Zobrazeno 1 - 10
of 446
pro vyhledávání: '"Lee, Sukhan"'
Autor:
Yun, Sungmin, Kyung, Kwanhee, Cho, Juhwan, Choi, Jaewan, Kim, Jongmin, Kim, Byeongho, Lee, Sukhan, Sohn, Kyomin, Ahn, Jung Ho
Large language models (LLMs) have emerged due to their capability to generate high-quality content across diverse contexts. To reduce their explosively increasing demands for computing resources, a mixture of experts (MoE) has emerged. The MoE layer
Externí odkaz:
http://arxiv.org/abs/2409.01141
Autor:
Lee, Soojin1 (AUTHOR), Lee, Sukhan1 (AUTHOR) lsh1@skku.edu, Lee, Jungsun2 (AUTHOR), Jo, Young Tak3 (AUTHOR), Park, Eunil4 (AUTHOR), Cha, Junyeop4 (AUTHOR)
Publikováno v:
BMC Psychiatry. 11/19/2024, Vol. 24 Issue 1, p1-17. 17p.
Autor:
Puche, Aaron Valero, Lee, Sukhan
The 3D Bin Packing Problem (3D-BPP) is one of the most demanded yet challenging problems in industry, where an agent must pack variable size items delivered in sequence into a finite bin with the aim to maximize the space utilization. It represents a
Externí odkaz:
http://arxiv.org/abs/2208.07123
Autor:
Lee, Sukhan1 (AUTHOR) christie74@skku.edu, Lee, Soojin1 (AUTHOR), Park, Hyunwoo2 (AUTHOR) hwpark0104@skku.edu
Publikováno v:
Sensors (14248220). Aug2024, Vol. 24 Issue 15, p4850. 26p.
Autor:
Ryu, Wonyeol1 (AUTHOR) ryuwon10@skku.edu, Lee, Sukhan2 (AUTHOR) lsh1@skku.edu, Park, Eunil3 (AUTHOR) pa1324@gmail.com
Publikováno v:
Sensors (14248220). Jun2024, Vol. 24 Issue 11, p3442. 21p.
Autor:
Puche, Aaron Valero, Lee, Sukhan
In this paper, we present a novel audio synthesizer, CAESynth, based on a conditional autoencoder. CAESynth synthesizes timbre in real-time by interpolating the reference sounds in their shared latent feature space, while controlling a pitch independ
Externí odkaz:
http://arxiv.org/abs/2111.05174
Publikováno v:
Sensors (14248220); Nov2024, Vol. 24 Issue 21, p6890, 16p