Freddy Bouchet is a Directeur de Recherche at CNRS and a Professeur attaché at École Normale Supérieure de Paris (ENS-PSL). His work bridges mathematical physics, climate science, data science, and statistical mechanics , focusing on turbulent flows, climate extremes, and large deviation theory . He will lead the Laboratoire de Météorologie Dynamique (LMD) starting 2025. Research Themes : Statistical mechanics of geophysical flows (Jupiter's jets, ocean currents). Large deviation theory for rare events in turbulence and climate. Non-equilibrium phase transitions in atmospheric/oceanic systems. Ensemble inequivalence in systems with long-range interactions. Scientific Awards : Three Physicists Prize Collaborations : Tapio Schneider, Antoine Venaille, J. Laurie, O. Zaboronski, B. Dubrulle, A. Venaille. Labs & Teams : Climate and Statistical Mechanics group at ENS de Lyon Future director of Laboratoire de Météorologie Dynamique (LMD/IPSL) Publications span climate dynamics, turbulence, statistical mechanics, and large deviation theory , with applications to Jupiter's atmosphere, ocean vortices, and non-equilibrium systems . His work often challenges paradigms like Tsallis non-extensive statistics.
Grégoire Allaire is a Professor of Applied Mathematics at École Polytechnique, where he leads research in shape optimization , homogenization , and multi-scale modeling . His work bridges theoretical and applied domains, focusing on partial differential equations (PDEs), composite materials, and computational methods.
Yvain Bruned is a Professor of Mathematics at Université de Lorraine, Nancy, France, where he leads research in singular stochastic partial differential equations and related fields. He serves as Principal Investigator for the ERC Starting Grant LoRDeT (2023-2028), which focuses on advancing the theory of decorated trees and Hopf algebraic structures for solving singular SPDEs and dispersive PDEs at low regularity. Previously, he was a Lecturer at the University of Edinburgh (2019-2022) and completed postdoctoral work at Imperial College London and University of Warwick under Martin Hairer. His educational background includes: PhD in Mathematics (2012-2015), UPMC (Paris 6), on "Singular KPZ type equations" under Lorenzo Zambotti Master 2 in Probability and Statistics, ENS Cachan / Rennes 1, with honors Master 1 in Mathematics, ENS Cachan, with honors Bachelor in Mathematics and Computer Science, University of Rennes 1, with honors Student at ENS Cachan Brittany extension (2009-2013) Classes Préparatoires in Mathematics and Physics (2007-2009) Bruned's research centers on singular stochastic partial differential equations, with particular focus on Regularity Structures, renormalization theory, and their connections to Hopf algebras. His work bridges theoretical mathematics with applications in quantum field theory, wave turbulence, and numerical analysis. He has developed novel approaches using decorated trees to handle renormalization procedures for singular SPDEs and has extended these methods to dispersive PDEs with random initial data. His research program aims to establish existence and uniqueness results for quasilinear and dispersive SPDEs while developing algebraic tools through deformations of Hopf algebras. His extensive publication record demonstrates consistent contributions to the field of singular SPDEs, with a clear trajectory from foundational work on Regularity Structures to more recent applications in dispersive PDEs and numerical methods. The publications reveal a strong collaborative network with leading researchers in stochastic analysis, mathematical physics, and algebra. His work shows increasing sophistication in handling renormalization procedures through algebraic structures, with recent papers exploring connections between different mathematical frameworks. His major scientific recognition includes: ERC Starting Grant LoRDeT (2023-2028) Bruned actively supervises a large group of researchers, currently advising 4 PhD students and 2 postdoctoral researchers at Université de Lorraine, with several former PhD students having completed their degrees at the University of Edinburgh. His ERC grant has enabled him to organize multiple international workshops in Nancy, fostering collaboration between researchers in singular SPDEs, algebraic structures, and numerical analysis. The grant also supports the development of software platforms for decorated trees and their Hopf algebraic structures. As Principal Investigator of the ERC LoRDeT project, Bruned leads a vibrant research team based at the Elie Cartan Institute of Lorraine, which includes postdocs, PhD students, and visiting researchers. The team regularly organizes specialized workshops on topics including operads, symmetries for quantum field theory, and normal forms for singular dynamics, creating a dynamic research environment that bridges multiple mathematical disciplines.
Pierre Marion is a Researcher at INRIA Paris, working within the Sierra research team since September 2025. His work focuses on the theoretical foundations of deep learning and he is beginning to explore applications of AI in mathematics. Marion has established collaborations across multiple institutions including EPFL, Sorbonne Université, and Google DeepMind. His educational background includes: Engineering degree from École polytechnique (2015-2018) with specialization in Applied Mathematics Master's degree from Sorbonne Université (2019-2020) PhD from Sorbonne Université (2020-2023) under the supervision of Gérard Biau and Jean-Philippe Vert Postdoctoral research at EPFL (2024) supervised by Lénaïc Chizat Marion's research interests primarily focus on the theory of deep learning, where he investigates the optimization and statistical properties of various neural network architectures. His work spans from shallow networks to complex generative models, with a particular emphasis on understanding the mathematical foundations that govern deep learning performance. Recently, he has begun exploring applications of AI in mathematical research, aiming to bridge the gap between theoretical machine learning and mathematical discovery. His research often combines rigorous theoretical analysis with practical implications for training deep neural networks. Analysis of Marion's recent publications reveals several key trends in his research. He has made significant contributions to understanding the role of large learning rates in optimization dynamics, demonstrating how they can accelerate convergence in logistic regression and prevent memorization in score-based generative models. His work on attention mechanisms has provided theoretical guarantees for their effectiveness in specific tasks like single-location regression and clustering. Additionally, Marion has extensively studied the connections between residual networks and neural ordinary differential equations , establishing generalization bounds and exploring scaling properties in the large-depth regime. His earlier work included contributions to natural language processing and quasi-Monte Carlo methods, reflecting a broad mathematical foundation that informs his current deep learning research. Marion has received several notable scientific awards: Runner-up PhD Award of AFIA (French Association for Artificial Intelligence) in 2024 Google PhD Fellowship in 2022 Ecole polytechnique Grand Prize of Research Internships in 2018 As an advisor, Marion currently supervises PhD student Yu-Han Wu (since 2024), with whom he has co-authored multiple publications on large learning rates and denoising score matching. Previously, he co-supervised several Master's students including Seorim Park, Yerkin Yesbay, and Nathan Doumèche. Marion has been actively involved in the machine learning community through conference organization (NeurIPS@Paris meetups), session chairing (ICSDS 2022), and extensive reviewing activities. He has served as a reviewer for top journals including JASA and Annals of Statistics, and conferences including NeurIPS and ICLR, where he was recognized as a top reviewer at NeurIPS 2023. Marion is a member of the Sierra research team at INRIA Paris, which focuses on machine learning theory and applications. He has also collaborated with researchers at CREST (Center for Research in Economics and Statistics), as evidenced by his participation in seminars organized by Anna Korba and Karim Lounici. His work often bridges theoretical computer science, statistics, and applied mathematics, reflecting the interdisciplinary nature of modern machine learning research.
Houman BOROUCHAKI is a Professor at the University of Technology of Troyes (UTT), France, with over 20 years of academic leadership. He has served as Head of the Automatic Mesh Generation and Advanced Methods (GAMMA3) project team since 2008 and previously led the Laboratory of Mechanical Systems and Concurrent Engineering (LASMIS) (2005-2007). His work bridges academic research and industrial applications through collaborations with INRIA , French Petroleum Institute (IFPEN) , Dassault Aviation , and others. Research Interests: A pioneer in adaptive meshing , he focuses on finite element methods , geometric modeling , and numerical simulations . His innovations underpin mesh generation algorithms , 3D triangulation software , and industrial applications in metal forming, composite simulation, and subterranean modeling. Scientific Trends: His recent work emphasizes metric-based meshing , high-order geometric validity , and parallel processing for mesh generation , with applications in petroleum reservoirs, aviation surfaces, and nanomaterials. His Google Scholar profile reflects 25+ years of contributions to meshing and simulation. Teaching: With 22 years of experience, he teaches courses on meshing , numerical analysis , geometric modeling , and computer graphics at UTT, covering undergraduate to PhD levels. Labs & Teams: He leads the interdisciplinary GAMMA3 team and has contributed to LASMIS (mechanical engineering), L2n (CNRS-UMR 7076) (nanomaterials), and LIST3N (computer science).
Rémi Giraud is an Associate Professor at ENSEIRB-MATMECA (Bordeaux INP) in the Electronic department, conducting research at the IMS laboratory within the Signal and Image Processing group (MOTIVE team). He is also a member of the In2Brain research group. Dr. Giraud received his M.Sc. in telecommunications from ENSEIRB-MATMECA and a Master's in signal and image processing from the University of Bordeaux in 2014, graduating with honors as top of his class. He completed his Ph.D. in computer science at the University of Bordeaux in 2017, followed by a year as Assistant Professor before becoming Associate Professor in 2018. Current position: Associate Professor at ENSEIRB-MATMECA (Bordeaux INP), Electronic department Research affiliation: IMS laboratory, Signal and Image Processing group, MOTIVE team Additional affiliation: In2Brain research group Education: PhD in Computer Science (2017, University of Bordeaux), M.Sc. in Telecommunications and Signal/Image Processing (2014, ENSEIRB-MATMECA and University of Bordeaux) His research focuses on image processing and analysis, deep learning, and computer vision, with particular expertise in (un)supervised image segmentation, colorization, matching techniques, irregular under-representations (superpixels), spatial relations, and medical imaging (3D MRI applications). His work bridges theoretical computer vision with practical medical applications, developing algorithms that enhance image understanding in both general and specialized contexts. Dr. Giraud has developed several significant methodologies including SCALP (Superpixels with Contour Adherence using Linear Path), TASP (Texture-Aware SuperPixel), DSP (Dual Superpixel Descriptors), and NNSC (Nearest Neighbor-based Superpixel Clustering). His publications demonstrate consistent advancement in superpixel segmentation techniques with increasing focus on medical imaging applications, particularly brain MRI analysis. He currently supervises multiple PhD students including Julien Walther (working on Deep Learning Models from Structural Image Representations), Eloi Navet (An AI Assembly for Neurological Disease Prediction), Edern Le Bot (Holistic Brain MRI Segmentation), and Matthieu Vilain (Semi-supervised Deep Learning for image sequences). His research has resulted in numerous publications in top-tier conferences and journals, with a clear trajectory from theoretical algorithm development to practical implementation in medical contexts.
Pierre Alliez is a Senior Researcher and Team Leader at Inria Sophia Antipolis – Méditerranée, leading the TITANE project-team. He holds roles such as President of the Inria Evaluation Commission and Scientific Coordinator of the Inria-DFKI partnership. His research focuses on Geometry Processing, including mesh compression, surface reconstruction, and optimal transportation. Alliez has authored numerous scientific publications and book chapters, receiving accolades like the Eurographics Young Researcher Award (2005) and ERC grants (IRON, TITANIUM). His academic activities include supervising over 50 PhD students and postdoctoral researchers, and leading projects like GRAPES (Learning and Processing Shapes) and BIM2TWIN (digital twin construction). He has served on editorial boards for Computer Graphics Forum and ACM Transactions on Graphics , and organized major conferences like Pacific Graphics and Eurographics. His work bridges computational geometry, computer graphics, and applied mathematics, with practical applications in 3D printing, cultural heritage, and urban modeling. Education: No specific educational details provided, but has authored a textbook on Polygon Mesh Processing (AK Peters, 2010). Research Interests: Geometry Processing, Mesh Generation, Surface Reconstruction, Optimal Transport, and 3D Data Analysis. Grants & Projects: ANR Pisco, ERC IRON, BIM2TWIN, GRAPES, and collaborations with industries like Dassault Systèmes and Dorea Technology. Labs/Teams: Leads the TITANE team at Inria, contributing to software like CGAL and advancing open-source tools for geometric processing.
Professor Petros Elia is a faculty member at EURECOM, holding the position of Professor within the Department of Communications systems. He specializes in Information Theory , Coding Theory , Caching , Distributed Computing , and Wireless Networks , with additional research in Biometrics . His work focuses on advancing theoretical foundations and practical applications in distributed systems and wireless communication efficiency. He received a prestigious ERC Consolidator Grant for his DUALITY project (2016) and a four-year Fulbright Scholarship (1993-1997). He is also a recipient of the Newcom++ Network of Excellence Distinguished Achievement Award (2008-2011) and the Best Student Paper Award at SPAWC 2011, awarded to his advisee Arun Singh. His research explores cutting-edge topics such as tessellated distributed computing , hypergraph decomposition , and topology-aware caching , with recent contributions presented at venues like the IEEE International Symposium on Information Theory (ISIT 2025). His work bridges theoretical advancements with real-world applications in wireless networks and distributed systems. Education: Supported by his Fulbright Scholarship, he pursued studies in the U.S. during 1993-1997. Grants: ERC Consolidator Grant (2016), and others. Advising: Mentor to Arun Singh , whose work earned a student paper award. He actively contributes to teaching Mobile Communications at EURECOM and remains a key figure in advancing the field through interdisciplinary collaborations and leadership in the Communication Systems department.
Marie Kratz is a Full Professor at ESSEC Business School (Cergy, France), affiliated with the CREAR - Center of Research in Econo-finance and Actuarial Sciences on Risk . Her work bridges theoretical and applied domains in extreme value theory , heavy-tailed distributions , and risk management , with applications in finance, cybersecurity, and neuroscience. Research Focus : Extreme value theory, risk concentration, cyber risk modeling, Gaussian random fields, and pro-cyclicality in financial risk measures. Collaborations : Active collaborations with Michel Dacorogna, Marcel Bräutigam, and Sibsankar Singha on cyber risk and financial applications. Methodologies : Development of the Normex method for aggregated heavy-tailed risks, hybrid Gaussian-Pareto models, and near-explosive random coefficient autoregressive models. Awards and Recognition : No specific awards mentioned in the text.
Slava Rychkov is a Permanent Professor of Theoretical Physics at the Institut des Hautes Études Scientifiques (IHES), a position he has held since 2017. He specializes in strongly coupled quantum and conformal field theories, with applications across high energy physics, statistical mechanics, and condensed matter physics. His current research focuses on the conformal bootstrap and renormalization group techniques, including both perturbative and nonperturbative methods like tensor network renormalization. Education: Ph.D. in Physics, Princeton University (2002) Master of Science, Moscow Institute of Physics and Technology (1996) Recent research highlights include a groundbreaking connection between Deligne categories and symmetries of probabilistic loop ensembles in statistical physics, and a novel method for analytic continuation of Euclidean CFTs to Lorentzian signature. His work on the 2+ϵ expansion challenges established assumptions about critical exponents in 3D systems. Publications span topics from tensor renormalization group methods to rigorous mathematical approaches in the conformal bootstrap program. Scientific Awards: Jacques Solvay International Chair in Physics (2025) Grand Prix Mergier-Bourdeix, French Academy of Sciences (2019) New Horizons in Physics Prize (2014) As Deputy Director of the Simons Collaboration on the Nonperturbative Bootstrap, Rychkov leads efforts to rigorously analyze conformal field theories. His former advisees include prominent researchers at institutions like EPFL, Princeton, and Università di Genova. Current projects focus on resolving fundamental questions about critical phenomena and phase transitions using advanced mathematical physics tools.
Laurent Caraffa is a Researcher at Université Gustave Eiffel, working at the LaSTIG laboratory of IGN (National Institute of Geographic and Forest Information). His research focuses on large-scale 3D data processing, including surface reconstruction from point clouds and images, leveraging triangulated structures and implicit methods. His work also covers indexing and searching within point clouds for large-scale place recognition, with applications in urban environments and navigation systems. Caraffa's research interests span 3D Data Processing, Surface Reconstruction, Point Cloud Processing, Large-scale Place Recognition, Indexing and Retrieval, Big Data, Cloud Computing, Mathematical Optimization, 3D Mapping, and Photogrammetry in degraded conditions. His work bridges theoretical computational geometry with practical applications in geographic information systems and autonomous navigation. His publication record demonstrates significant contributions to distributed 3D processing, particularly through advancements in Delaunay triangulation, watertight surface reconstruction, and neural radiance fields. Recent work shows a clear trajectory toward more efficient and scalable methods for processing massive 3D datasets, with growing emphasis on implicit representations and learning-based approaches for 3D reconstruction. Caraffa actively participates in the scientific community through organizing events like the Big Data Day 2023 at IGN and contributing to major research projects. His work has resulted in publications in top-tier conferences including ICLR, CVPR, ISPRS, and IEEE Big Data, establishing him as a significant contributor to the field of large-scale 3D data processing. As a research supervisor, Caraffa currently co-supervises four PhD students working on projects funded by AID, Criteo, and Huawei, focusing on large-scale place recognition, implicit representations for 3D reconstruction, and 3D reconstruction in degraded conditions. He is also the co-founder of ExtraLabs, a company developing distributed computing solutions for cooperative digital twins, demonstrating the practical impact of his research.
Anna Korba is an Assistant Professor at École Polytechnique, specifically affiliated with ENSAE/CREST in the Statistics Department since September 2020. She is also a co-administrator of the Master Data Science program at École Polytechnique. Her academic journey has positioned her as a leading researcher in machine learning, with particular expertise in kernel methods, optimal transport, and statistical optimization. Dr. Korba received her PhD from Telecom ParisTech in 2018 under the supervision of Prof. Stephan Clémençon. Prior to her current position, she was a postdoctoral researcher at University College London's Gatsby Computational Neuroscience Unit working with Arthur Gretton from December 2018 to August 2020. Her academic foundation includes a Master's degree in Machine Learning and Computer Vision (MVA) from ENS Cachan and ENSAE in 2015. Anna Korba's research primarily focuses on machine learning with emphasis on kernel methods, optimal transport, optimization, particle systems, and preference learning. Her work bridges theoretical statistics with practical machine learning applications, particularly in developing novel sampling and optimization methods. She has made significant contributions to understanding Wasserstein gradient flows, density ratio estimation, and variational inference techniques. Her publication record demonstrates a strong trajectory in top-tier machine learning conferences including ICML, NeurIPS, AISTATS, and ICLR. Her research shows a clear evolution from foundational work on ranking and preference learning during her PhD to more recent contributions in Wasserstein-based optimization, sampling methods, and deep probabilistic modeling. The interdisciplinary nature of her work connects statistics, optimization theory, and practical machine learning applications. Top 10% Oral Presentation at AISTATS 2022 Top 15% Long Oral Presentation at ICML 2021 She actively mentors PhD students and postdoctoral researchers, currently advising seven PhD candidates and having successfully guided several alumni to prestigious positions. Dr. Korba also contributes to the academic community through her role in administering the Master Data Science program and collaborating with researchers across institutions worldwide. As part of the CREST research center, Dr. Korba works within a vibrant team of researchers focused on statistics, machine learning, and their applications to economic and social sciences. Her research group includes current PhD students and postdocs working on various aspects of her research interests, creating a dynamic environment for advancing the field of statistical machine learning.
François Goulette is a Professor and Deputy Director of the Computer Science and Systems Engineering Unit (U2IS) at ENSTA Paris, part of Institut Polytechnique de Paris. His research focuses on 3D point cloud processing, LiDAR perception, and autonomous systems within the Robotics Center (CAOR). His primary research interests lie in 3D point cloud processing , LiDAR perception , and autonomous systems . His work spans fundamental algorithm development to practical applications in autonomous driving, cultural heritage digitization, and robotics. He has made significant contributions to domain generalization of LiDAR perception, semantic segmentation of 3D point clouds, and point cloud registration techniques. The analysis of his recent publications reveals a strong focus on domain generalization for LiDAR perception systems, with multiple papers addressing challenges in 3D semantic segmentation across different environments. His work combines multi-scale architectures , unsupervised learning , and dataset creation to advance the state-of-the-art in autonomous systems perception. The research spans both theoretical algorithm development and practical applications in urban environments. François Goulette leads research activities within the Robotics Center (CAOR) at ENSTA Paris. His team develops advanced techniques for 3D environment understanding, with applications in autonomous vehicles, cultural heritage preservation, and industrial robotics. The research combines computer vision, machine learning, and robotics to solve challenging problems in 3D perception and scene understanding.
Olivier ALLIX is a Professor at the Laboratoire de Mécanique et Technologie (LMT) at École Normale Supérieure de Cachan (ENS-Cachan). His research focuses on computational mechanics, including multiscale modeling of composite materials, structural failure analysis, and non-intrusive coupling strategies. He has held leadership roles such as Head of LMT-Cachan and Vice-president of the International Association for Computational Mechanics (IACM). Expertise: Computational structural mechanics, material failure, inverse problems, and multiscale approaches. Editorial Roles: Associate editor of multiple journals including Computational Mechanics and Computer Methods in Applied Mechanics and Engineering . Awards: IACM Fellow, Euromech Fellow, and recipient of the Gay-Lussac Humboldt Prize (2019). His work integrates experimental mechanics with computational methods, emphasizing big data applications and model validation. He has organized major conferences like the World Congress on Computational Mechanics and co-led international research initiatives such as the IRTG ‘Virtual Material and Structures’ with Hannover University. Teaching includes advanced courses on structural dynamics, composite materials, and computational mechanics at the Master’s level. His research group collaborates with industries like Safran, IFPEN, and DGA on projects involving fatigue analysis, mooring systems, and composite testing.
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.
