1.2k citations
- CentraleSupélecFR19 papers
- Université Paris-SaclayFR19 papers
- University of OuluFI15 papers
- Centre National de la Recherche ScientifiqueFR12 papers
- SupélecFR12 papers
- Huawei Technologies (China)CN11 papers
- Télécom ParisFR11 papers
- Virginia TechUS11 papers
- Institut national de recherche en sciences et technologies du numériqueFR9 papers
- Laboratoire Traitement et Communication de l’InformationFR9 papers
- Laboratoire des signaux et systèmesFR8 papers
- École Normale Supérieure - PSLFR7 papers
13 papers · 1 filter
Combining Pre- and Post-Demosaicking Noise Removal for RAW Video
Marco Sánchez-Beeckman, Antoni Buades, Nicola Brandonisio +1
Denoising is one of the fundamental steps of the processing pipeline that converts data captured by a camera sensor into a display-ready image or video. It is generally performed e…
Pricing Filtering in Dantzig-Wolfe Decomposition
Abdellah Bulaich Mehamdi, Mathieu Lacroix, Sébastien Martin
Column generation is used alongside Dantzig-Wolfe Decomposition, especially for linear programs having a decomposable pricing step requiring to solve numerous independent pricing s…
Zero-shot Model-based Reinforcement Learning using Large Language Models
Abdelhakim Benechehab, Youssef Attia El Hili, Ambroise Odonnat +6
The emerging zero-shot capabilities of Large Language Models (LLMs) have led to their applications in areas extending well beyond natural language processing tasks. In reinforcemen…
Random matrix theory improved Fréchet mean of symmetric positive definite matrices
Florent Bouchard, Ammar Mian, Malik Tiomoko +2
In this study, we consider the realm of covariance matrices in machine learning, particularly focusing on computing Fréchet means on the manifold of symmetric positive definite mat…
Modelling the 5G Energy Consumption using Real-world Data: Energy Fingerprint is All You Need
Tingwei Chen, Yantao Wang, Hanzhi Chen +5
The introduction of 5G technology has revolutionized communications, enabling unprecedented capacity, connectivity, and ultra-fast, reliable communications. However, this leap has…
MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
Renchunzi Xie, Ambroise Odonnat, Vasilii Feofanov +3
Leveraging the models' outputs, specifically the logits, is a common approach to estimating the test accuracy of a pre-trained neural network on out-of-distribution (OOD) samples w…