Zobrazeno 1 - 10
of 516
pro vyhledávání: '"Vincent Pascal"'
In this work, we tackle a challenging and extreme form of subpopulation shift, which is termed compositional shift. Under compositional shifts, some combinations of attributes are totally absent from the training distribution but present in the test
Externí odkaz:
http://arxiv.org/abs/2410.06303
APOLLO3 homogenization techniques for transport core calculations—application to the ASTRID CFV core
Autor:
Jean-François Vidal, Pascal Archier, Bastien Faure, Valentin Jouault, Jean-Marc Palau, Vincent Pascal, Gérald Rimpault, Fabien Auffret, Laurent Graziano, Emiliano Masiello, Simone Santandrea
Publikováno v:
Nuclear Engineering and Technology, Vol 49, Iss 7, Pp 1379-1387 (2017)
This paper presents a comparison of homogenization techniques implemented in the APOLLO3 platform for transport core calculations: standard scalar flux weighting and new flux–moment homogenization, in different combinations with (or without) leakag
Externí odkaz:
https://doaj.org/article/477c8ca3a3094f79947d6b834be5c8d7
Autor:
Eastwood, Cian, von Kügelgen, Julius, Ericsson, Linus, Bouchacourt, Diane, Vincent, Pascal, Schölkopf, Bernhard, Ibrahim, Mark
Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown at training time, it is difficult to deduce a priori which attributes
Externí odkaz:
http://arxiv.org/abs/2311.08815
Autor:
Klissarov, Martin, D'Oro, Pierluca, Sodhani, Shagun, Raileanu, Roberta, Bacon, Pierre-Luc, Vincent, Pascal, Zhang, Amy, Henaff, Mikael
Exploring rich environments and evaluating one's actions without prior knowledge is immensely challenging. In this paper, we propose Motif, a general method to interface such prior knowledge from a Large Language Model (LLM) with an agent. Motif is b
Externí odkaz:
http://arxiv.org/abs/2310.00166
Autor:
Pezeshki, Mohammad, Bouchacourt, Diane, Ibrahim, Mark, Ballas, Nicolas, Vincent, Pascal, Lopez-Paz, David
Environment annotations are essential for the success of many out-of-distribution (OOD) generalization methods. Unfortunately, these are costly to obtain and often limited by human annotators' biases. To achieve robust generalization, it is essential
Externí odkaz:
http://arxiv.org/abs/2309.16748
Publikováno v:
EPJ Web of Conferences, Vol 247, p 06044 (2021)
Sodium-cooled Fast Reactors (SFRs) remain a potential candidate to meet future energy needs. In addition, the SFRs experimental feedback is considerable, for instance, the French research program has considered experimental facilities including the S
Externí odkaz:
https://doaj.org/article/5b99b66d5a4347d9b17e16c85be4a7ee
Autor:
Bordes, Florian, Shekhar, Shashank, Ibrahim, Mark, Bouchacourt, Diane, Vincent, Pascal, Morcos, Ari S.
Synthetic image datasets offer unmatched advantages for designing and evaluating deep neural networks: they make it possible to (i) render as many data samples as needed, (ii) precisely control each scene and yield granular ground truth labels (and c
Externí odkaz:
http://arxiv.org/abs/2308.03977
Autor:
Bar, Amir, Bordes, Florian, Shocher, Assaf, Assran, Mahmoud, Vincent, Pascal, Ballas, Nicolas, Darrell, Trevor, Globerson, Amir, LeCun, Yann
Masked Image Modeling (MIM) is a promising self-supervised learning approach that enables learning from unlabeled images. Despite its recent success, learning good representations through MIM remains challenging because it requires predicting the rig
Externí odkaz:
http://arxiv.org/abs/2308.00566
Disentanglement aims to recover meaningful latent ground-truth factors from the observed distribution solely, and is formalized through the theory of identifiability. The identifiability of independent latent factors is proven to be impossible in the
Externí odkaz:
http://arxiv.org/abs/2306.16334
Self-supervised learning (SSL) algorithms can produce useful image representations by learning to associate different parts of natural images with one another. However, when taken to the extreme, SSL models can unintendedly memorize specific parts in
Externí odkaz:
http://arxiv.org/abs/2304.13850