جستجوی استاد راهنمای دانشگاهی

Gianni Franchi is an assistant professor at ENSTA Paris , affiliated with the Computer Science and Systems Engineering Unit (U2IS) . His work focuses on theoretical deep learning , with a strong emphasis on uncertainty quantification, robustness, and explainability in machine learning models. Current affiliation: ENSTA Paris (U2IS) Academic rank: Assistant Professor Key collaborators: David Filliat, Emanuel Aldea, Andrei Bursuc, Antoine Manzanera His research spans uncertainty quantification , explainable AI , and reliable machine learning . He investigates methods like Bayesian neural networks, ensemble approaches, and deterministic uncertainty models. His work also addresses domain adaptation , self-supervised learning , and autonomous systems , particularly in trajectory forecasting and semantic segmentation for autonomous driving. Recent publications analyze probabilistic modeling for robustness, symmetry-aware Bayesian methods , and multi-modal datasets like InfraParis. He develops frameworks like Torch-Uncertainty and benchmarks such as MUAD for uncertainty types in autonomous driving. Key themes: Uncertainty Quantification Deep Learning Theory Autonomous Systems Explainable AI Dataset Creation Bayesian Methods

• Theoretical Deep Learning
• Uncertainty Quantification
• Reliable Artificial Intelligence
• +۱۰ مورد دیگر

Sylvain Faisan is a permanent Assistant Professor at ICube - MIV (University of Strasbourg, France). His research focuses on image processing, statistical modeling, and geometry, with applications in medical imaging and neuroscience. He works on advanced methodologies integrating machine learning and mathematical frameworks. Key Research Areas: Polarimetric image processing, retinal image registration, 3D statistical model comparison, topology-preserving image deformation, and fMRI brain mapping Technical Expertise: Bayesian inference, non-local means filtering, reversible jump MCMC algorithms, causal modeling, and constrained optimization His publications demonstrate interdisciplinary applications in optics, biomedical imaging, and computational anatomy. He contributes to developing algorithms that maintain physical admissibility and topological integrity in complex imaging problems.

• Image Processing
• Machine Learning
• Geometry
• +۶ مورد دیگر

Jean-Yves Marion is a Professor at the University of Lorraine and director of LORIA (Laboratoire Lorrain de Recherche en Informatique et ses Applications) since 2013. He is a Senior Member of the Institut Universitaire de France (IUF) with appointments in both 2015 and 2025. He teaches at the École Nationale Supérieure des Mines de Nancy (ENSMN) and serves as a scientific advisor for the Cyber Campus. His educational background includes a PhD in Computer Science from the University of Paris 7 (1991), followed by post-doctoral research at Indiana University (1992-1993), and Habilitation to Direct Research (2000). He served as a lecturer at the University of Nancy 2 from 1995-2002 before becoming a professor at the University of Lorraine in 2002. Marion specializes in computer security with a focus on distinguishing malicious code from ordinary software through morphological analysis techniques. His research involves extracting the internal structure of code as if giving it an 'X-ray' to identify signatures of malicious behavior. He works extensively with the High Security Laboratory which maintains a collection of 6 million computer viruses for research purposes. His publications demonstrate a consistent focus on binary code analysis, malware detection, and implicit computational complexity. His work bridges theoretical computer science concepts like Kleene's recursion theorem with practical cybersecurity applications. Senior Member of the Institut Universitaire de France (2015) Senior Member of the Institut Universitaire de France (2025) As director of LORIA, Marion leads research teams working on cybersecurity challenges. His approach to malware analysis, which examines the 'skeleton' of code rather than surface features, represents an innovative methodology in the field. He has presented his work internationally at venues including the International Symposium on Foundations & Practice of Security (FPS 2016) and the International Workshop on Logic and Computational Complexity in Kyoto.

• Computer Security
• Cybersecurity
• Malware Analysis
• +۴ مورد دیگر

Fabrice Neyret is a senior CNRS researcher in Computer Graphics and head of the MAVERICK team (formerly ARTIS- EVASION ) within the LJK laboratory at Université Grenoble Alpes and INRIA Rhône-Alpes, France. Education PhD in Computer Science, INRIA Rocquencourt, 1996 Diplôme d’Ingénieur, Télécom Paris (ENST), 1991 DESS Ingénierie Mathématique, 1989 Maîtrise d’Ingénierie Mathématique, 1988 Licence de Mathématiques, 1987 Research Interests Neyret’s work centers on Computer Graphics with a strong focus on procedural modeling , real-time rendering of natural phenomena , and GPU acceleration . He investigates volumetric textures, clouds, smoke, rivers, lava, and forests, aiming to bridge physics-based models with efficient, user-friendly methods for video production and interactive applications. Scientific Output & Trends His publications span over two decades and highlight a consistent emphasis on real-time realistic rendering of complex natural scenes. Key themes include volumetric rendering (GigaVoxels), procedural noise, GPU-friendly algorithms, and simulation of dynamic phenomena such as convective clouds, ocean waves, and lava flows. Awards & Recognition Multiple film-festival selections for scientific visualizations (e.g., Eurographics, Festival du Film Scientifique de Palaiseau, Festival international du film scientifique de Parmes) Invited seminars at MIT, University of Toronto, University of Montréal, and others Advising & Teaching Neyret has supervised more than 30 PhD and Master students since 1997, covering topics from fractal noise rendering to large-scale volumetric visualization. He teaches in the Master DEA IVR program and offers internships and postdoc positions regularly. Teams & Labs He leads the MAVERICK research team, hosted jointly by the LJK laboratory (Université Grenoble Alpes) and INRIA . The team’s infrastructure includes access to high-end GPU clusters and collaborative links with Weta Digital and other international partners.

• Computer Graphics
• Volumetric Textures
• Real-time Rendering
• +۴ مورد دیگر

BOHI Amine is a researcher at CESI (School of Engineering and Digital Tools, Department of Computer Science), with a PhD in Computer Science from the University of Toulon (2017). His academic profile spans disciplines including Machine Learning, Signal and Image Processing, and Biomedical Engineering, with a focus on applications in Digital Health and Human-Robot Interaction. Education : PhD in Computer Science (University of Toulon, 2013-2017); Master 2 in Computer Science (University of Fes, Morocco, 2009-2011); Bachelor’s in Mathematical and Computer Sciences (University of Fes, 2006-2009). His research interests include: Machine Learning and Deep Learning Signal and Image Processing 3D Shape Analysis Computer Vision Digital Health Biomimetic Feature Design BOHI’s publications reflect expertise in facial emotion recognition for elderly care, cortical folding modeling, and soft tissue organ deformation analysis using MRI. He supervises diverse research internships, mentoring students from institutions like Sorbonne Paris Nord, Université de Technologie King Mongkut, and INP Grenoble. Current projects involve developing intelligent solutions for emotional interaction with elderly individuals suffering from neurodegenerative disorders, in collaboration with VyV3 Bourgogne. He also contributes to the design of multimodal datasets and wearable health monitoring systems. BOHI’s technical work includes contributions to maritime surveillance systems (PARE project) and semantic information platforms, demonstrating a capacity to bridge theoretical research with practical applications across domains.

• Machine Learning
• Deep Learning
• Signal and Image Processing
• +۱۲ مورد دیگر

Thomas Boudier is an Associate Professor at Centrale Méditerranée with additional affiliation as Professor Associate at Sorbonne University's Institute of Biology Paris-Seine (IBPS). His research focuses on bioimage informatics, bridging computer science and biological imaging to develop advanced tools for analyzing complex biological structures. His educational background includes: PhD in Bioimage Informatics from Sorbonne University (1994-1997) Master's in Computer Vision from Nice Sophia Antipolis University (1992-1993) Undergraduate studies in Mathematics from Paris Diderot University (1990-1992) Dr. Boudier's research spans the intersection of computer science and biological imaging, with particular expertise in 3D image analysis and processing. His work has significantly contributed to developing computational methods for analyzing complex biological structures across multiple scales. He has pioneered approaches for electron microscopy image segmentation, 3D reconstruction of cellular structures, and quantitative analysis of tissue organization. His research has important applications in neuroscience, cancer biology, and regenerative medicine, where precise quantification of cellular and subcellular structures is critical. His extensive publication record demonstrates consistent innovation in bioimage analysis, with recent work focusing on deep learning applications for electron microscopy, 3D analysis of neuronal structures, and computational modeling of cardiac cells. His development of specialized software tools like TAPAS, Spot Spine, and CardioVinci has provided the research community with valuable resources for automated image analysis. Throughout his career, Dr. Boudier has maintained strong collaborations across international institutions, including work at Academia Sinica in Taiwan and The Walter and Eliza Hall Institute of Medical Research in Australia. His research laboratory is affiliated with INRIA - National Institute for Research in Digital Science and Technology, where he contributes to advancing computational methods for biological imaging.

• Image Processing
• Biomedical Imaging
• Computer Vision
• +۳ مورد دیگر

Remi Chassagne is a Research Fellow at Grenoble Alpes University, affiliated with the Laboratory of Geophysical and Industrial Flows (LEGI), a joint research unit of CNRS, Grenoble INP, and Grenoble Alpes University, where he contributes to the MEIGE team. His research focuses on: Sediment Transport mechanics using mechanistic and granular approaches Vertical grain size segregation and diffusion remixing in sediment beds Eulerian-Eulerian two-phase flow modeling (SedFoam) Bridging particle-scale phenomena to continuum models Interactions between sediment particles of different sizes Chassagne's work integrates discrete element modeling (DEM) for particle-scale dynamics with continuum modeling to address sediment transport in geophysical contexts. His research emphasizes vertical grain size segregation, infiltration dynamics of small grains in coarse beds, and the development of numerical frameworks like SedFoam for multiphase flow simulation. This mechanistic approach connects micro-scale particle interactions to macro-scale sediment transport predictions. Analysis of his publication record (2016-2024) reveals consistent focus on sediment transport mechanics, with dominant themes in granular flow behavior, size segregation processes, and computational modeling advancements. Key contributions include frictional-collisional bedload models, sediment-vegetation interactions, and bi-disperse mixture mobility. His work demonstrates strong integration of computational methods with experimental validation through LEGI's hydrodynamic facilities. As part of LEGI's MEIGE team, Chassagne utilizes the laboratory's advanced infrastructure including hydrodynamic tunnels, wave channels, and rotating platforms to investigate geophysical flows relevant to river, coastal, and industrial applications.

• Sediment Transport
• Granular Flows
• Fluid Dynamics
• +۳ مورد دیگر

Isabelle Bloch is a full Professor at Télécom Paris (Institut Polytechnique de Paris) and Emeritus Professor at the University of Bordeaux . She heads the Image, Modeling, Analysis, Geometry, Synthesis (IMAGES) research team within the Information Processing and Communication Laboratory (LTCI) in the Image, Data, Signal (IDS) Department . Education & Affiliations Professor – Télécom Paris, Institut Polytechnique de Paris (current) Professeure Émérite – University of Bordeaux (honorary) Research Interests Her work lies at the intersection of computer science, applied mathematics and medicine . Core themes include mathematical morphology , fuzzy and bipolar logics , 3-D image interpretation , discrete 3-D geometry & topology , information fusion , structural pattern recognition , spatial reasoning and medical imaging . Recent projects extend these concepts to explainable AI , argumentation theory , computational musicology and robotic surgery guidance . Scientific Awards Blondel Medal (2008) – awarded by the French Electrical & Electronics Engineering Society to outstanding young scientists. Grants & Collaborative Projects While specific grant numbers are not listed in the text, Prof. Bloch coordinates and participates in large-scale interdisciplinary projects funded by national (ANR) and European programs, spanning medical AI, pediatric oncology imaging, neuro-informatics and ethical AI. Labs & Teams She leads the IMAGES team (≈ 25 researchers) inside the LTCI – a joint research unit of Télécom Paris and CNRS. The group develops theory and open-source software in mathematical morphology, deep learning and symbolic AI, and collaborates closely with clinical partners at Necker–Enfants Malades Hospital, AP-HP and Gustave Roussy.

• Mathematical morphology
• Fuzzy set theory and bipolar fuzzy sets
• 3D image interpretation and computer vision
• +۷ مورد دیگر

Eric Barthélemy is a University Professor at Grenoble Institute of Technology (ENSE3) and has been a member of the Laboratory of Geophysical and Industrial Flows (LEGI) since 1989. His research focuses on wave dynamics , coastal physics , and hydro-sedimentary mechanisms driving coastal evolution. Research Interests Gravity wave and soliton gas dynamics Coastal morphological changes (event and long-term scales) Vorticity dynamics in surge zones Sediment transport mechanisms (sheet/plug flow) Substrate stability under non-permanent flows Publications & Research Trends : His work spans experimental (wave channels, wind tunnels), analytical, and numerical studies of shallow water wave turbulence, rip current vorticity, sediment transport in coastal zones, and soliton gas statistics. Collaborations include N. Mordant, H. Michallet, and R. Cienfuegos. Teaching : Lectures on wave mechanics , sediment transport , and free surface flows at the master's level. Labs & Teams : Works with the MEIGE team and utilizes LEGI facilities like the wave channel and variable slope channel. Technical collaborators include J.-M. Barnoud and C. Rousseau (ENSE3).

• Wave Dynamics
• Coastal Physics
• Sediment Transport
• +۳ مورد دیگر

Maria A. Zuluaga is a full-time Professor at EURECOM (Department of Data Science) and holds an affiliate faculty position as Senior Lecturer at King's College London's School of Biomedical Engineering & Imaging Sciences. She previously served as a Senior Research Associate at University College London. Her academic background includes a BSc in Electronics Engineering from Universidad del Valle, an MSc in Computer Science from Universidad de los Andes, and a PhD in Signal and Image Processing from Université de Lyon. Her research develops novel machine learning methods for healthcare applications, focusing on neurovascular imaging, cardiovascular analysis, and cancer research. Key areas include medical image segmentation, trustworthy AI deployment, multimodal learning, and time-series analysis. Her work bridges technical innovation with clinical needs to advance medical diagnostics and treatment planning. Publications demonstrate strong focus on medical imaging (85% of recent papers), particularly segmentation techniques (40%), with emerging themes in trustworthy AI (25%) and multimodal learning (20%). Vascular analysis dominates application domains (50%), followed by cancer research (30%) and neuroimaging (20%). Awards & Honors: ERC Consolidator Grant (2024) She leads research in medical AI through publications and major grants, though specific student advisees, labs, or additional grants aren't detailed in available sources.

• Machine Learning
• Medical Image Analysis
• Healthcare AI
• +۶ مورد دیگر

Guillaume Tochon is an Assistant Professor at EPITA since 2016 and an Invited Researcher at the Institut de Mécanique Céleste et de Calcul des Éphémérides (IMCCE, Observatoire de Paris) since 2022. He holds a M.Sc. and Ph.D. in electrical engineering and signal/image processing from Grenoble Institute of Technology and Université Grenoble Alpes, with postdoctoral experience at Carnegie Institution for Science and UCLA. His research focuses on mathematical morphology, statistical signal processing, and machine/deep learning, applied to space imagery (e.g., astrometry) and satellite data analysis. He leads projects on morphological neural networks, Sentinel-2 time series dynamics, and meteor/satellite detection using 1-second exposure imagery. Education: M.Sc. in Electrical Engineering, Grenoble Institute of Technology (2012) Ph.D. in Signal and Image Processing, Université Grenoble Alpes (2015) Visiting Scholar, UCLA Department of Mathematics (2013) Research Interests: Combines mathematical morphology with machine learning to address challenges in remote sensing and space imagery. Key areas include hierarchical representations, noise analysis, and applications in astrometry and hyperspectral unmixing. Current projects involve neural Koopman operators for forecasting, Sentinel-2 time-series assimilation, and meteor detection in night-sky imagery. Teaching: At EPITA, he teaches Mathematics for Signal Processing, Data Compression, Image Processing, Convex Optimization, Machine Learning, and Constrained Optimization across undergraduate and graduate levels. Collaborations: Works with researchers at IMCCE (e.g., V. Lainey, J. Vaubaillon), IMT-Atlantique, and Grenoble-INP. Supervises PhD students in topics such as noise estimation, spectral dynamics, and Cassini image analysis. Labs/Teams: Active in EPITA Research Laboratory's Image Processing and Pattern Recognition team and IMCCE's PEGASE team.

• Mathematical Morphology
• Statistical Signal Processing
• Machine Learning
• +۴ مورد دیگر

Etienne Le Quentrec is a Lecturer at the University of Strasbourg, affiliated with the ICube laboratory and the IMAGeS team (Images, Modeling, Learning, Geometry and Statistics). His academic focus spans discrete geometry, mathematical morphology, and image processing. Education: License in Mathematics (Strasbourg, 2014), External Aggregation in Mathematics (Strasbourg, 2016), Master 2 Research and Innovation (Toulouse, 2017), Master 2 MAPI3 (Toulouse, 2018) Research: Thesis on geometric characteristic estimation from image discretization, with applications in topology preservation and error modeling Teaching: Prolog, Python, Algorithms, Data Structures, Applied Numerical Analysis (2018-2021) He actively participates in scientific events including the Discrete Geometry and Mathematical Morphology conferences (2019, 2021) and co-founded the Association of Young Researchers of ICube (AJCI).

• Discrete Geometry
• Mathematical Morphology
• Image Processing
• +۳ مورد دیگر

Jing-Rebecca Li is a Professor and Research Scientist at ENSTA Paris, affiliated with the Applied Mathematics Unit (UMA) and INRIA Saclay as part of the IDEFIX research team. Her work bridges advanced mathematical techniques with medical imaging applications, particularly in diffusion MRI. She maintains a dual affiliation between ENSTA Paris, a leading engineering school in France, and INRIA, the French national research institute for digital science and technology. HDR (Habilitation à Diriger des Recherches) in Mathematics, Université Paris-Sud, 2013 Ph.D. in Mathematics, Massachusetts Institute of Technology, 2000 B.Sc. in Mathematics, University of Michigan, 1995 Dr. Li's research focuses on developing sophisticated numerical methods to solve partial differential equations with applications in diffusion magnetic resonance imaging. Her work spans brain and cardiac imaging, numerical linear algebra, machine learning algorithms for inverse problems in PDEs, and natural language processing tools. She has pioneered approaches to simulate diffusion MRI signals in complex biological tissues, enabling more accurate interpretation of imaging data for neuroscience and cardiology applications. Her research has significant implications for understanding brain microstructure and cardiac tissue organization through non-invasive imaging techniques. Her recent publications demonstrate a clear trend toward increasingly sophisticated modeling of biological tissues, with growing emphasis on cardiac applications alongside her foundational work in brain imaging. She has developed robust computational frameworks that incorporate permeable interfaces, geometrical deformations, and realistic neuronal geometries to better simulate diffusion MRI signals. Her work increasingly integrates machine learning with traditional numerical methods, creating hybrid approaches that leverage the strengths of both paradigms for microstructure estimation. Householder Prize for the best dissertation in Numerical Algebra (2002) Dr. Li has supervised numerous doctoral students across multiple institutions, with a focus on computational methods for diffusion MRI. Her current research is supported by significant grants including the Engineering for Health (E4H) interdisciplinary center project investigating biomarkers for Multiple Sclerosis through diffusion MRI (2023-2025). Previously, she led the ANR-funded SIMUDMRI project (2010-2014) and participated in the US-French Collaboration project on Computational Imaging of the Aging Cerebral Microvasculature (2013-2016). Her work demonstrates strong interdisciplinary collaboration between mathematics, computer science, and medical imaging communities. As leader of the IDEFIX research team at INRIA Saclay, Dr. Li directs a group focused on inversion methods for differential equations applied to imaging and physics problems. Her team has developed the SpinDoctor software package, a widely used MATLAB toolbox for diffusion MRI simulation that has become a standard tool in the field. The team maintains strong collaborations with Neurospin (CEA) and international research groups working on advancing diffusion MRI methodology and applications.

• Diffusion Magnetic Resonance Imaging
• Numerical Methods for Partial Differential Equations
• Numerical Linear Algebra
• +۴ مورد دیگر

Joëlle Barido-Sottani is a postdoctoral researcher at École Normale Supérieure (ENS), focusing on developing mathematical models to study diversification processes using phylogenetic analysis. Her research integrates birth-death processes, Bayesian inference, and fossil data to understand evolutionary dynamics. She contributes to software frameworks like BEAST2 and RevBayes , enhancing tools for phylogenetic analysis and phylodynamic studies. Her work bridges evolutionary biology and computational methods, emphasizing methodological advancements in fossil integration and model development. Her research interests include phylogenetic modeling , Bayesian statistical methods , and the application of these techniques to study diversification patterns across species. She has developed computational tools such as FossilSimShiny and EvoPhylo , which facilitate simulations and data preprocessing in evolutionary studies. Her recent work highlights the importance of integrating fossil records with modern species data to improve estimates of historical diversification rates. Over the past few years, her publications have focused on enhancing phylogenetic inference through methodological innovations. For example, her work on the Multi-Type Fossilized Birth-Death model (2025) addresses heterogeneous diversification rates, while her guidelines for MCMC-based Bayesian inference (2024) provide practical frameworks for researchers. She has also contributed to epidemiological applications of phylogenetic models, extending their utility beyond traditional evolutionary studies. Barido-Sottani’s collaborations emphasize open-source software development, enabling broader accessibility to advanced phylogenetic tools. Her teaching efforts, such as organizing virtual workshops like Taming the BEAST , reflect her commitment to advancing computational training in evolutionary biology.

• Phylogenetics
• Bayesian Inference
• Diversification Models
• +۳ مورد دیگر

Edwin Carlinet is an Assistant Professor at EPITA Research Laboratory (LRE), specializing in mathematical morphology, hierarchical image representations, and high-performance computing. His research develops efficient algorithms for image processing with applications in document analysis and historical map vectorization. Key projects include the SoDuCo initiative extracting data from 19th-century Parisian trade directories and parallel implementations of morphology algorithms. He leads development of the Pylene image processing library, focusing on generic and efficient implementations. Teaching covers parallel programming, data compression, C++, and GPU programming at EPITA, alongside bioinformatics courses at Sup'Biotech. Research supervision includes PhD candidates working on modern implementations of mathematical morphology algorithms and noise estimation techniques. Recent publications focus on optimizing computational workflows for historical document processing, including noise impact analysis on morphological structures and GPU acceleration of max-tree computation.

• Mathematical Morphology
• Image Processing
• High Performance Computing
• +۱ مورد دیگر