Zobrazeno 1 - 10
of 1 388
pro vyhledávání: '"Azizpour, A."'
Graphons are continuous models that represent the structure of graphs and allow the generation of graphs of varying sizes. We propose Scalable Implicit Graphon Learning (SIGL), a scalable method that combines implicit neural representations (INRs) an
Externí odkaz:
http://arxiv.org/abs/2410.17464
Modeling complex systems that evolve toward equilibrium distributions is important in various physical applications, including molecular dynamics and robotic control. These systems often follow the stochastic gradient descent of an underlying energy
Externí odkaz:
http://arxiv.org/abs/2410.11433
The field of medical image segmentation is hindered by the scarcity of large, publicly available annotated datasets. Not all datasets are made public for privacy reasons, and creating annotations for a large dataset is time-consuming and expensive, a
Externí odkaz:
http://arxiv.org/abs/2409.20253
Inverse problems have many applications in science and engineering. In Computer vision, several image restoration tasks such as inpainting, deblurring, and super-resolution can be formally modeled as inverse problems. Recently, methods have been deve
Externí odkaz:
http://arxiv.org/abs/2407.20784
Are score function estimators an underestimated approach to learning with $k$-subset sampling? Sampling $k$-subsets is a fundamental operation in many machine learning tasks that is not amenable to differentiable parametrization, impeding gradient-ba
Externí odkaz:
http://arxiv.org/abs/2407.16058
Urbanization advances at unprecedented rates, resulting in negative effects on the environment and human well-being. Remote sensing has the potential to mitigate these effects by supporting sustainable development strategies with accurate information
Externí odkaz:
http://arxiv.org/abs/2406.17458
Autor:
Vinuesa, Ricardo, Rabault, Jean, Azizpour, Hossein, Bauer, Stefan, Brunton, Bingni W., Elofsson, Arne, Jarlebring, Elias, Kjellstrom, Hedvig, Markidis, Stefano, Marlevi, David, Cinnella, Paola, Brunton, Steven L.
Technological advancements have substantially increased computational power and data availability, enabling the application of powerful machine-learning (ML) techniques across various fields. However, our ability to leverage ML methods for scientific
Externí odkaz:
http://arxiv.org/abs/2405.04161
Recent advances in generative AI have led to the development of techniques to generate visually realistic synthetic video. While a number of techniques have been developed to detect AI-generated synthetic images, in this paper we show that synthetic
Externí odkaz:
http://arxiv.org/abs/2404.15955
As generative AI progresses rapidly, new synthetic image generators continue to emerge at a swift pace. Traditional detection methods face two main challenges in adapting to these generators: the forensic traces of synthetic images from new technique
Externí odkaz:
http://arxiv.org/abs/2404.08814
Autor:
Nilsson, Alfred, Wijk, Klas, Gutha, Sai bharath chandra, Englesson, Erik, Hotti, Alexandra, Saccardi, Carlo, Kviman, Oskar, Lagergren, Jens, Vinuesa, Ricardo, Azizpour, Hossein
Feature selection is a crucial task in settings where data is high-dimensional or acquiring the full set of features is costly. Recent developments in neural network-based embedded feature selection show promising results across a wide range of appli
Externí odkaz:
http://arxiv.org/abs/2403.00563