Zobrazeno 1 - 10
of 64 161
pro vyhledávání: '"A. A. Horvath"'
With the increase in the number of parameters in large language models, the process of pre-training and fine-tuning increasingly demands larger volumes of GPU memory. A significant portion of this memory is typically consumed by the optimizer state.
Externí odkaz:
http://arxiv.org/abs/2411.07837
Autor:
Koska, Ben, Horváth, Mojmír
We present a novel 4.5B parameter small language model that can handle multiple input and output modalities, including text, images, videos, and audio. Despite its small size, the model achieves near state-of-the-art performance on a variety of tasks
Externí odkaz:
http://arxiv.org/abs/2411.05903
Autor:
Bojtor, A., Krisztian, D., Korsos, F., Kollarics, S., Parada, G., Kollar, M., Horvath, E., Mettan, X., Markus, B. G., Forro, L., Simon, F.
Publikováno v:
Nanomaterials 14, 1742 (2024)
The measurement and description of the charge-carrier lifetime (tauc) is crucial for the wide-ranging applications of lead-halide perovskites. We present time-resolved microwave-detected photoconductivity decay (TRMCD) measurements and a detailed ana
Externí odkaz:
http://arxiv.org/abs/2411.02754
Binary population synthesis (BPS) is an essential tool for extracting information about massive binary evolution from gravitational-wave (GW) detections of compact object mergers. It has been successfully used to constrain the most likely permutation
Externí odkaz:
http://arxiv.org/abs/2410.11830
Distribution Regression (DR) on stochastic processes describes the learning task of regression on collections of time series. Path signatures, a technique prevalent in stochastic analysis, have been used to solve the DR problem. Recent works have dem
Externí odkaz:
http://arxiv.org/abs/2410.09196
Autor:
Recasens, Pol G., Horváth, Ádám, Gutierrez-Torre, Alberto, Torres, Jordi, Berral, Josep Ll., Pejó, Balázs
Federated learning is increasingly popular as it enables multiple parties with limited datasets and resources to train a high-performing machine learning model collaboratively. However, similarly to other collaborative systems, federated learning is
Externí odkaz:
http://arxiv.org/abs/2410.05020
Non-iid data is prevalent in real-world federated learning problems. Data heterogeneity can come in different types in terms of distribution shifts. In this work, we are interested in the heterogeneity that comes from concept shifts, i.e., shifts in
Externí odkaz:
http://arxiv.org/abs/2410.03497
Statistical data heterogeneity is a significant barrier to convergence in federated learning (FL). While prior work has advanced heterogeneous FL through better optimization objectives, these methods fall short when there is extreme data heterogeneit
Externí odkaz:
http://arxiv.org/abs/2410.03042
We perform a first study of the impact of varying two components of the initial conditions in binary population synthesis of compact binary mergers - the initial mass function, which is made metallicity- and star formation rate-dependent, and the orb
Externí odkaz:
http://arxiv.org/abs/2410.01451
Autor:
Chegaar, Mouna, Horváth, Á. P.
Considering potentials defined by Bessel kernel with Bessel convolution a Kerman-Sawyer type characterization of trace inequality is given. As an application an estimate on the least eigenvalue of Schr\"odinger-Bessel operators is derived.
Externí odkaz:
http://arxiv.org/abs/2409.18445