Zobrazeno 1 - 10
of 259
pro vyhledávání: '"Kim Yeongmin"'
Relation extraction (RE) is a fundamental task in natural language processing, aiming to identify relations between target entities in text. While many RE methods are designed for a single sentence or document, cross-document RE has emerged to addres
Externí odkaz:
http://arxiv.org/abs/2405.20649
Recent advances in powerful pre-trained diffusion models encourage the development of methods to improve the sampling performance under well-trained diffusion models. This paper introduces Diffusion Rejection Sampling (DiffRS), which uses a rejection
Externí odkaz:
http://arxiv.org/abs/2405.17880
Diffusion-based representation learning has achieved substantial attention due to its promising capabilities in latent representation and sample generation. Recent studies have employed an auxiliary encoder to identify a corresponding representation
Externí odkaz:
http://arxiv.org/abs/2405.17111
Autor:
Kim, Yeongmin, Na, Byeonghu, Park, Minsang, Jang, JoonHo, Kim, Dongjun, Kang, Wanmo, Moon, Il-Chul
With significant advancements in diffusion models, addressing the potential risks of dataset bias becomes increasingly important. Since generated outputs directly suffer from dataset bias, mitigating latent bias becomes a key factor in improving samp
Externí odkaz:
http://arxiv.org/abs/2403.01189
Autor:
Na, Byeonghu, Kim, Yeongmin, Bae, HeeSun, Lee, Jung Hyun, Kwon, Se Jung, Kang, Wanmo, Moon, Il-Chul
Conditional diffusion models have shown remarkable performance in various generative tasks, but training them requires large-scale datasets that often contain noise in conditional inputs, a.k.a. noisy labels. This noise leads to condition mismatch an
Externí odkaz:
http://arxiv.org/abs/2402.17517
The proposed method, Discriminator Guidance, aims to improve sample generation of pre-trained diffusion models. The approach introduces a discriminator that gives explicit supervision to a denoising sample path whether it is realistic or not. Unlike
Externí odkaz:
http://arxiv.org/abs/2211.17091
Unsupervised anomaly detection is coming into the spotlight these days in various practical domains due to the limited amount of anomaly data. One of the major approaches for it is a normalizing flow which pursues the invertible transformation of a c
Externí odkaz:
http://arxiv.org/abs/2210.14913
Autor:
Kim, Yeongmin1 (AUTHOR), Choi, Wongyung2 (AUTHOR), Choi, Woojeong3 (AUTHOR), Ko, Grace4 (AUTHOR), Han, Seonggyun5 (AUTHOR), Kim, Hwan-Cheol6 (AUTHOR), Kim, Dokyoon7 (AUTHOR), Lee, Dong-gi7 (AUTHOR), Shin, Dong Wook8,9 (AUTHOR), Lee, Younghee2 (AUTHOR) amazon@snu.ac.kr
Publikováno v:
BioData Mining. 5/25/2024, Vol. 17 Issue 1, p1-18. 18p.
Autor:
Kim, Yeongmin, Oh, Gwangeon, Lee, Jun, Kang, Hyokyeong, Kim, Hyerim, Park, Jimin, Kansara, Shivam, Hwang, Jang-Yeon, Park, Young, Lestari, Kiki Rezki, Kim, Tae-Hoon, Kim, Jaekook
Publikováno v:
In Journal of Power Sources 30 December 2023 588
Autor:
Lee, Jun, Baek, Jaeryeol, Kim, Yeongmin, Jeong, Wangchae, Kim, Hyerim, Oh, Gwangeon, Oh, Yunjae, Jeong, Seohee, Kansara, Shivam, Sambandam, Balaji, Hwang, Jang-Yeon, Kim, Jaekook
Publikováno v:
In Materials Today Chemistry October 2023 33