Welcome to the
Operational Research and AI Lab at LIX
ORAILIX is an AI research team at the Laboratoire d’Informatique de l’X (LIX) at École Polytechnique, directed by Prof. Sonia Vanier. Founded in September 2024, our research projects aim to develop new hybrid approaches that combine the power of machine learning algorithms and architectures with the robustness of operational research methods.
News
Our mission is to develop secure, ethical, and robust AI-based systems that address real-world challenges.
Launch of the Master Trustworthy and Responsible AI (TRAI)
Faced with the rapid rise of artificial intelligence and the various challenges it raises (societal, environmental and regulatory), L'X is strengthening its commitment to responsible AI through this innovative master's degree, taught entirely in English.
AI Action Summit
PhD students contributed drafting the AI Summit Paris Report at Ecole Polytechnique
Publications
- MUCH: A Multilingual Claim Hallucination BenchmarkJérémie Dentan, Alexi Canesse, Davide Buscaldi, Aymen Shabou, Sonia Vanier (2025).
- Simulation-Driven Railway Delay Prediction: An Imitation Learning Approach Clément Elliker, Sonia Vanier, Jesse Read (AAAI-26).
- Guess or Recall? Training CNNs to Classify and Localize Memorization in LLMs Jérémie Dentan, Davide Buscaldi, Sonia Vanier (AAAI-26).
- Dentan, Jérémie, Davide Buscaldi, Aymen Shabou and Sonia Vanier. “Predicting memorization within Large Language Models fine-tuned for classification.” (2024).
- I-GLIDE: Input Groups for Latent Health Indicators in Degradation Estimation accepted at ECML PKDD 2025 for presentation.
- Uncertainty Quantification as a Complementary Latent Health Indicator for Remaining Useful Life Prediction on Turbofan Engines has been accepted at MIMAR 2025.
- PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models" has been accepted at CVPR 2025.
Meet the team
Faculty, postdocs, PhD candidates and visiting researchers — working across hybrid ML and operations research, trustworthy AI, and AI for mobilities.
See all members
Our two Research Chairs
Research & partnerships
The team sits at the intersection of LIX, École Polytechnique and Institut Polytechnique de Paris, with industry chairs powering work across trustworthy AI, mobilities, and hybrid ML + operations research. Hover a node to highlight its connections.
In the press
Selected coverage of ORAILIX research, partnerships and chair launches.
Rénovation du campus, investissement dans l'IA : Polytechnique veut lever 200 millions d'euros
SNCF Group, LIX and Fondation X create the AI & Mobility Chair
Crédit Agricole S.A. et l'École Polytechnique inaugurent la Chaire IA de Confiance et Responsable
Chaire Intelligence Artificielle & Optimisation pour les Mobilités
Polytechnique et SNCF créent une chaire IA appliquée aux mobilités
Sonia Vanier — speaker profile on AI & Operations Research
Crédit Agricole et l'École Polytechnique inaugurent la Chaire IA de Confiance et Responsable
Le Groupe SNCF et l'École Polytechnique lancent la chaire IA et Optimisation pour les Mobilités
