Research
Summary
My current research focuses on leveraging differential geometry and partial differential equations for machine learning. I developed Intrinsic Green's Learning (IGL), a framework that models target functions on manifolds as solutions to linear PDEs whose source terms are learned from data. By discovering low-dimensional coordinate charts where Green's kernels decompose as low-rank tensors, IGL achieves scalability linear in the intrinsic dimension while providing interpretability through structured differential operators. This work was presented at AI & PDE Workshop @ ICLR 2026.
My doctoral thesis is entitled "End-to-end approach to classification in unstructured spaces with application to judicial decisions" and focused both on theoretical and practical Machine Learning. I try to reduce the need for expertise required in the usual Machine Learning workflow as it is the first obstacle to the adoption of artificial intelligence solutions.
A detailed summary of my doctoral thesis is available here.
I am also a member of the Eloquence AI Community of Experts (Horizon Europe), where I provide AI/LLM expertise and assess technical proposals for ethical bias mitigation in AI systems.
Selected Publications
- "Intrinsic Green's Learning: Supervised Learning on Manifolds via Inverse PDE", Alexandre Quemy. AI & PDE Workshop @ ICLR 2026, 2026.
- "ydata-profiling: Accelerating Data-Centric AI with high-quality data", Fabiana Clemente, Gonçalo Martins Ribeiro, Alexandre Quemy, et al.. Neurocomputing, 2023.
- "A large reproducible benchmark on text classification for the legal domain based on the ECHR-OD repository", Alexandre Quemy, Robert Wrembel, Natalia Łopuszyńska, George Papadakis, Andrés Domínguez Delgado. Information Systems, 2023.
- "Artificial intelligence and fair trial rights", Helga Molbæk-Steensig, Alexandre Quemy. Artificial Intelligence and Human Rights, 2023.
- "Binary Classification In Unstructured Space With Hypergraph Case-Based Reasoning", Alexandre Quemy. Information Systems, 2019.
Full publication list (20+ papers) available below.
Thesis
-
“End-to-end approach to classification in unstructured spaces with application to judicial decisions”
Supervisor: Robert Wrembel (Poznan University of Technology)
Ph.D. thesis
-
“Insertion of adaptive modalities in the mono or multi objectives evolutionary planner Divide-and-Evolve”
Supervisor: Marc Schoenauer (Inria), Christian Gout (INSA)
Master thesis
Publications
“ydata-profiling: Accelerating Data-Centric AI with high-quality data”
Fabiana Clemente, Gonçalo Martins Ribeiro, Alexandre Quemy, et al.
Neurocomputing
“A large reproducible benchmark on text classification for the legal domain based on the ECHR-OD repository”
Alexandre Quemy, Robert Wrembel, Natalia Łopuszyńska, George Papadakis, Andrés Domínguez Delgado
Information Systems
“Judicial independence and impartiality: Tenure changes at the European Court of Human Rights”
Helga Molbæk-Steensig, Alexandre Quemy
European Journal of International Law
“MultiZenoTravel: a Tunable Benchmark for Multi-Objective Planning with Known Pareto Front”
Alexandre Quemy, Marc Schoenauer, Johann Dréo
arXiv preprint arXiv:2304.14659
“Case-based and quantum classification for ERP-based brain-computer interfaces”
Grégoire Hugues Cattan, Alexandre Quemy
Brain Sciences
“First steps towards quantum machine learning applied to the classification of event-related potentials”
Grégoire Cattan, Alexandre Quemy, Anton Andreev
arXiv preprint arXiv:2302.02648
“Artificial intelligence and fair trial rights”
Helga Molbæk-Steensig, Alexandre Quemy
Artificial Intelligence and Human Rights
“ECHR-OD: On Building an Integrated Open Repository of Legal Documents for Machine Learning Applications”
Alexandre Quemy and Robert Wrembel
Information Systems
“True Pareto Fronts for Realistic Multi-Objective AI Planning Instances”
Alexandre Quemy
To be submitted to International Conference on Automated Planning and Scheduling (ICAPS)
“A Physical Approach to Classification”
Alexandre Quemy
To be submitted to International Conference on Machine Learning (ICML)
“Raisonnement par Cas appliqué aux Interfaces Cerveau-Machines: Étude pilote”
Grégoire Cattan, Alexandre Quemy
IBM; Poznan University of Technologies
“Paradiseo: From a Modular Framework for Evolutionary Computation to the Automated Design of Metaheuristics”
Johann Dreo, Arnaud Liefooghe, Sébastien Verel, Marc Schoenauer, Juan Merelo, Alexandre Quemy, Benjamin Bouvier, Jan Gmys
Genetic and Evolutionary Computation Conference (GECCO)
“Two-stage Optimization for Machine Learning Workflow”
Alexandre Quemy
Information Systems
“Binary Classification In Unstructured Space With Hypergraph Case-Based Reasoning”
Alexandre Quemy
Information Systems
“Data Pipeline Selection and Optimization”
Alexandre Quemy
International Workshop on Design, Optimization, Languages and Analytical Processing of Big Data (DOLAP) @ International Conference on Extending Database Technology/International Conference on Database Theory (EDBT/ICDT) Joint Conference
“Binary Classification With Hypergraph Case-Based Reasoning”
Alexandre Quemy
International Workshop on Design, Optimization, Languages and Analytical Processing of Big Data (DOLAP) @ International Conference on Extending Database Technology/International Conference on Database Theory (EDBT/ICDT) Joint Conference
“Unsupervised Video Semantic Partitioning Using IBM Watson and Topic Modelling”
Alexandre Quemy and Krzysztof Jamrog and Marcin Janiszewski
International Workshop on Data Analytics solutions for Real-LIfe APplications (DARLI-AP) @ International Conference on Extending Database Technology/International Conference on Database Theory (EDBT/ICDT) Joint Conference
Awards
IBM Innovation Award
Restlessly reinvent – our company and ourselves
2019
Best Paper, International Workshop On Design, Optimization
Languages and Analytical Processing of Big Data
2018, Lisbon
Grant from the Polish Academy of Science
IFIP World Computer Congress PhD Student Research Competition
2018
IBM Analytics Hero Award
Restlessly reinvent – our company and ourselves
2018
Best Paper, International Workshop On Design, Optimization
Languages and Analytical Processing of Big Data
2018, Vienna
IBM Manager’s Choice Award x2
Dare to Create Original Ideas
2016
Teaching & Supervision
Supervision
-
“Graph-based linear explanation for supervised machine learning models”
2018 - 2019
Pawel Mroz, Master Thesis
-
“Design and implementation of a technique to assess regressions associated to GitHub Pull Request”
Sum. 2019
Laetitia Beignon, Internship
-
“Improving predictions of the European Court of Human Rights decisions”
Spr. 2019
Amadeusz Masny, Internship
-
“Hyperparameter Tuning: state-of-the-art and benchmarking”
Spr. 2019
Sylwia Wronia, Internship
-
“Hyperparameter optimization of Split-and-Merge, a semantic partitioning algorithm”
Sum. 2018
Pawel Rzonca, Internship
Teaching
-
“Theoretical Machine Learning”
2018 - 2019
Lectures at IBM Krakow Software Lab
-
“IBM Watson Services Overview”
2016 - 2019
Regular presentation at polish universities
Talks
“Is practical AutoML more than CASH?”
GHOST Day: a practical machine learning conference Poznan, Poland
“Towards Data Pipeline Selection and Optimization”
IBM CEE Regional Technical Exchange Budapest, Hungary
“AI for the legal domain: an explainability challenge (extended)”
IBM Vitality Talks Cracow, Poland
“Artificial Intelligence Microservices for NLP”
IBM Vitality Talks Cracow, Poland
“Can we really compare our algorithms? Beyond worst-case time complexity”
IBM Vitality Talks Cracow, Poland
“Data Science Techniques for Law and Justice: Current State of Research and Open Problems”
IBM Vitality Talks Cracow, Poland
“Intelligent Home Automation, combining IoT and Machine Learning”
KrakYourNet 7 Cracow, Poland
“General Parallel File System (GPFS) presentation and administration”
IBM Vitality Talks Cracow, Poland
Academic Service
Community of Experts
-
Community of Experts Member
Jan. 2025 – Present
Eloquence AI — Horizon Europe
Providing AI/LLM expertise and assessing technical proposals for ethical bias mitigation in AI systems.
Reviewer
- Fuzzy Information and Engineering, Taylor & Francis.
- Data & Knowledge Engineering, Elsevier.
- Computing, Springer.
- Expert Systems With Applications, Elsevier. [Certificate]