From the 1 of 46 papers with an AI index.
5 citations
- Institut Polytechnique de BordeauxFR27 papers
- Université Toulouse-I-CapitoleFR27 papers
- Université Toulouse III - Paul SabatierFR27 papers
- Université Toulouse - Jean JaurèsFR27 papers
- Centre National de la Recherche ScientifiqueFR20 papers
- Université Fédérale de Toulouse Midi-PyrénéesFR9 papers
- National University of SingaporeSG4 papers
- Aix-Marseille UniversitéFR3 papers
- Communauté d'universités et établissements de ToulouseFR3 papers
- École Nationale de l’Aviation CivileFR3 papers
- Institut de Recherche en Astrophysique et PlanétologieFR3 papers
- Lyon 1 UniversitéFR3 papers
25 papers
FleetScape: A Mixed Reality Sandtable for Spatial Supervision and Control of Scalable Drone Fleets
Peisen Xu, Jérémie Garcia, Peter Cleveland +2
FleetScape is a mixed-reality sandtable interface that lets operators supervise large drone fleets through layered spatial visualizations, enabling smooth transitions between manua…
Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging
Ahmed Rayane Kebir, Jose G. Moreno, Lynda Tamine
Conversational information retrieval is challenging since it requires the consideration of the conversation history which potentially gives rise to topic shifts and coreference res…
LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks
Arthur Chiron, Franck Mamalet, Thomas Massena +2
While accuracy, robustness, and calibration are all essential for reliable neural networks, they are often studied separately; developing models that satisfy all three simultaneous…
LipSSD: Lipschitz-Constrained Single-Shot Detection for Adversarially Robust Object Detection
Vincent Lébé, Yannick Prudent, Corentin Friedrich +3
Object detectors have many applications in safety-critical systems, but they are known to be sensitive to worst-case perturbations such as adversarial attacks, which limits their a…
Fun-TSG: A Function-Driven Multivariate Time Series Generator with Variable-Level Anomaly Labeling
Pierre Lotte, André Péninou, Olivier Teste
Reliable evaluation of anomaly detection methods in multivariate time series remains an open challenge, largely due to the limitations of existing benchmark datasets. Current resou…
Turbo-Muon: Almost-Orthogonal Pre-Conditioning for Fast Muon Updates
Thibaut Boissin, Thomas Massena, Franck Mamalet +1
Orthogonality-based optimizers, such as Muon, have recently shown strong performance across large-scale training and community-driven efficiency challenges. However, these methods…