Zobrazeno 1 - 10
of 10 268
pro vyhledávání: '"Ertekin, A."'
This study introduces SLLMBO, an innovative framework that leverages Large Language Models (LLMs) for hyperparameter optimization (HPO), incorporating dynamic search space adaptability, enhanced parameter landscape exploitation, and a hybrid, novel L
Externí odkaz:
http://arxiv.org/abs/2410.20302
Autor:
Shah, Aagam, Weissbach, Reimar, Griggs, David A., Hart, A. John, Ertekin, Elif, Tawfick, Sameh
With the increasing adoption of metal additive manufacturing (AM), researchers and practitioners are turning to data-driven approaches to optimise printing conditions. Cross-sectional images of melt tracks provide valuable information for tuning proc
Externí odkaz:
http://arxiv.org/abs/2409.18326
Autor:
Guan, Xin, Demchak, Nathaniel, Gupta, Saloni, Wang, Ze, Ertekin Jr., Ediz, Koshiyama, Adriano, Kazim, Emre, Wu, Zekun
Publikováno v:
COLING 2025 Main Conference
The development of unbiased large language models is widely recognized as crucial, yet existing benchmarks fall short in detecting biases due to limited scope, contamination, and lack of a fairness baseline. SAGED(bias) is the first holistic benchmar
Externí odkaz:
http://arxiv.org/abs/2409.11149
Autor:
Wang, Ze, Wu, Zekun, Guan, Xin, Thaler, Michael, Koshiyama, Adriano, Lu, Skylar, Beepath, Sachin, Ertekin Jr., Ediz, Perez-Ortiz, Maria
The use of Large Language Models (LLMs) in hiring has led to legislative actions to protect vulnerable demographic groups. This paper presents a novel framework for benchmarking hierarchical gender hiring bias in Large Language Models (LLMs) for resu
Externí odkaz:
http://arxiv.org/abs/2406.15484
Short-range order (SRO) alters the mechanical properties of technologically relevant structural materials such as medium/high entropy alloys and austenitic stainless steels. In this study, we present a generalized spin cluster expansion (CE) model an
Externí odkaz:
http://arxiv.org/abs/2405.04423
Dismai-Bench: Benchmarking and designing generative models using disordered materials and interfaces
Publikováno v:
Digital Discovery, 2024, 3, 1889-1909
Generative models have received significant attention in recent years for materials science applications, particularly in the area of inverse design for materials discovery. However, these models are usually assessed based on newly generated, unverif
Externí odkaz:
http://arxiv.org/abs/2404.06734
The low symmetry of monoclinic $\beta$-Ga$_2$O$_3$ leads to elaborate intrinsic defects, such as Ga vacancies split amongst multiple lattice sites. These defects contribute to fast, anisotropic Ga diffusion, yet their complexity makes it challenging
Externí odkaz:
http://arxiv.org/abs/2402.09354
In this study, a novel approach is demonstrated for converting calorimeter images from fast simulations to those akin to comprehensive full simulations, utilizing conditional Generative Adversarial Networks (GANs). The concept of pix2pix is tailored
Externí odkaz:
http://arxiv.org/abs/2401.02248
Autor:
Taştan, İrem, Ozdamar Ertekin, Zeynep
Publikováno v:
Qualitative Market Research: An International Journal, 2024, Vol. 27, Issue 5, pp. 724-749.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/QMR-05-2023-0059
Publikováno v:
Elektronika ir Elektrotechnika, Vol 30, Iss 5, Pp 22-30 (2024)
The demand for high-gain, efficient, and cost-effective power converters with simple control mechanisms to connect electric vehicle batteries to the grid is increasing. This study introduces a switched capacitor-based power boost converter circuit to
Externí odkaz:
https://doaj.org/article/b84a7b5786b6462c9824b2b228bddbba