Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Jo, Jaehyeong"'
Text-to-image diffusion models have shown remarkable success in generating personalized subjects based on a few reference images. However, current methods often fail when generating multiple subjects simultaneously, resulting in mixed identities with
Externí odkaz:
http://arxiv.org/abs/2404.04243
Autor:
Park, Seong Hyeon, Choi, Gahyun, Kim, Gyunghun, Jo, Jaehyeong, Lee, Bumsung, Kim, Geonyoung, Park, Kibog, Lee, Yong-Ho, Hahn, Seungyong
Engineering the admittance of external environments connected to superconducting qubits is essential, as increasing the measurement speed introduces spontaneous emission loss to superconducting qubits, known as Purcell loss. Here, we report a broad b
Externí odkaz:
http://arxiv.org/abs/2310.13282
Autor:
Jo, Jaehyeong, Hwang, Sung Ju
Learning the distribution of data on Riemannian manifolds is crucial for modeling data from non-Euclidean space, which is required by many applications in diverse scientific fields. Yet, existing generative models on manifolds suffer from expensive d
Externí odkaz:
http://arxiv.org/abs/2310.07216
Existing NAS methods suffer from either an excessive amount of time for repetitive sampling and training of many task-irrelevant architectures. To tackle such limitations of existing NAS methods, we propose a paradigm shift from NAS to a novel condit
Externí odkaz:
http://arxiv.org/abs/2305.16943
Autor:
Lee, Jaewoong, Jang, Sangwon, Jo, Jaehyeong, Yoon, Jaehong, Kim, Yunji, Kim, Jin-Hwa, Ha, Jung-Woo, Hwang, Sung Ju
Token-based masked generative models are gaining popularity for their fast inference time with parallel decoding. While recent token-based approaches achieve competitive performance to diffusion-based models, their generation performance is still sub
Externí odkaz:
http://arxiv.org/abs/2304.01515
Generation of graphs is a major challenge for real-world tasks that require understanding the complex nature of their non-Euclidean structures. Although diffusion models have achieved notable success in graph generation recently, they are ill-suited
Externí odkaz:
http://arxiv.org/abs/2302.03596
Autor:
Song, Wonho, Lee, Jung-Yong, Kim, Junhyung, Park, Jinyoung, Jo, Jaehyeong, Hyun, Eunseok, Kim, Jiwan, Eom, Daejin, Choi, Gahyun, Park, Kibog
The effective work-function of metal electrode is one of the major factors to determine the threshold voltage of metal/oxide/semiconductor junction. In this work, we demonstrate experimentally that the effective work-function of Aluminum (Al) electro
Externí odkaz:
http://arxiv.org/abs/2208.08044
A well-known limitation of existing molecular generative models is that the generated molecules highly resemble those in the training set. To generate truly novel molecules that may have even better properties for de novo drug discovery, more powerfu
Externí odkaz:
http://arxiv.org/abs/2206.07632
Generating graph-structured data requires learning the underlying distribution of graphs. Yet, this is a challenging problem, and the previous graph generative methods either fail to capture the permutation-invariance property of graphs or cannot suf
Externí odkaz:
http://arxiv.org/abs/2202.02514
Graph neural networks have recently achieved remarkable success in representing graph-structured data, with rapid progress in both the node embedding and graph pooling methods. Yet, they mostly focus on capturing information from the nodes considerin
Externí odkaz:
http://arxiv.org/abs/2106.15845