241 citations
- Universidad de ZaragozaES5 papers
- Arts et MétiersFR4 papers
- Universidad Politécnica de MadridES4 papers
- CNRS@CREATE Ltd (Singapore)SG3 papers
- Instituto Tecnológico de AragónES2 papers
- Laboratoire Procédés et Ingénierie en Mécanique et MatériauxFR2 papers
- All4tec (France)FR1 paper
- Centre National de la Recherche ScientifiqueFR1 paper
- Dassault Aviation (France)FR1 paper
- École Normale Supérieure de LyonFR1 paper
- European Organization for Nuclear ResearchCH1 paper
- Institute for Basic ScienceKR1 paper
13 papers
mOSCAR: A Large-scale Multilingual and Multimodal Document-level Corpus
Matthieu Futeral, Armel Zebaze, Pedro Ortiz Suarez +5
Multimodal Large Language Models (mLLMs) are trained on a large amount of text-image data. While most mLLMs are trained on caption-like data only, Alayrac et al. (2022) showed that…
Efficient Wait-Free Linearizable Implementations of Approximate Bounded Counters Using Read-Write Registers
Colette Johnen, Adnane Khattabi, Alessia Milani +1
Relaxing the sequential specification of a shared object is a way to obtain an implementation with better performance compared to implementing the original specification. We apply…
Thermodynamics-informed super-resolution of scarce temporal dynamics data
Carlos Bermejo-Barbanoj, Beatriz Moya, Alberto Badías +2
We present a method to increase the resolution of measurements of a physical system and subsequently predict its time evolution using thermodynamics-aware neural networks. Our meth…
Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems
Quercus Hernández, Alberto Badías, Francisco Chinesta +1
We develop inductive biases for the machine learning of complex physical systems based on the port-Hamiltonian formalism. To satisfy by construction the principles of thermodynamic…
Thermodynamics-informed neural networks for physically realistic mixed reality
Quercus Hernández, Alberto Badías, Francisco Chinesta +1
The imminent impact of immersive technologies in society urges for active research in real-time and interactive physics simulation for virtual worlds to be realistic. In this conte…
Thermodynamics-informed graph neural networks
Quercus Hernández, Alberto Badías, Francisco Chinesta +1
In this paper we present a deep learning method to predict the temporal evolution of dissipative dynamic systems. We propose using both geometric and thermodynamic inductive biases…