Onofrio Semeraro, Michele Alessandro Bucci, Lionel Mathelin, Luigi Marra, Amine Saibi. From robotics to fluid dynamics: opportunities and pitfalls of Reinforcement Learning in flow control. iTi Workshop on Structure and control of wall-bounded turbulent flows, Jul 2025, Bertinoro, Italy. ⟨hal-05379587⟩
Amine Saibi, Lionel Mathelin, Onofrio Semeraro. A Multistep Reinforcement Learning Control of Shear Flows in Minimal Input–Output Plants Under Large Time-delays. Flow, Turbulence and Combustion, 2025, 115 (3), pp.1379-1402. ⟨10.1007/s10494-025-00697-w⟩. ⟨hal-05379450⟩
Eliott Pradeleix, Rémy Hosseinkhan-Boucher, Alena Shilova, Onofrio Semeraro, Lionel Mathelin. Learning Meets Differential Equations: From Theory to Applications Learning non-Markovian Dynamical Systems with Signature-based Encoders. ML-DE 2025 - 2nd Workshop on "Machine Learning Meets Differential Equations: From Theory to Applications",, Oct 2025, Bologna, Italy. pp.1-25. ⟨hal-05379481⟩
Mathurin Videau, Alessandro Leite, Marc Schoenauer, Olivier Teytaud. Mixture of Experts for Image Classification: What's the Sweet Spot?. Transactions on Machine Learning Research Journal, 2025. ⟨hal-05329451⟩
Antoine Szatkownik, Aurélien Decelle, Beatriz Seoane, Nicolas Béreux, Léo Planche, et al.. PRIVET: Privacy Metric Based On Extreme Value Theory. 2025. ⟨hal-05326013⟩
Tristan Bilot, Baoxiang Jiang, Zefeng Li, Nour El Madhoun, Khaldoun Al Agha, et al.. Sometimes Simpler is Better: A Comprehensive Analysis of State-of-the-Art Provenance-Based Intrusion Detection Systems. USENIX Security 2025, Aug 2025, Seattle, United States. ⟨hal-05245280⟩
Baoxiang Jiang, Tristan Bilot, Nour El Madhoun, Khaldoun Al Agha, Anis Zouaoui, et al.. ORTHRUS: Achieving High Quality of Attribution in Provenance-based Intrusion Detection Systems. USENIX Security 2025, Aug 2025, Seattle, United States. ⟨hal-05245139⟩
Djamel Mesbah, Nour El Madhoun, Khaldoun Al Agha, Hani Chalouati. Exploring NLP Techniques for Code Smell Detection: A Comparative Study. The 39th International Conference on Advanced Information Networking and Applications (AINA-2025), Apr 2025, Barcelone, Spain. ⟨hal-05014865⟩
Stéphane Rivaud, Louis Fournier, Thomas Pumir, Eugene Belilovsky, Michael Eickenberg, et al.. PETRA: Parallel End-to-end Training with Reversible Architectures. The Thirteenth International Conference on Learning Representations, 2025, Singapour, Singapore. ⟨hal-04594647v2⟩