no code implementations • 18 Apr 2024 • Thibault Castells, Hyoung-Kyu Song, Bo-Kyeong Kim, Shinkook Choi
Latent Diffusion Models (LDMs) have emerged as powerful generative models, known for delivering remarkable results under constrained computational resources.
no code implementations • 18 Apr 2024 • Thibault Castells, Hyoung-Kyu Song, Tairen Piao, Shinkook Choi, Bo-Kyeong Kim, Hanyoung Yim, Changgwun Lee, Jae Gon Kim, Tae-Ho Kim
The intensive computational burden of Stable Diffusion (SD) for text-to-image generation poses a significant hurdle for its practical application.
no code implementations • 18 Apr 2024 • KyungHwan Shim, Jaewoong Yun, Shinkook Choi
Conventional pruning approaches can only compress and accelerate the MSA module using head pruning, although the head is not an atomic unit.
no code implementations • 5 Feb 2024 • Bo-Kyeong Kim, Geonmin Kim, Tae-Ho Kim, Thibault Castells, Shinkook Choi, Junho Shin, Hyoung-Kyu Song
Structured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs.
3 code implementations • 25 May 2023 • Bo-Kyeong Kim, Hyoung-Kyu Song, Thibault Castells, Shinkook Choi
Text-to-image (T2I) generation with Stable Diffusion models (SDMs) involves high computing demands due to billion-scale parameters.
DreamBooth Personalized Generation Image-to-Image Translation
no code implementations • 8 Apr 2023 • Shinkook Choi, Junkyeong Choi
As deep learning advances, edge devices and lightweight neural networks are becoming more important.
no code implementations • 2 Apr 2023 • Bo-Kyeong Kim, Jaemin Kang, Daeun Seo, Hancheol Park, Shinkook Choi, Hyoung-Kyu Song, Hyungshin Kim, Sungsu Lim
Virtual humans have gained considerable attention in numerous industries, e. g., entertainment and e-commerce.
no code implementations • 29 Jun 2022 • Bo-Kyeong Kim, Shinkook Choi, Hancheol Park
Pruning effectively compresses overparameterized models.
1 code implementation • 11 Nov 2019 • Tae-Ho Kim, Sungjae Cho, Shinkook Choi, Sejik Park, Soo-Young Lee
The embedding space of seq2seq-based TTS has abundant information on the text.