Zobrazeno 1 - 10
of 4 628
pro vyhledávání: '"Gallinari P"'
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Koupaï, Armand Kassaï, Benet, Jorge Misfut, Yin, Yuan, Vittaut, Jean-Noël, Gallinari, Patrick
Publikováno v:
Conference on Neural Information Processing Systems (NeurIPS) 2024
Solving parametric partial differential equations (PDEs) presents significant challenges for data-driven methods due to the sensitivity of spatio-temporal dynamics to variations in PDE parameters. Machine learning approaches often struggle to capture
Externí odkaz:
http://arxiv.org/abs/2410.23889
Autor:
Boudec, Lise Le, de Bezenac, Emmanuel, Serrano, Louis, Regueiro-Espino, Ramon Daniel, Yin, Yuan, Gallinari, Patrick
Physics-informed deep learning often faces optimization challenges due to the complexity of solving partial differential equations (PDEs), which involve exploring large solution spaces, require numerous iterations, and can lead to unstable training.
Externí odkaz:
http://arxiv.org/abs/2410.06820
Large Language Models (LLMs) often encounter conflicts between their learned, internal (parametric knowledge, PK) and external knowledge provided during inference (contextual knowledge, CK). Understanding how LLMs models prioritize one knowledge sour
Externí odkaz:
http://arxiv.org/abs/2410.05817
Solving time-dependent parametric partial differential equations (PDEs) is challenging, as models must adapt to variations in parameters such as coefficients, forcing terms, and boundary conditions. Data-driven neural solvers either train on data sam
Externí odkaz:
http://arxiv.org/abs/2410.03437
Current pre-trained cross-lingual sentence encoders approaches use sentence-level objectives only. This can lead to loss of information, especially for tokens, which then degrades the sentence representation. We propose MEXMA, a novel approach that i
Externí odkaz:
http://arxiv.org/abs/2409.12737
Autor:
Yagoubi, Mouadh, Danan, David, Leyli-abadi, Milad, Brunet, Jean-Patrick, Mazari, Jocelyn Ahmed, Bonnet, Florent, gmati, maroua, Farjallah, Asma, Cinnella, Paola, Gallinari, Patrick, Schoenauer, Marc
The integration of machine learning (ML) techniques for addressing intricate physics problems is increasingly recognized as a promising avenue for expediting simulations. However, assessing ML-derived physical models poses a significant challenge for
Externí odkaz:
http://arxiv.org/abs/2407.01641
Publikováno v:
Conference on Neural Information Processing Systems (NeurIPS) 2024
We present AROMA (Attentive Reduced Order Model with Attention), a framework designed to enhance the modeling of partial differential equations (PDEs) using local neural fields. Our flexible encoder-decoder architecture can obtain smooth latent repre
Externí odkaz:
http://arxiv.org/abs/2406.02176
Autor:
Yagoubi, Mouadh, Leyli-Abadi, Milad, Danan, David, Brunet, Jean-Patrick, Mazari, Jocelyn Ahmed, Bonnet, Florent, Farjallah, Asma, Schoenauer, Marc, Gallinari, Patrick
The use of machine learning (ML) techniques to solve complex physical problems has been considered recently as a promising approach. However, the evaluation of such learned physical models remains an important issue for industrial use. The aim of thi
Externí odkaz:
http://arxiv.org/abs/2403.01623
Autor:
Bronnec, Florian Le, Duong, Song, Ravaut, Mathieu, Allauzen, Alexandre, Chen, Nancy F., Guigue, Vincent, Lumbreras, Alberto, Soulier, Laure, Gallinari, Patrick
State-space models are a low-complexity alternative to transformers for encoding long sequences and capturing long-term dependencies. We propose LOCOST: an encoder-decoder architecture based on state-space models for conditional text generation with
Externí odkaz:
http://arxiv.org/abs/2401.17919