Zobrazeno 1 - 10
of 2 616
pro vyhledávání: '"Kim, Tae Ho"'
Autor:
Castells, Thibault, Song, Hyoung-Kyu, Piao, Tairen, Choi, Shinkook, Kim, Bo-Kyeong, Yim, Hanyoung, Lee, Changgwun, Kim, Jae Gon, Kim, Tae-Ho
The intensive computational burden of Stable Diffusion (SD) for text-to-image generation poses a significant hurdle for its practical application. To tackle this challenge, recent research focuses on methods to reduce sampling steps, such as Latent C
Externí odkaz:
http://arxiv.org/abs/2404.11925
Autor:
Cho, Joseph, Puspitasari, Fachrina Dewi, Zheng, Sheng, Zheng, Jingyao, Lee, Lik-Hang, Kim, Tae-Ho, Hong, Choong Seon, Zhang, Chaoning
The evolution of video generation from text, starting with animating MNIST numbers to simulating the physical world with Sora, has progressed at a breakneck speed over the past seven years. While often seen as a superficial expansion of the predecess
Externí odkaz:
http://arxiv.org/abs/2403.05131
Autor:
Kim, Bo-Kyeong, Kim, Geonmin, Kim, Tae-Ho, Castells, Thibault, Choi, Shinkook, Shin, Junho, Song, Hyoung-Kyu
Structured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs. Width pruning reduces the size of projection weight matrices (e.g., by removing attention heads) while maintaining the number
Externí odkaz:
http://arxiv.org/abs/2402.02834
Segment anything model (SAM) addresses two practical yet challenging segmentation tasks: \textbf{segment anything (SegAny)}, which utilizes a certain point to predict the mask for a single object of interest, and \textbf{segment everything (SegEvery)
Externí odkaz:
http://arxiv.org/abs/2312.09579
Uniform-precision neural network quantization has gained popularity since it simplifies densely packed arithmetic unit for high computing capability. However, it ignores heterogeneous sensitivity to the impact of quantization errors across the layers
Externí odkaz:
http://arxiv.org/abs/2212.10878
Autor:
Kim, Tae Ho
Comprehensive modeling of gas foil bearings (GFBs) anchored to reliable test data will enable the widespread usage of GFBs into novel turbomachinery applications, such as light weight business aircraft engines, hybrid fuel cell-turbine power systems,
Externí odkaz:
http://hdl.handle.net/1969.1/85852
Autor:
Lee, Seung Jae, Shin, Sang-Hun, Cha, Min Suc, Yang, Seok Hwan, Kim, Tae Hoon, Cho, Hye Jin, Oh, Keun-Hwan, Kim, Tae-Ho, Kim, Sungjun, Lee, Jang Yong
Publikováno v:
In Materials Today Energy July 2024 43
Autor:
Lee, Yeon Su, Kim, Hyunjun, Lee, Sung Min, Yuk, Miguhn, Kim, Eunseo, Kim, Tae-Ho, Kim, Sung-Kon
Publikováno v:
In Applied Surface Science 30 October 2024 671
Publikováno v:
In Optical Materials March 2024 149
Autor:
Kiran Kumar, B., Reddi Babu, P., Kavaz, Esra, Kshetri, Yuwaraj K., Kim, Tae-Ho, Anjos, Virgilio de Carvalho dos, Deva Prasad Raju, B.
Publikováno v:
In Optical Materials February 2024 148