Huadai Liu

Huadai Liu

Auto-generated profile, based on publicly available information

Huadai Liu

Hong Kong University of Science and Technology

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 October 2025
Verified
Conference Paper
Open access
HLHuadai Liu
Huadai Liu
JWJialei Wang
Jialei Wang
Xiangtai LiXiangtai Li
Xiangtai Li
WWWen Wang
Wen Wang
QCQian Chen
Qian Chen
WXWei Xue
Wei Xue

28 October 2024
Verified
Conference Paper
Open access
HLHuadai Liu
Huadai Liu
RHRongjie Huang
Rongjie Huang
YLYang Liu
Yang Liu
HCHengyuan Cao
Hengyuan Cao
JWJialei Wang
Jialei Wang
ZZZhou Zhao
Zhou Zhao
Recent advancements in Latent Diffusion Models (LDMs) have propelled them to the forefront of various generative tasks. However, their iterative sampling process poses a significant computational burden, resulting in slow generation speeds and limiting their application in text-to-audio generation deployment. In this work, we introduce AudioLCM, a novel consistency-based model tailored for efficient and high-quality text-to-audio generation. Unlike prior approaches that address noise removal through iterative processes, AudioLCM integrates Consistency Models (CMs) into the generation process, facilitating rapid inference through a mapping from any point at any time step to the trajectory's initial point. To overcome the convergence issue inherent in LDMs with reduced sample iterations, we propose the Guided Latent Consistency Distillation with a multi-step Ordinary Differential Equation (ODE) solver. This innovation shortens the time schedule from thousands to dozens of steps while maintaining sample quality, thereby achieving fast convergence and high-quality generation. Furthermore, to optimize the performance of transformer-based neural network architectures, we integrate the advanced techniques pioneered by LLaMA into the foundational framework of transformers. This architecture supports stable and efficient training, ensuring robust performance in text-to-audio synthesis. Experimental results on text-to-audio generation and text-to-music synthesis tasks demonstrate that AudioLCM needs only 2 iterations to synthesize high-fidelity audios, while it maintains sample quality competitive with state-of-the-art models using hundreds of steps. AudioLCM enables a sampling speed of 333x faster than real-time on a single NVIDIA 4090Ti GPU, making generative models practically applicable to text-to-audio generation deployment. Our extensive preliminary analysis shows that each design in AudioLCM is effective. https://AudioLCM.github.io/. Code is Available https://github.com/Text-to-Audio/AudioLCM

4 October 2026
Verified
Book Chapter
Closed access
PDF file
PSPeiwen Sun
Peiwen Sun
XLXudong Lu
Xudong Lu
HLHuadai Liu
Huadai Liu
YBYang Bo
Yang Bo
DWDongming Wu
Dongming Wu
XYXiangyu Yue
Xiangyu Yue