Alert button
Picture for Taesu Kim

Taesu Kim

Alert button

QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference

Feb 15, 2024
Taesu Kim, Jongho Lee, Daehyun Ahn, Sarang Kim, Jiwoong Choi, Minkyu Kim, Hyungjun Kim

Viaarxiv icon

SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks

Feb 14, 2024
Jiwon Song, Kyungseok Oh, Taesu Kim, Hyungjun Kim, Yulhwa Kim, Jae-Joon Kim

Viaarxiv icon

Squeezing Large-Scale Diffusion Models for Mobile

Jul 03, 2023
Jiwoong Choi, Minkyu Kim, Daehyun Ahn, Taesu Kim, Yulhwa Kim, Dongwon Jo, Hyesung Jeon, Jae-Joon Kim, Hyungjun Kim

Figure 1 for Squeezing Large-Scale Diffusion Models for Mobile
Figure 2 for Squeezing Large-Scale Diffusion Models for Mobile
Figure 3 for Squeezing Large-Scale Diffusion Models for Mobile
Figure 4 for Squeezing Large-Scale Diffusion Models for Mobile
Viaarxiv icon

OWQ: Lessons learned from activation outliers for weight quantization in large language models

Jun 13, 2023
Changhun Lee, Jungyu Jin, Taesu Kim, Hyungjun Kim, Eunhyeok Park

Figure 1 for OWQ: Lessons learned from activation outliers for weight quantization in large language models
Figure 2 for OWQ: Lessons learned from activation outliers for weight quantization in large language models
Figure 3 for OWQ: Lessons learned from activation outliers for weight quantization in large language models
Figure 4 for OWQ: Lessons learned from activation outliers for weight quantization in large language models
Viaarxiv icon

Cross-speaker Emotion Transfer by Manipulating Speech Style Latents

Mar 15, 2023
Suhee Jo, Younggun Lee, Yookyung Shin, Yeongtae Hwang, Taesu Kim

Figure 1 for Cross-speaker Emotion Transfer by Manipulating Speech Style Latents
Figure 2 for Cross-speaker Emotion Transfer by Manipulating Speech Style Latents
Figure 3 for Cross-speaker Emotion Transfer by Manipulating Speech Style Latents
Figure 4 for Cross-speaker Emotion Transfer by Manipulating Speech Style Latents
Viaarxiv icon

Hi,KIA: A Speech Emotion Recognition Dataset for Wake-Up Words

Nov 07, 2022
Taesu Kim, SeungHeon Doh, Gyunpyo Lee, Hyungseok Jeon, Juhan Nam, Hyeon-Jeong Suk

Figure 1 for Hi,KIA: A Speech Emotion Recognition Dataset for Wake-Up Words
Figure 2 for Hi,KIA: A Speech Emotion Recognition Dataset for Wake-Up Words
Figure 3 for Hi,KIA: A Speech Emotion Recognition Dataset for Wake-Up Words
Figure 4 for Hi,KIA: A Speech Emotion Recognition Dataset for Wake-Up Words
Viaarxiv icon

Text-driven Emotional Style Control and Cross-speaker Style Transfer in Neural TTS

Jul 13, 2022
Yookyung Shin, Younggun Lee, Suhee Jo, Yeongtae Hwang, Taesu Kim

Figure 1 for Text-driven Emotional Style Control and Cross-speaker Style Transfer in Neural TTS
Figure 2 for Text-driven Emotional Style Control and Cross-speaker Style Transfer in Neural TTS
Figure 3 for Text-driven Emotional Style Control and Cross-speaker Style Transfer in Neural TTS
Figure 4 for Text-driven Emotional Style Control and Cross-speaker Style Transfer in Neural TTS
Viaarxiv icon

GP22: A Car Styling Dataset for Automotive Designers

Jul 05, 2022
Gyunpyo Lee, Taesu Kim, Hyeon-Jeong Suk

Figure 1 for GP22: A Car Styling Dataset for Automotive Designers
Figure 2 for GP22: A Car Styling Dataset for Automotive Designers
Figure 3 for GP22: A Car Styling Dataset for Automotive Designers
Figure 4 for GP22: A Car Styling Dataset for Automotive Designers
Viaarxiv icon

EdiTTS: Score-based Editing for Controllable Text-to-Speech

Oct 06, 2021
Jaesung Tae, Hyeongju Kim, Taesu Kim

Figure 1 for EdiTTS: Score-based Editing for Controllable Text-to-Speech
Figure 2 for EdiTTS: Score-based Editing for Controllable Text-to-Speech
Figure 3 for EdiTTS: Score-based Editing for Controllable Text-to-Speech
Figure 4 for EdiTTS: Score-based Editing for Controllable Text-to-Speech
Viaarxiv icon

Learning pronunciation from a foreign language in speech synthesis networks

Nov 23, 2018
Younggun Lee, Taesu Kim

Figure 1 for Learning pronunciation from a foreign language in speech synthesis networks
Figure 2 for Learning pronunciation from a foreign language in speech synthesis networks
Figure 3 for Learning pronunciation from a foreign language in speech synthesis networks
Figure 4 for Learning pronunciation from a foreign language in speech synthesis networks
Viaarxiv icon