Zobrazeno 1 - 10
of 34 312
pro vyhledávání: '"A, Zielinski"'
Model merging combines knowledge from task-specific models into a unified multi-task model to avoid joint training on all task data. However, current methods face challenges due to representation bias, which can interfere with tasks performance. As a
Externí odkaz:
http://arxiv.org/abs/2412.17023
Autor:
Siwak, M., Kóspál, Á., Ábrahám, P., Marton, G., Zieliński, P., Gromadzki, M., Wyrzykowski, Ł., Nagy, Z., Szilágyi, M., Potter, S. B., Sefako, R., Worters, H. L., Buckley, D. A. H., Giannini, T., Fiorellino, E., de Miera, F. Cruz-Sáenz, Kun, M., Szabó, Zs. M., Lucas, P. W., Krzesiński, J., Zakrzewski, B., Ogłoza, W., Pál, A., Cseh, B., Horti-Dávid, Á., Joó, A., Kalup, Cs., Kriskovics, L., Sódor, Á., Szakáts, R., Vinkó, J.
Context. We analyse multi-colour photometric and spectroscopic observations of a Young Stellar Object Gaia20bdk. Aims. We aim to investigate the exact nature of the eruptive phenomenon that the star has been experiencing since 2018. Methods. We use p
Externí odkaz:
http://arxiv.org/abs/2412.07697
Autor:
Przewięźlikowski, Marcin, Balestriero, Randall, Jasiński, Wojciech, Śmieja, Marek, Zieliński, Bartosz
Masked Image Modeling (MIM) has emerged as a popular method for Self-Supervised Learning (SSL) of visual representations. However, for high-level perception tasks, MIM-pretrained models offer lower out-of-the-box representation quality than the Joint
Externí odkaz:
http://arxiv.org/abs/2412.03215
Deep Learning (DL) models are often black boxes, making their decision-making processes difficult to interpret. This lack of transparency has driven advancements in eXplainable Artificial Intelligence (XAI), a field dedicated to clarifying the reason
Externí odkaz:
http://arxiv.org/abs/2412.02399
The problem is in the estimation of the fraction of population with a sensitive characteristic. We consider the Item Count Technique an indirect method of questioning designed to protect respondents' privacy. The exact confidence interval for the sen
Externí odkaz:
http://arxiv.org/abs/2410.14301
Autor:
Merta, Łukasz, Zieliński, Marcin
In this note, we examine the arrangements of lines and configurations of points that emerge from Fermat (von Dyck) and Komiya-Kuribayashi quartics. These quartics are characterized by having the maximum number of lines of maximal tangency, that is, l
Externí odkaz:
http://arxiv.org/abs/2410.13997
Autor:
Kasperski, Adam, Zielinski, Pawel
In this paper, the recoverable robust shortest path problem in acyclic digraphs is considered. The interval budgeted uncertainty representation is used to model the uncertain second-stage costs. The computational complexity of this problem has been o
Externí odkaz:
http://arxiv.org/abs/2410.09425
Autor:
Zieliński, Krzysztof, Penning, Ryan, Blumberg, Bruce, Schlette, Christian, Kjærgaard, Mikkel Baun
Improving robot deployment is a central step towards speeding up robot-based automation in manufacturing. A main challenge in robot deployment is how to best place the robot within the workcell. To tackle this challenge, we combine two knowledge sour
Externí odkaz:
http://arxiv.org/abs/2410.00484
Capturing real-world 3D spaces as point clouds is efficient and descriptive, but it comes with sensor errors and lacks object parametrization. These limitations render point clouds unsuitable for various real-world applications, such as robot program
Externí odkaz:
http://arxiv.org/abs/2410.00479
Autor:
Zielinski, Sebastian, Nüßlein, Jonas, Kölle, Michael, Gabor, Thomas, Linnhoff-Popien, Claudia, Feld, Sebastian
As contemporary quantum computers do not possess error correction, any calculation performed by these devices can be considered an involuntary approximation. To solve a problem on a quantum annealer, it has to be expressed as an instance of Quadratic
Externí odkaz:
http://arxiv.org/abs/2409.15891