Alert button
Picture for Huixia Li

Huixia Li

Alert button

DiffusionGPT: LLM-Driven Text-to-Image Generation System

Jan 18, 2024
Jie Qin, Jie Wu, Weifeng Chen, Yuxi Ren, Huixia Li, Hefeng Wu, Xuefeng Xiao, Rui Wang, Shilei Wen

Viaarxiv icon

AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration

Sep 23, 2023
Lijiang Li, Huixia Li, Xiawu Zheng, Jie Wu, Xuefeng Xiao, Rui Wang, Min Zheng, Xin Pan, Fei Chao, Rongrong Ji

Figure 1 for AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration
Figure 2 for AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration
Figure 3 for AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration
Figure 4 for AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration
Viaarxiv icon

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

Apr 04, 2023
Yuexiao Ma, Huixia Li, Xiawu Zheng, Xuefeng Xiao, Rui Wang, Shilei Wen, Xin Pan, Fei Chao, Rongrong Ji

Figure 1 for Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
Figure 2 for Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
Figure 3 for Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
Figure 4 for Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
Viaarxiv icon

Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios

Jul 13, 2022
Jiashi Li, Xin Xia, Wei Li, Huixia Li, Xing Wang, Xuefeng Xiao, Rui Wang, Min Zheng, Xin Pan

Figure 1 for Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios
Figure 2 for Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios
Figure 3 for Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios
Figure 4 for Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios
Viaarxiv icon

OMPQ: Orthogonal Mixed Precision Quantization

Sep 16, 2021
Yuexiao Ma, Taisong Jin, Xiawu Zheng, Yan Wang, Huixia Li, Guannan Jiang, Wei Zhang, Rongrong Ji

Figure 1 for OMPQ: Orthogonal Mixed Precision Quantization
Figure 2 for OMPQ: Orthogonal Mixed Precision Quantization
Figure 3 for OMPQ: Orthogonal Mixed Precision Quantization
Figure 4 for OMPQ: Orthogonal Mixed Precision Quantization
Viaarxiv icon

PAMS: Quantized Super-Resolution via Parameterized Max Scale

Nov 09, 2020
Huixia Li, Chenqian Yan, Shaohui Lin, Xiawu Zheng, Yuchao Li, Baochang Zhang, Fan Yang, Rongrong Ji

Figure 1 for PAMS: Quantized Super-Resolution via Parameterized Max Scale
Figure 2 for PAMS: Quantized Super-Resolution via Parameterized Max Scale
Figure 3 for PAMS: Quantized Super-Resolution via Parameterized Max Scale
Figure 4 for PAMS: Quantized Super-Resolution via Parameterized Max Scale
Viaarxiv icon