Edouard Oyallon is a CNRS Researcher at Sorbonne University's MLIA team within the Institute of Intelligent Systems and Robotics (ISIR). His research focuses on machine learning foundations, particularly the symmetries of deep neural networks, and large-scale distributed/decentralized training algorithms. He has contributed to frameworks like Kymatio for wavelet scattering transforms and collaborates on projects such as SHARP (Frugal Learning) and ADONIS (ANR-funded). He advises multiple PhD and postdoctoral researchers and teaches advanced deep learning courses at Institut Polytechnique de Paris (IPP). Grants include the ADONIS project (ANR/Sorbonne) and participation in VHS and CoCa4AI initiatives. His work spans theoretical and applied aspects, with recent emphasis on optimizing LLM training at exascale. He maintains active roles in academic service, including organizing workshops on federated learning and graph machine learning.
Cezary Kaliszyk is a Professor in Theoretical Computer Science at the University of Melbourne, previously affiliated with the University of Innsbruck. He is actively involved in research and leadership in formal methods, automated reasoning, and machine learning for theorem proving. Research Interests: Automated Reasoning and Interactive Theorem Proving Formalized Mathematics and Proof Automation Machine Learning for Logic and Theorem Proving Integration of AI with Proof Assistants (Coq, Isabelle) Dependent Type Theory and Higher-Order Logic His recent publications (2023–2025) span topics in dependently-typed logic, learning for proof guidance, formalization of surreal numbers, and blockchain-based formal methods. The works consistently bridge formal logic with machine learning, emphasizing automation, explainability, and cross-system integration. Scientific Leadership and Projects: Principal Investigator, ERC project FormalWeb3 Lead Developer, CoqHammer , Tactician , ProofWeb WG5 Leader, COST Action EuroProofNet (until 2024) Contributor to HOL(y)Hammer , Isabelle Enigma He supervises multiple PhD students and has mentored several graduates in formal methods and AI. He teaches courses in theoretical computer science, logic, and machine learning. There are no listed awards in the provided data, but his extensive publication record and project leadership indicate significant recognition in the field. Labs and Research Groups: He leads a research group focused on formal methods and learning-based reasoning, collaborating internationally on projects involving proof automation, formal libraries, and semantic technologies.
David Gesbert serves as Professor and Director of EURECOM, a leading research institution in Sophia Antipolis, France, specializing in digital sciences. Previously heading the Communications Systems Department, he now directs EURECOM while leading the Foundations & Algorithms research group within the Communication Systems Department. His leadership spans institutional administration and cutting-edge research supervision. Dr. Gesbert's research portfolio demonstrates exceptional depth across communications theory and wireless networking: Communication theory and information theory fundamentals Signal processing for wireless networks with emphasis on robustness Machine learning applications for decentralized network optimization Connected robotics and UAV-enabled flying radio access networks 6G wireless architecture with focus on AI integration Distributed decision making under information uncertainties His publication trajectory reveals a strategic evolution from classical communication theory toward AI-integrated wireless systems, particularly focusing on UAV-aided networks and connected robotics for 6G. Recent work emphasizes learning-based approaches for network optimization under asymmetric information conditions, with growing emphasis on sustainability and green communications. Dr. Gesbert's scientific recognition includes: Fellow of IEEE (2011) and Asia Pacific Artificial Intelligence Association (2021) Thomson-Reuters List of Highly Cited Researchers in Computer Science Multiple Best Paper Awards at IEEE conferences (EW 2017, ICC 2019) ERC Advanced Grant recipient for the PERFUME project on Smart Device Communications 3IA Chair funding for AI for future IoT Networks 2019 Winner of 'Fundamental research project of the year' by French SCS He actively mentors PhD students and researchers, welcoming collaboration in his research domains. His group secures substantial research funding including ERC grants, 3IA Chairs, and participation in major European projects like the WINDMILL ITN Marie Curie project on Machine Learning in Wireless Communications. Dr. Gesbert serves on editorial boards and regularly delivers keynotes at premier international conferences, establishing himself as a thought leader in next-generation wireless communications.
Séverine Dusollier is a Professor of Intellectual Property at the Law School of Sciences Po Paris and holds a Senior Chair at the Institut Universitaire de France. She serves as Director of the Law School's Research Centre and Head of the Master in Innovation Law, actively contributing to doctoral committee activities. Her expertise spans copyright law , digital rights , and intellectual property frameworks. Key roles : Research Centre Director, Master in Innovation Law Head International engagement : Founding Member of the European Copyright Society, ATRIP member Her research focuses on digital copyright issues , authorship concepts , contractual protections for creators , and the evolution of exceptions and limitations . Recent work explores generative AI implications, public domain dynamics , and inclusive property models . She has held visiting positions at Berkeley, Columbia, NYU, and Cambridge. Notable scientific awards include: ERC research grant (2014–2019) Senior Chair, Institut Universitaire de France CSPLA (French Copyright Council) membership Her publications emphasize digital transitions , IP openness , and fair remuneration in streaming , reflecting her dedication to reconciling traditional IP structures with modern technological realities.
Francis Bach is a Professor and researcher at INRIA, leading the SIERRA project-team since 2011, which is part of the Computer Science Department at Ecole Normale Supérieure (ENS) within PSL Research University. His work bridges CNRS, ENS, and INRIA as a joint research effort. Elected to the French Academy of Sciences in 2020, he currently runs the ERC project SEQUOIA following his previous ERC project SIERRA (2009-2014). His research spans statistical machine learning with focus on optimization, sparse methods, kernel-based learning, neural networks, graphical models, and signal processing. Bach completed his Ph.D. in Computer Science at U.C. Berkeley under Professor Michael Jordan, followed by work at Ecole des Mines de Paris and the WILLOW project-team at INRIA/ENS/CNRS (2007-2010). His recent book "Learning Theory from First Principles" was published by MIT Press in December 2024. Bach's publication record shows consistent high-impact contributions across machine learning theory and applications, with recent work focusing on conformal prediction, diffusion models, optimization theory, and learning theory foundations. His research demonstrates strong connections between theoretical guarantees and practical algorithms, with applications spanning generative modeling, robust optimization, and statistical inference. Elected to French Academy of Sciences (2020) ERC project SIERRA (2009-2014) ERC project SEQUOIA (current) Author of "Learning Theory from First Principles" (MIT Press, 2024) Bach actively mentors numerous PhD students and postdocs, with many alumni now holding faculty positions at institutions like EPFL, Ecole Polytechnique, University of Washington, and University of Montreal. His teaching includes advanced courses on learning theory at ENS's Master's programs. He regularly presents tutorials at major conferences including COLT, NeurIPS, and ICML, demonstrating his leadership in the theoretical machine learning community.
Christophe VIGNAT is a Professor at CentraleSupélec, affiliated with the Laboratoire des Signaux et Systèmes (L2S). His research focuses on number theory, special functions, probability, and their applications in signal processing and control systems. He has held visiting professorships at École Polytechnique Fédérale de Lausanne (EPFL) and Tulane University. VIGNAT's work bridges pure mathematics and applied fields, with notable contributions to Bernoulli/Euler polynomials, multiple zeta values, and probabilistic methods in number theory. His recent publications explore topics like partition functions, theta functions, and Ramanujan-type identities. He has delivered talks at international conferences and collaborates widely with researchers in mathematics and physics. Research Interests: Number theory, special functions (Bessel, orthogonal polynomials), probability theory, signal processing, control systems, analytic combinatorics, and their interconnections. His work often employs symbolic computation and probabilistic approaches to uncover identities and structures in mathematical analysis. Publications Trends: Recent articles emphasize partition theory, zeta functions, and integrals related to classical polynomials. His collaborations highlight interdisciplinary efforts between pure mathematics and applied sciences. Over 150 refereed papers and conference contributions demonstrate his prolific output across diverse mathematical domains. Education: While specific academic history isn’t detailed, his roles and publications suggest advanced training in mathematics and engineering, typical for a full professor in systems and control.
Igor Kortchemski is a CNRS researcher at the Department of Mathematics and Applications (DMA) at École Normale Supérieure, Paris, and a lecturer in the Department of Applied Mathematics at École Polytechnique. His primary research focuses on the continuous limits of random discrete models, particularly examining how discrete combinatorial structures converge to continuous objects under appropriate scaling. His educational background includes a PhD in Mathematics (2012) under Jean-François Le Gall at École Normale Supérieure and a Habilitation à diriger des recherches (HDR) in Mathematics (2016). Kortchemski's research spans several interconnected areas: Random trees and Galton-Watson processes with heavy-tailed distributions Random planar maps and their geometric properties Growth-fragmentation processes and their connections to Lévy processes Scaling limits of combinatorial structures and their continuous counterparts His publication record shows a consistent focus on the geometric properties of random discrete structures, with recent work (2023-2025) exploring uniform attachment processes with freezing, critical tree phenomena, and the mesoscopic geometry of sparse random maps. His research often involves sophisticated probabilistic analysis combined with combinatorial insights. Scientific recognition includes: prix de thèse solennel Perrissin-Pirasset / Schneider de la chancellerie des Universités de Paris (2012) Kortchemski actively contributes to academic service: Examiner for the minor math exam at École Polytechnique (FUF) since 2023 Member of the mathematics jury for ENS International Selection (2023) Member of the jury for the external mathematics competitive examination (Agrégation) since 2021 Member of the jury for the Arts and Economic and Social Sciences Bank (B/L) mathematics exams (2015-2018) He mentors the next generation of researchers as co-director of Antoine Aurillard's and Vanessa Dan's theses (both since 2023), and previously directed Etienne Bellin's (2020-2023) and Paul Thevenin's (2017-2020) theses.
Loris D'Antoni is an Associate Professor in the Department of Computer Science and Engineering at the University of California at San Diego (UCSD) . He is also a Visiting Academic at Amazon Web Services (AWS) . His research focuses on helping people write trustworthy software through techniques in program synthesis, formal verification, and machine learning robustness. Bachelor and Master in Computer Science from University of Torino (2008, 2010) PhD in Computer Science from University of Pennsylvania (2015) His research integrates programming languages , automata theory , and formal methods to ensure software reliability. Recent work explores semantics-guided synthesis and specification-aligned LLMs , with applications in network security, machine learning fairness, and automated code repair. Key trends in his publications include program synthesis , formal verification , and trustworthy AI systems . He has contributed to tools like AutomataTutor and SemGuS , a framework for customizable synthesis problems using constrained Horn clauses. Phillip R. Certain-Gary D. Sandefur Distinguished Faculty Award NSF CAREER Award Microsoft Research Faculty Fellowship Google and Facebook Faculty Awards Best Paper Award at ICDCN 2023 Distinguished Paper Award at SBES 2021 D'Antoni actively contributes to academic community service as a committee member in PLDI , OOPSLA , POPL , and CAV . He leads the Programming Systems Group at UCSD and collaborates with SemGuS research team on synthesis frameworks.
Abderrahim Benslimane is a Full Professor of Computer Science at the University of Avignon, France, where he serves as Vice Dean of International Relations at the UFR STS (Unité de Formation et de Recherche en Sciences et Technologies). He is also Head of the master degree SICOM (Systèmes Informatiques Communicants: réseaux, services et sécurité) program at the university. His extensive academic career spans several decades with significant contributions to computer science, particularly in networking and security domains. Professor Benslimane holds a HDR (Title to supervise researches) from the University of Cergy-Pontoise, a Ph.D. from the University of Franche-Comté, along with M.S. and B.S. degrees in Computer Science from the same institution and the University of Nancy respectively. His research interests primarily focus on distributed computing, networking and communication protocols, with particular emphasis on modeling, describing and implementing secure communication protocols and multimedia applications in heterogeneous network architectures. He combines engineering and theoretical approaches using graphs, distributed algorithms, transition systems, and performance evaluation models. Benslimane's scholarly work demonstrates a strong trend toward addressing security and privacy challenges in emerging technologies. His recent publications focus on cybersecurity applications for wireless sensor networks, Internet of Things, blockchain implementations, UAV communications, and vehicular networks. He has pioneered research in energy attack mitigation, trust management systems, and secure group communications, often employing game theory and novel cryptographic approaches. His work bridges theoretical foundations with practical implementations in next-generation networking technologies. IEEE VTS Distinguished Lecturer (2020-2022) Best Paper award at IEEE ICC 2019 Multiple Prime d'Encadrement et de Recherche Doctorale awards (1998-2021) Prime d'Excellence Scientifique (2011-2015) IEEE Senior Member As an academic leader, Benslimane has served as Editor in Chief of Multimedia Intelligence and Security Inderscience Journal, Area Editor of IEEE Internet of Things Journal, and Associate Editor for multiple prestigious publications including IEEE Transactions on Multimedia and IEEE Wireless Communication Magazine. He has founded and led research centers including the Informatics Research center (CRI) at the French University in Egypt and the Multimedia and networking team (RAM) at the Laboratoire d'Informatique d'Avignon (LIA). His laboratory research focuses on security, communication protocols, graphs and distributed algorithms, with applications in ad hoc networks, sensor networks, vehicular networks, and IoT.
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.
Jaouad Mourtada is an Assistant Professor in the Department of Statistics at ENSAE/CREST, École Nationale de la Statistique et de l'Administration Économique since September 2020. Previously, he was a postdoctoral researcher at the Laboratory for Computational and Statistical Learning at the University of Genoa (2019-2020). He completed his PhD in Statistics at École Polytechnique under the supervision of Stéphane Gaïffas and Erwan Scornet. His educational background includes a Master's degree in Mathematics with specialization in Probability and Random Models (2016), a Master's degree in Fundamental Mathematics (2015), and a Bachelor's degree in Mathematics from Pierre and Marie Curie University and École Normale Supérieure (2013). Dr. Mourtada's research focuses on the intersection of statistics and learning theory, with particular interest in high-dimensional statistics, online learning, and density estimation. His work explores the complexity of prediction and estimation problems through rigorous theoretical analysis. His research spans statistical learning theory, robust statistics, and the theoretical foundations of machine learning algorithms. His publication record since 2017 demonstrates consistent contributions to top-tier venues in statistics and machine learning, with recent work focusing on universal coding, aggregation methods, robust regression, and the theoretical analysis of kernel methods and random forests. His research shows a progression from online learning and expert aggregation to more complex statistical learning problems involving high-dimensional data and model misspecification. He teaches courses including Statistical Learning Theory for Master 2 Data Science students and Probability Theory at ENSAE. His teaching spans theoretical foundations of machine learning and core probability concepts for advanced statistics students.
Paolo Papotti is an Associate Professor of Computer Science at EURECOM (France) since 2017, affiliated with the Data Science department. Previously, he was a senior scientist at QCRI (Qatar) and an assistant professor at Arizona State University (USA). He earned his PhD in Computer Science from the University of Roma Tre (Italy) in 2007, following an MEng in Computer Engineering from the same institution in 2003. His research focuses on scalable data management, data integration, data cleaning, and computational fact-checking. Notable contributions include work on knowledge graph rule discovery (Rudik), fact-checking frameworks (Scrutinizer), and data quality systems. His research has been supported by awards such as the 2020 Google Faculty Research Fellowship. Key publications include advancements in table representation learning, LLM-based data querying, and crowdsourced fact-checking validation. His work spans theoretical foundations and practical tools for improving data quality and information trustworthiness.
Nicolas Riviere is a Professor at INSA Lyon in the Department of Mechanical Engineering, working within the Laboratory of Fluid Mechanics and Acoustics (LMFA - UMR 5509). He is part of the "Fluides complexes et transferts" (Complex Fluids and Transfers) group and the Environment team. His teaching activities primarily focus on fluid mechanics at the Mechanical Engineering Department of INSA Lyon, covering: General balances (mass, momentum, energy) Aerodynamics Compressible flows Numerical simulation of flows Free surface hydraulics Prof. Riviere's research centers on free surface hydrodynamics, with applications to natural and industrial risks. His work takes an experimental approach, utilizing the laboratory's channel facilities, particularly the channel intersection installation. His research spans river floods with compound beds, urban flooding, sanitation networks, torrential flows, and flow-obstacle interactions. He has developed a strong interdisciplinary focus, co-leading the "Baignades en Rivières Urbaines" studio with Oldrich Navratil from University Lyon 2 and the EVS Laboratory. His publication record demonstrates consistent contributions to the fields of fluid mechanics and environmental hydraulics, with recent work focusing on open-channel flows, urban flooding phenomena, vegetation-flow interactions, and experimental techniques for studying complex hydraulic phenomena. His research often bridges theoretical fluid mechanics with practical environmental applications. Prof. Riviere has received recognition for his work in environmental fluid mechanics, with numerous publications in high-impact journals in hydraulic engineering and fluid mechanics. He has supervised multiple PhD students and research projects related to environmental fluid mechanics and has collaborated with various institutions on interdisciplinary research projects addressing water-related challenges. The laboratory where he works, LMFA, provides extensive experimental facilities including wind tunnels, hydrodynamic channels, and advanced measurement techniques such as PIV (Particle Image Velocimetry), LDV (Laser Doppler Velocimetry), and other state-of-the-art instrumentation for fluid flow analysis.
Nora MAREÏ, CNRS Researcher at PRODIG (UMR 8586), specializes in transport geography, territorial development, and urban dynamics across European, Mediterranean, and West African contexts. Her work bridges macroregional geoeconomic analysis with local territorial realities, focusing on infrastructure, logistics, and regional integration processes. Doctorate from University of Nantes (2012 thesis: Le détroit de Gibraltar, Porte du Monde, Frontière de l’Europe ) 2022-2026: Coordinator of ANR Trans-Log project on logistics cities 2021-2025: Member of LMI Movida II international lab Research interests include: Comparative analysis of institutional vs. private territorial production Metropolitanization and circulation patterns in Global South cities Eurafrican connectivity through ports like Tanger-Med Maritime chokepoints (Gibraltar, Suez) as development catalysts Recent publications examine: 2024: Morocco's role in Mediterranean-African transport hubs 2022: Tanger-Med's networked territorial challenges 2021: Dualization in Global South city logistics 2020: Regional integration models Scientific recognition: 2013 CNU Mappemonde thesis prize finalist 2023 'The Waters of Discord' award Teaching contributions: Master's courses on fieldwork methodology (since 2019) International transport geopolitics instruction (since 2013)
Alain Durmus is a Professor at École Polytechnique, affiliated with the applied mathematics department (CMAP). His research focuses on computational statistics, machine learning, and stochastic methods, including Monte Carlo algorithms, Bayesian inference, and optimization. He explores topics such as Markov chain Monte Carlo (MCMC), stochastic approximation, and generative models. His work emphasizes theoretical guarantees for algorithms like Langevin Monte Carlo and Hamiltonian Monte Carlo, with applications to high-dimensional Bayesian inference and inverse problems. Key contributions include hypocoercivity analysis of piecewise deterministic MCMC processes, convergence guarantees for stochastic gradient methods, and the development of efficient sampling techniques. He has also contributed to Bayesian imaging and federated learning through works like the QLSD algorithm. Awarded the Best Student Paper Award at ICASSP 2020 for his work on the Sliced-Wasserstein distance. His teaching spans mathematical statistics, stochastic methods, and probability at École Polytechnique and ENS Paris-Saclay. He has also contributed to conferences and workshops on topics ranging from MCMC convergence to optimization in machine learning.
