Zobrazeno 1 - 10
of 66 435
pro vyhledávání: '"Horváth, A."'
Autor:
Demidovich, Yury, Ostroukhov, Petr, Malinovsky, Grigory, Horváth, Samuel, Takáč, Martin, Richtárik, Peter, Gorbunov, Eduard
Non-convex Machine Learning problems typically do not adhere to the standard smoothness assumption. Based on empirical findings, Zhang et al. (2020b) proposed a more realistic generalized $(L_0, L_1)$-smoothness assumption, though it remains largely
Externí odkaz:
http://arxiv.org/abs/2412.02781
Autor:
Ponkshe, Kaustubh, Singhal, Raghav, Gorbunov, Eduard, Tumanov, Alexey, Horvath, Samuel, Vepakomma, Praneeth
Low-rank adapters have become a standard approach for efficiently fine-tuning large language models (LLMs), but they often fall short of achieving the performance of full fine-tuning. We propose a method, LoRA Silver Bullet or LoRA-SB, that approxima
Externí odkaz:
http://arxiv.org/abs/2411.19557
In a recent article we introduced a new class of shapes, called \emph{soft cells} which fill space as \emph{soft tilings} without gaps and overlaps while minimizing the number of sharp corners. We defined the \textit{edge bending algorithm} deforming
Externí odkaz:
http://arxiv.org/abs/2412.04491
The statistics of fluctuations on large regions of space encodes universal properties of many-body systems. At equilibrium, it is described by thermodynamics. However, away from equilibrium such as after quantum quenches, the fundamental principles a
Externí odkaz:
http://arxiv.org/abs/2411.14406
Autor:
Puel, Tharnier O., Turflinger, Adam T., Horvath, Sebastian P., Thompson, Jeff D., Flatté, Michael E.
We propose a new method for converting single microwave photons to single optical sideband photons based on spinful impurities in magnetic materials. This hybrid system is advantageous over previous proposals because (i) the implementation allows muc
Externí odkaz:
http://arxiv.org/abs/2411.12870
Autor:
Horváth, Markó, Tamási, Tímea
In dynamic vehicle routing problems (DVRPs), some part of the information is revealed or changed on the fly, and the decision maker has the opportunity to re-plan the vehicle routes during their execution, reflecting on the changes. Accordingly, the
Externí odkaz:
http://arxiv.org/abs/2411.12406
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
Autor:
Horvath, Andras
Stable diffusion models have ushered in a new era of advancements in image generation, currently reigning as the state-of-the-art approach, exhibiting unparalleled performance. The process of diffusion, accompanied by denoising through iterative conv
Externí odkaz:
http://arxiv.org/abs/2410.19798