Zobrazeno 1 - 10
of 3 763
pro vyhledávání: '"Perez, P. C."'
Autor:
Liu, Haozhe, Liu, Shikun, Zhou, Zijian, Xu, Mengmeng, Xie, Yanping, Han, Xiao, Pérez, Juan C., Liu, Ding, Kahatapitiya, Kumara, Jia, Menglin, Wu, Jui-Chieh, He, Sen, Xiang, Tao, Schmidhuber, Jürgen, Pérez-Rúa, Juan-Manuel
We introduce MarDini, a new family of video diffusion models that integrate the advantages of masked auto-regression (MAR) into a unified diffusion model (DM) framework. Here, MAR handles temporal planning, while DM focuses on spatial generation in a
Externí odkaz:
http://arxiv.org/abs/2410.20280
Autor:
S, Gabriel Pérez, Pérez, Juan C., Alfarra, Motasem, Zarzar, Jesús, Rojas, Sara, Ghanem, Bernard, Arbeláez, Pablo
This paper presents preliminary work on a novel connection between certified robustness in machine learning and the modeling of 3D objects. We highlight an intriguing link between the Maximal Certified Radius (MCR) of a classifier representing a spac
Externí odkaz:
http://arxiv.org/abs/2408.13135
Efficient and accurate prediction of physical systems is important even when the rules of those systems cannot be easily learned. Reservoir computing, a type of recurrent neural network with fixed nonlinear units, is one such prediction method and is
Externí odkaz:
http://arxiv.org/abs/2408.09223
Time crystals are many-body systems that spontaneously break time-translation symmetry, and thus exhibit long-range spatiotemporal order and robust periodic motion. Recent results have demonstrated how to build time-crystal phases in driven diffusive
Externí odkaz:
http://arxiv.org/abs/2406.08581
Autor:
Pérez, Juan C., Pardo, Alejandro, Soldan, Mattia, Itani, Hani, Leon-Alcazar, Juan, Ghanem, Bernard
This study investigates whether Compressed-Language Models (CLMs), i.e. language models operating on raw byte streams from Compressed File Formats~(CFFs), can understand files compressed by CFFs. We focus on the JPEG format as a representative CFF, g
Externí odkaz:
http://arxiv.org/abs/2405.17146
Autor:
Bourouaine, Sofiane, Perez, Jean C., Chandran, Benjamin D. G., Jagarlamudi, Vamsee K., Raouafi, Nour E., Halekas, Jasper S.
In this work we analyze plasma and magnetic field data provided by the Parker Solar Probe (\emph{PSP}) and Solar Orbiter (\emph{SO}) missions to investigate the radial evolution of the heating of Alfv\'enic slow wind (ASW) by imbalanced Alfv\'en-Wave
Externí odkaz:
http://arxiv.org/abs/2403.17352
Autor:
Castillo, Angela, Kohler, Jonas, Pérez, Juan C., Pérez, Juan Pablo, Pumarola, Albert, Ghanem, Bernard, Arbeláez, Pablo, Thabet, Ali
This paper presents a comprehensive study on the role of Classifier-Free Guidance (CFG) in text-conditioned diffusion models from the perspective of inference efficiency. In particular, we relax the default choice of applying CFG in all diffusion ste
Externí odkaz:
http://arxiv.org/abs/2312.12487
Faithfully reconstructing 3D geometry and generating novel views of scenes are critical tasks in 3D computer vision. Despite the widespread use of image augmentations across computer vision applications, their potential remains underexplored when lea
Externí odkaz:
http://arxiv.org/abs/2306.08904
Autor:
Alfarra, Motasem, Itani, Hani, Pardo, Alejandro, Alhuwaider, Shyma, Ramazanova, Merey, Pérez, Juan C., Cai, Zhipeng, Müller, Matthias, Ghanem, Bernard
This paper proposes a novel online evaluation protocol for Test Time Adaptation (TTA) methods, which penalizes slower methods by providing them with fewer samples for adaptation. TTA methods leverage unlabeled data at test time to adapt to distributi
Externí odkaz:
http://arxiv.org/abs/2304.04795
Publikováno v:
Phys. Rev. E 108, 014107 (2023)
Large deviation theory provides the framework to study the probability of rare fluctuations of time-averaged observables, opening new avenues of research in nonequilibrium physics. One of the most appealing results within this context are dynamical p
Externí odkaz:
http://arxiv.org/abs/2301.10262