Zobrazeno 1 - 10
of 14 760
pro vyhledávání: '"Jung-Hwan In"'
Autor:
Soyoung Kim, Jung-Hwan In, Seon Hoon Kim, Karam Han, Dongkook Lim, Yun Sik Hwang, Kyung Min Lee, Ju Hyeon Choi
Publikováno v:
Applied Sciences, Vol 13, Iss 24, p 13271 (2023)
SiO2/Nb2O5 multilayer thin films were designed for the special application of an aviation lighting system emitting green light. For optical components in this system to meet requirements such as a high transmittance and durability, SiO2/Nb2O5 multila
Externí odkaz:
https://doaj.org/article/e2874444d18241a9a5d18d52ef62a352
Large Language Models (LLMs) have recently demonstrated remarkable success across various tasks. However, efficiently serving LLMs has been a challenge due to the large memory bottleneck, specifically in small batch inference settings (e.g. mobile de
Externí odkaz:
http://arxiv.org/abs/2309.15531
Transfer learning has become a popular task adaptation method in the era of foundation models. However, many foundation models require large storage and computing resources, which makes off-the-shelf deployment impractical. Post-training compression
Externí odkaz:
http://arxiv.org/abs/2305.04526
Token merging has emerged as a new paradigm that can accelerate the inference of Vision Transformers (ViTs) without any retraining or fine-tuning. To push the frontier of training-free acceleration in ViTs, we improve token merging by adding the pers
Externí odkaz:
http://arxiv.org/abs/2303.02331
Publikováno v:
Journal of Research in Interactive Marketing, 2023, Vol. 18, Issue 2, pp. 182-197.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/JRIM-08-2022-0253
Autor:
Chul-Hyun Lim1, Jung-Hwan Oh1 ojh@catholic.ac.kr
Publikováno v:
Gut & Liver. Nov2024, Vol. 18 Issue 6, p970-976. 7p.
Publikováno v:
Nanophotonics 2023
Exciton resonances in monolayer transition-metal dichalcogenides (TMDs) provide exceptionally strong light-matter interaction at room temperature. Their spectral line shape is critical in the design of a myriad of optoelectronic devices, ranging from
Externí odkaz:
http://arxiv.org/abs/2210.02064
This paper introduces the sparse periodic systolic (SPS) dataflow, which advances the state-of-the-art hardware accelerator for supporting lightweight neural networks. Specifically, the SPS dataflow enables a novel hardware design approach unlocked b
Externí odkaz:
http://arxiv.org/abs/2207.00068
Autor:
Hyun, Jonghyun, Lee, Hojin, Doo, Gisu, Lee, Dong Wook, Oh, Euntaek, Park, Jeesoo, Seok, Kyunghwa, Kim, Jung Hwan, Bae, Chulsung, Kim, Hee-Tak
Publikováno v:
In Applied Catalysis B: Environment and Energy 15 November 2024 357
Publikováno v:
In Dental Materials November 2024 40(11):1762-1772