETH Zurich's Institute for Biomechanics. His work intersects tissue engineering, biofabrication, and advanced computational techniques such as computer vision and 3D reconstruction. He focuses on interdisciplinary applications, including robotics and neural radiance fields (NeRF) for biomedical and robotic systems. Institution: ETH Zurich Role: Researcher (Staff of Professorship for Tissue Engineering and Biofabrication) Research interests span tissue engineering, biofabrication, and computational methods like 3D reconstruction, visual localization, and neural networks. His recent work emphasizes robust 3D scene understanding, camera pose estimation, and deep learning for multi-view stereo. Publications highlight advancements in relative pose estimation, neural radiance fields, and line-based geometric analysis, contributing to both robotics and biomedical engineering fields. He has no listed scientific awards, but his research demonstrates significant innovation in computational imaging and biofabrication. No advising or grant details are provided in the available texts. His affiliation with the Institute for Biomechanics suggests involvement in labs focused on biomechanical systems and biofabrication technologies.

• Pattern Recognition
• Applied Machine Learning
• Document Analysis
• +7 more

Fischer Andreas is a Professor at HES-SO (University of Applied Sciences and Arts Western Switzerland) , specifically affiliated with the School of Engineering and Architecture of Fribourg (HEIA-FR) . His research spans Pattern Recognition , Applied Machine Learning , Handwriting Recognition , and Graph-based Methods . He has secured significant grants from TAINA Technology , Swisscom , and the Hasler Foundation for projects including automatic handwriting recognition for tax forms , Swiss German translation , and graph-based keyword spotting in Vietnamese steles . Education : BSc in Computer Science from HEIA-FR. Research Highlights : Graph Neural Networks for Büchi automata classification Annotation-free alignment in historical documents Graph edit distance optimization for keyword spotting Hybrid deep learning for Vietnamese stele analysis Graph-based tumor budding analysis in digital pathology Collaborative Impact : Fischer's work bridges historical document analysis and medical imaging , demonstrated through frameworks like DIVA-DAF and tools like GammaFocus for histopathology. His 2024 conferences suggest ongoing exploration of LLM integration in document processing and OCR-free models for information extraction.

Benjamin GreweView profile

Associate Professor

• Artificial Intelligence
• Neural Networks
• Neuroscience
• +3 more

Prof. Dr. Benjamin Grewe is an Associate Professor at the Department of Information Technology and Electrical Engineering at ETH Zürich. His research focuses on the intersection of artificial intelligence, neuroscience, and neural networks, with a particular emphasis on cortical hierarchies, continual learning, and biologically plausible algorithms. He leads projects involving deep feedback control, synaptic connectivity analysis, and neural ensemble dynamics. Grewe teaches courses such as Learning in Deep Artificial and Biological Neuronal Networks and Reinforcement Learning Basics , integrating theoretical and applied perspectives. His work bridges computational models with biological insights, contributing to advancements in medical robotics, process control, and AI safety. His research interests span neural network architectures , continual learning , and biological neuronal systems . Recent projects explore synaptic plasticity in cortical microcircuits and the application of AI to surgical planning and industrial automation. Grewe’s publications reflect a multidisciplinary approach, addressing challenges in both technical and biological domains. No scientific awards are explicitly mentioned in the provided texts. His advising and grant activities remain unspecified in the available data. His lab, part of the Neural and Intelligent Systems group, focuses on developing biologically inspired algorithms and neural interfaces.

• Reservoir Computing
• Machine Learning
• Neural Networks
• +4 more

Lyudmila Grigoryeva is a Professor at the University of St. Gallen. Her research focuses on reservoir computing, machine learning, and nonlinear dynamical systems. She has contributed to advancing theoretical frameworks for recurrent neural networks, including memory capacity analysis, approximation bounds, and time-series forecasting. Key collaborations include work with Juan-Pablo Ortega Lahuerta and Lukas Gonon on reservoir systems and stochastic processes. Research Themes: Infinite-dimensional reservoirs, geometric invariant learning, and parallel-in-time solvers. Applications: Macroeconomic forecasting, chaotic attractor learning, and PDE solving. Her recent work addresses foundational questions in reservoir computing, such as memory capacity evaluation and universal approximation properties. She has also explored interdisciplinary applications in econometrics and computational neuroscience.

• Neuroscience
• MRI
• Brain Imaging
• +6 more

Benedetta Franceschiello is an Associate Professor at HES-SO Valais-Wallis, part of the School of Engineering (Haute Ecole d'Ingénierie) in Sion, Switzerland. She holds a position in the Department of Information Technology and Engineering, teaching linear algebra courses across multiple bachelor programs including Industrial Systems, Biomedical Engineering, and Environmental Engineering. Her research focuses on computational neuroscience, mathematical modeling of visual perception, and medical imaging techniques like MRI and EEG. Key interests include geometric optical illusions, neural dynamics, and the application of advanced mathematical methods to neuroimaging challenges. She has developed models linking cortical processes to perceptual phenomena, integrating psychophysics with computational neuroscience. Franceschiello's work addresses topics such as MRI signal reliability in brain network analysis, optimization techniques for medical image reconstruction (e.g., LASSO algorithms), and the use of machine learning for analyzing eye-tracking data in neurological disorders like spatial neglect. She has contributed to conferences including ISMRM, ARVO, and OHBM, and her research spans interdisciplinary areas combining mathematics, engineering, and neuroscience. Her recent studies emphasize the synergistic effects of physical stimulus properties in generating visual illusions and the development of automated 3D eye segmentation methods using MRI. Franceschiello's contributions bridge theoretical models with clinical applications, aiming to improve diagnostic tools and neuroimaging standards.

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

Elias Abad Rocamora is a Researcher and Doctoral Assistant at the École Polytechnique Fédérale de Lausanne (EPFL), affiliated with the Laboratory for Information and Inference Systems (LIONS) under the Institute of Electrical Engineering (IEM) within the School of Engineering (STI) . He is concurrently pursuing a Doctoral Program in Electrical Engineering through EPFL's Doctoral School of Engineering (EDoc-EDEE). His research focuses on adversarial machine learning, robustness certification, and efficient neural network architectures. Key areas include adversarial attacks against vision-language models, certified defenses under bounded perturbations, and regularization techniques to prevent catastrophic overfitting. His work also extends to 3D pointcloud processing using graph-based methods and formal verification of polynomial networks. Rocamora has contributed to cutting-edge research in AI safety, language model security, and geometric deep learning. His recent work emphasizes dual-domain robustness in multimodal models and efficient single-pass detection mechanisms for LLM jailbreaking inputs. Articles span cybersecurity applications, optimization strategies, and foundational aspects of model robustness. No scientific awards are currently listed. He collaborates actively within the LIONS lab, focusing on interdisciplinary projects at the intersection of electrical engineering and computer science.

Michael BronsteinView profile

Professor

• Geometric Deep Learning
• Machine Learning
• Pattern Recognition
• +6 more

Michael Bronstein is a Professor at Imperial College London, holding the Chair in Machine Learning and Pattern Recognition. He also serves as Head of Graph Learning Research at Twitter and leads ML research in Project CETI, a TED Audacious Prize-winning collaboration focused on understanding sperm whale communication. Professor Bronstein's research centers on Geometric Deep Learning , which aims to provide a unifying mathematical framework for neural network architectures like CNNs, RNNs, GNNs, and Transformers. His work spans multiple domains including: Computer vision Social science Biology Drug design Protein folding His groundbreaking research has led to applications in diverse fields, from understanding complex biological structures to developing new drug discovery methodologies. Bronstein approaches geometry in deep learning following the spirit of Felix Klein's Erlangen Programme, seeking unifying principles across disparate neural network architectures. Professor Bronstein has received numerous prestigious awards and honors: Royal Society Wolfson Research Merit Award Royal Academy of Engineering Silver Medal Five ERC grants Two Google Faculty Research Awards Two Amazon AWS ML Research Awards Member of the Academia Europaea Fellow of IEEE, IAPR, BCS, and ELLIS ACM Distinguished Speaker World Economic Forum Young Scientist Beyond academia, Bronstein is a serial entrepreneur who has founded multiple successful startups: Novafora Invision (acquired by Intel in 2012) Videocites Fabula AI (acquired by Twitter in 2019) He previously served as Principal Engineer at Intel Perceptual Computing and was a key developer of the Intel RealSense technology.

Johannes Josef SchneiderView profile

Researcher

• Applied Complex Systems Science
• Artificial Chemistry
• Microfluidics
• +3 more

Dr. Johannes Josef Schneider is a Researcher at the Zurich University of Applied Sciences (ZHAW) School of Engineering, affiliated with the Applied Complex Systems Science research group. His work focuses on computational modeling of complex systems, particularly artificial chemistry and microfluidic droplet networks. Research interests span: Artificial chemistry implementation in droplet-based systems Geometric constraints in particle agglomeration 3D arrangement of droplets and vesicles Computational methods for pandemic intervention modeling Network formation in polydisperse systems Schneider has contributed to several key projects including Bio-HhOST (as Deputy Project Leader) and SARS-CoV-2 intervention modeling. His collaborative research involves extensive work on chemical programmability using droplet agglomerations and ethical aspects of computational modeling. Research outputs demonstrate consistent focus on: Development of computational frameworks for chemical synthesis Analysis of droplet dynamics in constrained geometries Modeling of spatial population dynamics Investigation of vesicular interactions

Corentin DumeryView profile

Researcher

• Computer Vision
• Computer Graphics
• 3D Reconstruction
• +4 more

Corentin Dumery is a Doctoral Assistant at École Polytechnique Fédérale de Lausanne (EPFL) , affiliated with the Computer Vision Laboratory (CVLAB) and Machine Learning and Optimization Laboratory (MLO) within the School of Computer and Communication Sciences . His research bridges Computer Vision and Computer Graphics , focusing on 3D scene reconstruction, garment modeling, and neural rendering techniques. Previously, he interned at Meta Redmond , worked at CEA Paris-Saclay on polycube mapping, and was a visiting researcher at ETH Zurich under Prof. Olga Sorkine-Hornung . Corentin holds dual MSc degrees in Computer Science from National University of Singapore (NUS) and Télécom Paris . His work emphasizes 3D content creation for AR/VR Diffusion models for garment reconstruction Neural radiance field optimization Polycube mapping for hexahedral meshing His recent publications (2022–2025) span top venues like SIGGRAPH , ICCV , and CVPR , addressing challenges in 3D Gaussian splatting, view-consistent NeRF training, and single-view garment recovery. He also contributes to academic service as an Outstanding Reviewer at CVPR25 and co-organizes workshops like OpenSUN3D . At EPFL, he serves as Head Teaching Assistant for courses CS433 Machine Learning (2023–2024) and CS442 Computer Vision (2023–2024). Additionally, he is the VP/Treasurer of EPIC , EPFL's computer science PhD association.

• Robotic Manipulation
• Control Theory
• Differential Geometry
• +5 more

Fares J. Abu-Dakka is an Assistant Professor in the Mechanical Engineering Program at New York University Abu Dhabi, where he joined in September 2024. Previously, he served as a Lecturer and Researcher in the Faculty of Engineering - Electronic and Informatic Department at Mondragon Unibertsitatea (2023-2024) and as a Senior Scientist and Leader for the Robot Learning Group at the Munich Institute of Robotics and Machine Intelligence, Technische Universität München (2022-2023). His research focuses on advancing robotic manipulation through the integration of control theory, differential geometry, and machine learning, with particular emphasis on enhancing robotic systems' performance, adaptability, and safety. Dr. Abu-Dakka explores how advanced mathematical frameworks and intelligent algorithms can empower robots to interact more effectively with complex environments, with applications spanning industrial automation, prosthetics, and human-robot collaboration. His recent publications demonstrate expertise in geometry-aware motion planning, variable impedance control, safe execution of robotic skills, and human-robot skill benchmarking. He has organized multiple workshops at major robotics conferences including IROS and ECC, focusing on formal methods in robotics systems, certified control synthesis, and variable impedance learning and control. IEEE Senior Member (2024) Member of the ELLIS Society e.V (2024) Dr. Abu-Dakka actively contributes to the robotics community through workshop organization and collaborative research, with recent work examining AI-driven intent detection, neural interfaces, sensory feedback systems for prosthetics, and certified control synthesis with rigorous safety guarantees. His research bridges theoretical control methods with practical robotic applications, emphasizing mathematical rigor while addressing real-world implementation challenges.

Federica ArrigoniView profile

Associate Professor

• 3D Computer Vision
• Geometric Synchronization
• Motion Segmentation
• +5 more

Federica Arrigoni is an Associate Professor at the Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano (Italy). She holds an MS in Mathematics (2013, University of Milan) and a PhD in Industrial and Information Engineering (2018, University of Udine), where her thesis won awards from CVPL and the University of Udine. Her career spans Junior Researcher at Czech Technical University in Prague (2018-2020), Assistant Professor (RTD-A) at University of Trento (2020-2022), and Tenure-Track Assistant Professor (RTD-B) at Politecnico di Milano (2022-2024). Research Interests focus on geometric problems in 3D Computer Vision, including: Viewing graph solvability via cycle consistency Quantum motion segmentation Rotation synchronization Multi-model fitting Recent publications highlight synchronization algorithms, quantum computing applications, and geometric consistency in computer vision. She was honored with Best Paper Finalist at ICCV 2023 and Best Paper Honorable Mention at ICCV 2021. As Associate Editor for CVIU and reviewer for major conferences (CVPR, ECCV, ICCV), she contributes actively to the academic community. Scientific Recognition : Best Thesis Award, CVPL (2018) Best Thesis Award, University of Udine (2019) Best Paper Honorable Mention, ICCV 2021 Best Paper Finalist, ICCV 2023 Outstanding Reviewer, CVPR 2021