Zobrazeno 1 - 10
of 9 656
pro vyhledávání: '"Lee In-Bok"'
Autor:
Lee, Seanie, Seong, Haebin, Lee, Dong Bok, Kang, Minki, Chen, Xiaoyin, Wagner, Dominik, Bengio, Yoshua, Lee, Juho, Hwang, Sung Ju
Safety guard models that detect malicious queries aimed at large language models (LLMs) are essential for ensuring the secure and responsible deployment of LLMs in real-world applications. However, deploying existing safety guard models with billions
Externí odkaz:
http://arxiv.org/abs/2410.01524
Autor:
Lee, Dong Bok, Zhang, Aoxuan Silvia, Kim, Byungjoo, Park, Junhyeon, Lee, Juho, Hwang, Sung Ju, Lee, Hae Beom
In this paper, we address the problem of cost-sensitive multi-fidelity Bayesian Optimization (BO) for efficient hyperparameter optimization (HPO). Specifically, we assume a scenario where users want to early-stop the BO when the performance improveme
Externí odkaz:
http://arxiv.org/abs/2405.17918
Publikováno v:
World Literature Today, 2018 Feb 01. 92(1), 88-89.
Externí odkaz:
https://www.jstor.org/stable/10.7588/worllitetoda.92.1.0088b
Dataset distillation methods have achieved remarkable success in distilling a large dataset into a small set of representative samples. However, they are not designed to produce a distilled dataset that can be effectively used for facilitating self-s
Externí odkaz:
http://arxiv.org/abs/2310.06511
Autor:
kwon， hyun-ju
Publikováno v:
The study of Korean Poetry and Culture. 47:235-260
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a18234337301d861036d0145ac478468
https://doi.org/10.52530/kpac.2021.47.9
https://doi.org/10.52530/kpac.2021.47.9
Autor:
Lee Seong-bok
Publikováno v:
New England Review (10531297); 2024, Vol. 45 Issue 2, p84-88, 5p
Autor:
Lee, Chae Bok1 (AUTHOR), Choi, Hei Gwon2,3 (AUTHOR), Gurmessa, Sintayehu Kebede4 (AUTHOR), Jang, In-Taek1 (AUTHOR), Kumar, Naresh5 (AUTHOR), Jiang, Zongyou1 (AUTHOR), Kaushik, Nagendra Kumar6 (AUTHOR), Kim, Hwa-Jung1 (AUTHOR) hjukim@cnu.ac.kr
Publikováno v:
Cancer Cell International. 11/23/2024, Vol. 24 Issue 1, p1-16. 16p.
Autor:
Min, Geon1 (AUTHOR) aming20@ajou.ac.kr, Lee, Tae Bok1 (AUTHOR) dolphin0104@ajou.ac.kr, Heo, Yong Seok1,2 (AUTHOR) ysheo@ajou.ac.kr
Publikováno v:
Sensors (14248220). Nov2024, Vol. 24 Issue 22, p7112. 19p.
Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some recent works have shown that a co
Externí odkaz:
http://arxiv.org/abs/2210.10485
In this paper, we introduce a novel approach for systematically solving dataset condensation problem in an efficient manner by exploiting the regularity in a given dataset. Instead of condensing the dataset directly in the original input space, we as
Externí odkaz:
http://arxiv.org/abs/2208.10494