Zobrazeno 1 - 10
of 1 490
pro vyhledávání: '"A. Precioso"'
Large Language Models have undoubtedly revolutionized the Natural Language Processing field, the current trend being to promote one-model-for-all tasks (sentiment analysis, translation, etc.). However, the statistical mechanisms at work in the larger
Externí odkaz:
http://arxiv.org/abs/2408.13253
Despite extensive research on adversarial training strategies to improve robustness, the decisions of even the most robust deep learning models can still be quite sensitive to imperceptible perturbations, creating serious risks when deploying them fo
Externí odkaz:
http://arxiv.org/abs/2406.18451
Autor:
Sahoo, Sabyasachi, ElAraby, Mostafa, Ngnawe, Jonas, Pequignot, Yann, Precioso, Frederic, Gagne, Christian
Test Time Adaptation (TTA) addresses the problem of distribution shift by enabling pretrained models to learn new features on an unseen domain at test time. However, it poses a significant challenge to maintain a balance between learning new features
Externí odkaz:
http://arxiv.org/abs/2404.03784
Trees are convenient models for obtaining explainable predictions on relatively small datasets. Although there are many proposals for the end-to-end construction of such trees in supervised learning, learning a tree end-to-end for clustering without
Externí odkaz:
http://arxiv.org/abs/2402.12232
Attention-based architectures, in particular transformers, are at the heart of a technological revolution. Interestingly, in addition to helping obtain state-of-the-art results on a wide range of applications, the attention mechanism intrinsically pr
Externí odkaz:
http://arxiv.org/abs/2402.03485
Autor:
Tores, Julie, Sassatelli, Lucile, Wu, Hui-Yin, Bergman, Clement, Andolfi, Lea, Ecrement, Victor, Precioso, Frederic, Devars, Thierry, Guaresi, Magali, Julliard, Virginie, Lecossais, Sarah
In film gender studies, the concept of 'male gaze' refers to the way the characters are portrayed on-screen as objects of desire rather than subjects. In this article, we introduce a novel video-interpretation task, to detect character objectificatio
Externí odkaz:
http://arxiv.org/abs/2401.13296
While HDMaps are a crucial component of autonomous driving, they are expensive to acquire and maintain. Estimating these maps from sensors therefore promises to significantly lighten costs. These estimations however overlook existing HDMaps, with cur
Externí odkaz:
http://arxiv.org/abs/2311.10517
Interpretability is essential for machine learning models to be trusted and deployed in critical domains. However, existing methods for interpreting text models are often complex, lack mathematical foundations, and their performance is not guaranteed
Externí odkaz:
http://arxiv.org/abs/2311.01605
Autor:
Ohl, Louis, Mattei, Pierre-Alexandre, Bouveyron, Charles, Harchaoui, Warith, Leclercq, Mickaël, Droit, Arnaud, Precioso, Frédéric
In the last decade, recent successes in deep clustering majorly involved the Mutual Information (MI) as an unsupervised objective for training neural networks with increasing regularisations. While the quality of the regularisations have been largely
Externí odkaz:
http://arxiv.org/abs/2309.02858
In this paper, we present a novel algorithm called the Hybrid Search algorithm that integrates the Zermelo's Navigation Initial Value Problem with the Ferraro-Mart\'in de Diego-Almagro algorithm to find the optimal route for a vessel to reach its des
Externí odkaz:
http://arxiv.org/abs/2308.02434