Find Academic Supervisors

Nils Holzenberger is an Assistant Professor at Télécom Paris, France, since February 2023, affiliated with the Data Intelligence Graphs (DIG) research team within the Information Processing and Communication Laboratory (LTcI). His work bridges artificial intelligence, natural language processing, and legal domains through neuro-symbolic approaches to statutory reasoning, particularly in tax law. Education: PhD in Computer Science, Johns Hopkins University (2017-2022) Master's in Engineering, Mines ParisTech (2013-2017) Preparatory Classes, Lycée Louis-le-Grand (2011-2013) Holzenberger's research centers on legal artificial intelligence with emphasis on statutory reasoning limitations in large language models. He pioneered the SARA dataset for tax law reasoning and LegalBench benchmark, developing hybrid symbolic-neural frameworks that expose LLMs' shortcomings in precise legal interpretation. His work integrates Prolog solvers with NLP techniques to create executable tax code mappings and contract analysis tools, establishing foundational methods for verifiable legal AI systems. Analysis of his 15 most recent publications (2019-2024) reveals three dominant research thrusts: (1) Tax law reasoning benchmarks exposing LLM hallucinations, (2) Neuro-symbolic integration for statutory interpretation, and (3) Low-resource template extraction for legal documents. His work consistently demonstrates that pure neural approaches fail at precise legal reasoning, necessitating symbolic grounding for reliable legal AI applications. The DIG research team at Télécom Paris, where Holzenberger leads legal AI initiatives, is actively hiring faculty for neuro-symbolic projects. While specific grant details aren't public, his collaborations with HEC Paris, Copilex startup, and featured podcast appearances indicate substantial industry-academia engagement in legal tech development. Holzenberger directs the legal AI vertical within LTcI's DIG team, focusing on data intelligence for statutory reasoning. His group develops tools for tax minimization strategy discovery, contract analysis, and legal information extraction, maintaining close ties with legal practitioners through projects like the Prolog-based tax code interpreter. The team's infrastructure supports both academic research and startup partnerships in computational law.

• Natural Language Processing
• Artificial Intelligence
• Legal AI
• +3 more

Daniel Varro is a Professor affiliated with McGill University (Faculty of Engineering, School of Computer Science), with strong ties to Budapest University of Technology and Economics and Linköping University. He is a leading researcher in model-driven engineering, cyber-physical systems, and software engineering, actively contributing to top-tier conferences such as MODELS, ICSE, and ASE. His research focuses on model-based systems engineering (MBSE) , automated model generation , model transformations , and constraint-based consistency checking . Recently, his work has expanded into integrating large language models (LLMs) and machine learning into modeling workflows, including model querying, domain modeling, and bug detection. The recent publications reveal a strong trend toward AI-augmented modeling, logic-based solvers (e.g., Refinery), and safety assurance of autonomous systems (e.g., COLREGs compliance). His work bridges formal methods with practical software engineering challenges in industrial and safety-critical domains. Scientific Awards: No specific awards mentioned in the text. Advising and Grants: While no explicit list of students or grants is provided, his mentorship in the Doctoral Symposium and repeated leadership roles suggest active supervision and likely grant funding. He has led projects on automated model generation, model quality, and AI integration in modeling. Labs and Teams: Daniel Varro is associated with research groups focused on model-driven engineering and software evolution, likely leading or co-leading teams working on the VIATRA and Refinery frameworks for model transformation and solving.

• Model-Based Systems Engineering
• Cyber-Physical Systems
• Software Engineering
• +12 more

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.

• Automated Reasoning
• Formal Methods
• Formalized Mathematics
• +7 more

Ronja Sczepanski is an Assistant Professor at the Centre for European Studies and Comparative Politics (CEE) at Sciences Po. Her research explores the intersection of national and European identities, focusing on how political perceptions, social sorting, and behavioral processes drive identity change. Specializes in identity formation through political events like referenda Analyzes neighborhood effects and ethnic diversity on identity dynamics Investigates political party framing of social groups Her recent work examines how differentiated integration impacts EU policy compliance and validates open-source machine translation for text analysis. She teaches courses on European integration at institutions including ETH Zurich and the University of Cologne. Recipient of the PolMeth Europe Best Poster Award (2023) Published in journals like Comparative Political Studies and European Union Politics

• National and European Identities
• Social Identity Change
• Political Perceptions in Identity Formation
• +5 more

Clément Mallet is a Senior Researcher and Director of the LASTIG laboratory at Université Gustave Eiffel, IGN, and École Nationale des Sciences Géographiques (ENSG) in Champs-sur-Marne, France. He leads research in geospatial computer vision, focusing on the intersection of remote sensing, computer vision, and machine learning. His responsibilities include overseeing 75 laboratory members and directing the STRUDEL research team focused on spatio-temporal information modeling. Education: Habilitation (HDR) in Geographical Information Science, Université Paris-Est (2016) PhD in Image and Signal Processing, Télécom ParisTech (2010) Engineering Degree in Geographical Information Science, ENSG (2005) Master's in Remote Sensing, Université Paris 6 (2005) Research Interests: Dr. Mallet specializes in multi-modal land-cover mapping, change detection, geohistorical image analysis, and airborne lidar processing. His work integrates deep learning with geospatial data analysis to solve complex problems in environmental monitoring, urban studies, and historical geography. Current research explores foundation models for earth observation and semantic change detection using hybrid data generation techniques. Publication Trends: Mallet's recent articles (2021-2025) demonstrate strong focus on deep learning applications for geospatial challenges: 40% address land-cover mapping innovations, 30% develop novel change detection methodologies, 20% advance lidar data processing, and 10% explore historical map analysis. His work consistently bridges computer vision theory with operational remote sensing applications. Awards and Recognition: Schwidefsky Medal from ISPRS (2016) 5x Outstanding Reviewer awards (CVPR/ECCV/ICCV 2017-2024) Best Paper Awards at GEOBIA 2016 and ISPRS 2014 Young Researcher Award from GDR ISIS (2010) EuroSDR Best PhD Thesis supervision (2020) Research Leadership: Directs multiple national and international projects including MAESTRIA (ANR-funded multi-modal EO analysis) and HIATUS (historical image analysis). Supervised 14+ PhD students in geospatial AI topics. Secured funding from ANR, CNES, EU H2020 (VOLTA, LandSense), and industrial partners. Leads the STRUDEL team developing cutting-edge methods for territory dynamics analysis. Professional Service: Editor-in-Chief of ISPRS Journal of Photogrammetry and Remote Sensing (2021-present). Organized major conferences including ISPRS Congress (2020-2022 Program Chair) and JURSE events. Active in ISPRS working groups since 2008, currently leading initiatives in large-scale machine learning applications for geospatial data.

• Geospatial Computer Vision
• Remote Sensing
• Machine Learning
• +4 more

Benoît Sagot is a Senior Researcher in Natural Language Processing and Computational Linguistics at Inria , currently holding the 2023-2024 Informatics and Digital Sciences Annual Chair at Collège de France. He directs the ALMAnaCH research team and contributes to the PRAIRIE Institute for AI research. Research Focus: His work spans neural language models, machine translation, text simplification, multimodal NLP, and lexical resource development for French and low-resource languages. He explores computational morphology, etymology, and historical linguistics, with applications in opinion mining and computational oenology. Recent Articles emphasize language model interpretability, cross-lingual transfer, and multimodal integration (speech, image). Tools & Resources: He has developed morphological lexicons (Le fff, Alexina), corpora (OSCAR, CAMEMBERT), and parsing pipelines (SxPipe). Projects: Involved in initiatives like ANR BASNUM (Furetière's dictionary digitization) and 3IA PRAIRIE (AI research). His career combines foundational work in syntactic analysis with evolving deep learning approaches.

• Natural Language Processing
• Computational Linguistics
• Machine Translation
• +7 more

Pierre Marquis is a distinguished Professor of Computer Science at Université d'Artois , affiliated with the Centre de Recherche en Informatique de Lens (CRIL-CNRS, UMR 8188) . Since December 2024, he has served as the vice-president for research and doctoral studies at Université d'Artois. His research focuses on Artificial Intelligence , particularly knowledge representation , automated reasoning , inconsistency handling , and knowledge compilation , with recent emphasis on Explainable AI (XAI) . Research Interests: Marquis's work spans foundational AI topics including abduction , induction , belief revision , and preference modeling . He has pioneered knowledge compilation techniques to optimize AI tasks and developed frameworks for reasoning under inconsistency through paraconsistent logics and argumentation. His EXPEKTATION chair (2020-2026) under France's national AI program drives his current focus on interpretable machine learning models. Scientific Awards: 2025: CNRS Silver Medal 2022: AAIA Fellow 2017: Senior Member of Institut Universitaire de France (IUF) 2009: EurAI (ECCAI) Fellow Doctoral Students: Mentoring Clément Lens (critical patient monitoring systems) and Mehdi Sabiri (data-knowledge integration for AI explanations). Collaborating with students like Louenas Bounia (formal XAI models) and Romain Wallon (pseudo-Boolean constraints). Grants & Projects: Leads the EXPEKTATION research chair (2020-2026) and participates in ANR PING/ACK (2019-2023), ANR THEMIS (2021-2025), CNRS IRP MAKC (2020-2024), and H2020 TAILOR (2020-2024). Previously led PIA4 MAIA (2023-2032) and Pint (2022-2023). Labs & Teams: Active in CRIL-CNRS, contributing to PyXAI (Python XAI library) and d4 (model counting), while mentoring teams on consensus belief merging and dynamic constraint processing .

• Artificial Intelligence
• Knowledge Representation
• Automated Reasoning
• +6 more

Jean-Baptiste Alayrac is a Researcher at DeepMind, focusing on structured learning from video and natural language. His academic background includes a PhD from the Sierra and Willow groups at Ecole Normale Supérieure and Telecom ParisTech, where he explored machine learning and computer vision. He has held teaching roles as a Teaching Assistant at Ecole Normale Supérieure and other universities, contributing to courses in statistical machine learning and mathematics. His research interests span multimodal learning, vision-language models, self-supervised learning, and efficient retrieval systems. Notable projects include the Flamingo model for few-shot learning and the Perceiver IO architecture for structured data processing. He has also contributed to foundational works like HowTo100M, leveraging large-scale video-text embeddings. Alayrac's publications emphasize cross-modal interactions, with key contributions in adversarial robustness, layered video representations, and weakly supervised learning. His work often bridges computer vision and natural language processing, with applications in instructional video analysis and cross-lingual translation.

• Computer Vision
• Machine Learning
• Multimodal Learning
• +3 more

Cristina Butucea is a Professor of Statistics and Machine Learning at ENSAE-CREST, Institut Polytechnique de Paris . She was nominated an IMS Fellow (2019) for her contributions to nonparametric and high-dimensional statistics. She has co-organized major conferences like Fréjus 2018 , Luminy 2019-2020 , and Oberwolfach 2021 , and serves as Associate Editor for ALEA . Fields of interest: Nonparametric statistics, quantum statistics, differential privacy, inverse problems, machine learning. Awards: IMS Fellowship, conference organization leadership. Research trends: Focuses on optimal estimation under privacy constraints, quantum state reconstruction, high-dimensional inference, and adaptive nonparametric methods. Email: Cristina.Butucea@ensea.fr | Cristina.Butucea@ip-paris.fr

• Nonparametric Statistics
• High-Dimensional Statistics
• Inverse Problems
• +3 more

Taein Kwon is a postdoctoral research fellow at the Visual Geometry Group (VGG) within the Department of Engineering Science at the University of Oxford, working under Prof. Andrew Zisserman. Previously, he completed his PhD at ETH Zurich under Prof. Marc Pollefeys and earned master's and bachelor's degrees from UCLA and Yonsei University, respectively. His educational background includes: Bachelor's in Electrical Engineering from Yonsei University, Seoul, Korea Master's degree from UCLA PhD from ETH Zurich (defended July 2024) His research spans Egocentric Vision, Action Recognition, Hand-object Interaction, Video Understanding, AR/VR, and Multi-modal Learning, with emphasis on first-person perspective analysis for AI assistants and human-computer interaction. His work integrates 3D reconstruction, pose estimation, and multimodal signals to model complex human activities and physical interactions. Analysis of his 2021-2025 publications reveals a consistent focus on egocentric vision datasets (H2O, HoloAssist, EgoPressure) and novel frameworks for hand-object interaction, action recognition, and gesture understanding. His research demonstrates strong interdisciplinary connections between computer vision, robotics, and human-centered AI, with increasing emphasis on pressure sensing, co-speech gestures, and cross-modal alignment. His scientific recognition includes: CVPR Egovis 2022/2023 Distinguished Paper Award for HoloAssist (July 2024) SNSF Postdoc.Mobility fellowship (May 2024) He actively mentors students on egocentric vision projects, supervising master's theses, semester projects, and collaboration initiatives leading to publications at top conferences. His research is supported by the SNSF fellowship and industry collaborations with Meta Reality Labs and Microsoft Research. As part of Oxford's Visual Geometry Group, he contributes to cutting-edge computer vision research while maintaining strong ties with ETH Zurich's computer vision community through ongoing collaborations and dataset development efforts.

• Egocentric Vision
• Action Recognition
• Contextual AI
• +6 more

Dr. Yves Boubenec is an Associate Professor at École Normale Supérieure (ENS)-PSL University, Paris, France. He serves as Head of the LSP Neuro Platform and Director of Studies at the Department of Cognitive Studies. Academic Rank: Associate Professor Institution: ENS-PSL Departments: Cognitive Studies (ENS), LSP Neuro Platform Email: yves.boubenec@ens.psl.eu Research Focus: Boubenec investigates neural mechanisms of auditory perception and cognition using integrated methodologies spanning single-neuron electrophysiology to large-scale neuroimaging. His work reveals how context, learning, and multisensory interactions shape sound encoding in mammalian neocortex. Primary Research Themes Context-dependent auditory encoding Perceptual attention mechanisms Task-driven neural plasticity Self-supervised learning models Population-level cortical dynamics Human/ferret auditory comparisons Publication Trends: Recent work (2024-2025) examines speech production networks, premotor auditory categorization, and algebraic structures in sound learning. Earlier studies (2018-2022) focus on population gating, hierarchical auditory coding, and self-voice mechanisms. 2025 Self-voice frequency analysis Hierarchical ferret auditory cortex mapping Temporal window constraints 2024 Premotor category hemodynamics Self-supervised sound structures Human speech cortical encoding Methodological Expertise: Combines awake ferret functional UltraSound, Neuropixels recordings, and computational modeling to analyze neural representations across spatial scales. Specializes in translating animal model findings to human auditory processes.

• Auditory Neuroscience
• Perceptual Attention
• Sound Encoding
• +3 more

Auguste Genovesio is a Research Director (DR INSERM) leading the Computational Bioimaging and Bioinformatics team at the Centre for Computational Biology within the École Normale Supérieure (ENS) in Paris. His work focuses on large-scale cellular morphology analysis, integrating machine learning, microscopy, and computational modeling to study cellular responses to perturbations. His team develops algorithms for analyzing high-dimensional biological data, with applications in drug discovery, functional genomics, and neuroscience. Education and Affiliations: Genovesio’s research is anchored at ENS and collaborates with institutions like Institut Curie, Collège de France, and ESPCI. His lab develops open-source tools such as PySpacell and ALFA , advancing spatial analysis and genomic data processing. Research Interests: His group combines deep learning, bioinformatics, and experimental biology to tackle challenges in cellular dynamics, morphological heterogeneity, and predictive modeling. Recent work includes applying diffusion models to reveal subtle phenotypes and optimizing microscopy image analysis pipelines. Key Projects: Cross-modal knowledge distillation for transcriptomics, latent diffusion models for small datasets, and super-resolution microscopy via StyleGAN regularization. Applications: Collaborations in drug screening, neurobiology (e.g., Drosophila memory studies), and cancer cell analysis. Publications: Over 50 peer-reviewed articles since 2007, including work in Nature Communications , Developmental Cell , and NeurIPS . Recent focus on generative AI for biological image analysis and self-supervised learning biases. Grants & Awards: While specific grants aren’t listed, his lab’s cutting-edge research suggests significant institutional and collaborative support. No explicit awards mentioned in texts. Labs/Teams: Director of the Computational Bioimaging group, part of the Functional Genomics section at ENS. Supervises PhD students and postdocs in AI-driven biology and computational microscopy.

• Computational Bioimaging
• Bioinformatics
• Machine Learning
• +7 more

Deepak Garg is a researcher at the Max Planck Institute for Software Systems (MPI-SWS) in Germany. His work primarily focuses on secure compilation , type theory , and formal verification of software systems. Conference Roles: He has served as an author and committee member in premier programming language conferences such as POPL , PLDI , ICFP , and ESOP since 2015. Research Interests include: Secure compilation techniques for hyperproperty preservation. Modal and refined type theories for cost analysis and concurrency. Formal verification of C code and probabilistic programs. Compiler correctness and decentralized multi-language verification. Contributions span foundational research in programming languages, with a focus on security, complexity, and concurrency. His work has been published in tracks like PriSC , OOPSLA , and ESOP , addressing topics such as data-flow back-translation and robust property preservation.

• Programming Languages
• Secure Compilation
• Type Theory
• +7 more

Maryam Mehri Dehnavi is an Associate Professor in the Department of Computer Science at the University of Toronto and a Principal Research Scientist at NVIDIA. She holds the Canada Research Chair in Parallel and Distributed Computing and leads the ParaMathics research group. Research focuses on high-performance computing , machine learning , sparse matrix optimizations , and compiler design for heterogeneous systems. Her work develops domain-specific languages , scalable numerical libraries , and auto-vectorization techniques for cloud and GPU platforms. Recent publications address LLM compression , sparse code translation , GPU kernel synchronization , and control flow optimization . Scientific recognition: Ontario Early Researcher Award (2021), NSF CRII Grant, NSERC New Frontiers in Research Fund. Current students: Mushegh Shahinyan , Martin Phan , Maryam Haghifam , and others. Former advisees: Kazem Cheshmi (NJIT), Zachary Blanco (MIT Lincoln Lab), Yuanxi Li (Amazon).

• High-Performance Computing
• Cloud Computing
• Machine Learning
• +3 more

Emmanuel Dupoux is a Professor at the École des Hautes Études en Sciences Sociales (EHESS), affiliated with the Laboratory of Cognitive Sciences and Psycholinguistics (LSCP) and the Département d'Études Cognitives (DEC) at École normale supérieure (ENS), Paris. He leads the Cognitive Machine Learning team, focusing on interdisciplinary research at the intersection of cognitive science, artificial intelligence, and language development. His research centers on understanding human cognition through computational models, particularly in the domain of infant language acquisition. By leveraging machine learning techniques, his work aims to reverse-engineer how children learn language, bridging gaps between developmental psychology and AI. This includes modeling early phonological and lexical development using synthetic learning systems. The recent internship and postdoctoral positions advertised under his supervision highlight a growing focus on applying data science and AI to behavioral analysis in neurodegenerative diseases, indicating an expansion of his research into clinical cognitive neuroscience. His collaborative work with the Interventional Neuropsychology Laboratory underscores this interdisciplinary trajectory. Scientific Awards: No awards listed in the provided text. Emmanuel Dupoux actively advises graduate students and postdoctoral researchers, as evidenced by his role as principal adviser for an M1/M2 internship on reverse engineering infant language development and co-adviser for a postdoctoral position in AI for neurodegenerative disease analysis. While specific grants are not mentioned, his leadership in hosting research positions suggests active external funding. He is involved in fostering research teams that integrate cognitive theories with machine learning frameworks. He is associated with the Cognitive Machine Learning team at LSCP and collaborates with the Interventional Neuropsychology Laboratory , where he co-supervises research on AI-driven behavioral analysis in neurological disorders. These affiliations reflect a strong commitment to translational cognitive science, linking fundamental research in language development with clinical applications.

• Cognitive Science
• Psycholinguistics
• Machine Learning
• +4 more