Zobrazeno 1 - 10
of 2 418
pro vyhledávání: '"Park Sang Hyun"'
The recent emergence of latent diffusion models such as SDXL and SD 1.5 has shown significant capability in generating highly detailed and realistic images. Despite their remarkable ability to produce images, generating accurate text within images st
Externí odkaz:
http://arxiv.org/abs/2406.00505
Electroencephalography (EEG) motor imagery (MI) classification is a fundamental, yet challenging task due to the variation of signals between individuals i.e., inter-subject variability. Previous approaches try to mitigate this using task-specific (T
Externí odkaz:
http://arxiv.org/abs/2405.19346
The emergence of various adapters, including Low-Rank Adaptation (LoRA) applied from the field of natural language processing, has allowed diffusion models to personalize image generation at a low cost. However, due to the various challenges includin
Externí odkaz:
http://arxiv.org/abs/2404.07554
Autor:
Park Sang Hyun, Lee Sung-Gyu, Baek Soojeong, Ha Taewoo, Lee Sanghyub, Min Bumki, Zhang Shuang, Lawrence Mark, Kim Teun-Teun
Publikováno v:
Nanophotonics, Vol 9, Iss 5, Pp 1031-1039 (2020)
Exceptional points (EPs), also known as non-Hermitian degeneracies, have been observed in parity-time symmetric metasurfaces as parity-time symmetry breaking points. However, the parity-time symmetry condition puts constraints on the metasurface para
Externí odkaz:
https://doaj.org/article/75620aae56174333a4c3e6c341ddd174
Publikováno v:
Zhongguo Jianchuan Yanjiu, Vol 14, Iss S2, Pp 23-31 (2019)
[Objectives] This paper focusses on deriving formulations to predict the ultimate strength of both intact and damaged steel ring-stiffened cylinders subjected to hydrostatic pressure. The damage scenario considered in this study can represent the col
Externí odkaz:
https://doaj.org/article/25683c76b42f4e61a920e55deca32b10
Autor:
Kim, Soopil, An, Sion, Chikontwe, Philip, Kang, Myeongkyun, Adeli, Ehsan, Pohl, Kilian M., Park, Sang Hyun
Logical anomalies (LA) refer to data violating underlying logical constraints e.g., the quantity, arrangement, or composition of components within an image. Detecting accurately such anomalies requires models to reason about various component types t
Externí odkaz:
http://arxiv.org/abs/2312.13783
Artificial lattices have been used as a platform to extend the application of topological physics beyond electronic systems. Here, using the two-dimensional Lieb lattice as a prototypical example, we show that an array of disks which each support loc
Externí odkaz:
http://arxiv.org/abs/2305.12609
Publikováno v:
MICCAI 2023
As acquiring MRIs is expensive, neuroscience studies struggle to attain a sufficient number of them for properly training deep learning models. This challenge could be reduced by MRI synthesis, for which Generative Adversarial Networks (GANs) are pop
Externí odkaz:
http://arxiv.org/abs/2212.08034
Autor:
Baek, Soojeong, Park, Sang Hyun, Oh, Donghak, Lee, Kanghee, Lee, Sangha, Lim, Hosub, Ha, Taewoo, Park, Hyun-Sung, Zhang, Shuang, Yang, Lan, Min, Bumki, Kim, Teun-Teun
Non-Hermitian degeneracies, also known as exceptional points (EPs), have been the focus of much attention due to their singular eigenvalue surface structure. Nevertheless, as pertaining to a non-Hermitian metasurface platform, the reduction of an eig
Externí odkaz:
http://arxiv.org/abs/2208.10675
Autor:
Chikontwe, Philip, Nam, Soo Jeong, Go, Heounjeong, Kim, Meejeong, Sung, Hyun Jung, Park, Sang Hyun
Whole slide image (WSI) classification is a fundamental task for the diagnosis and treatment of diseases; but, curation of accurate labels is time-consuming and limits the application of fully-supervised methods. To address this, multiple instance le
Externí odkaz:
http://arxiv.org/abs/2206.10878