5 citations · 5 across the 6 of their papers we have counts for
5 papers · 1 filter
MVQ:Towards Efficient DNN Compression and Acceleration with Masked Vector Quantization
Shuaiting Li, Chengxuan Wang, Juncan Deng +5
Vector quantization(VQ) is a hardware-friendly DNN compression method that can reduce the storage cost and weight-loading datawidth of hardware accelerators. However, conventional…
VQ4ALL: Efficient Neural Network Representation via a Universal Codebook
Juncan Deng, Shuaiting Li, Zeyu Wang +3
The rapid growth of the big neural network models puts forward new requirements for lightweight network representation methods. The traditional methods based on model compression h…
Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusion
Shuaiting Li, Juncan Deng, Zeyu Wang +5
Text-to-image generation via Stable Diffusion models (SDM) have demonstrated remarkable capabilities. However, their computational intensity, particularly in the iterative denoisin…
VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers
Juncan Deng, Shuaiting Li, Zeyu Wang +3
The Diffusion Transformers Models (DiTs) have transitioned the network architecture from traditional UNets to transformers, demonstrating exceptional capabilities in image generati…
DiffX: Guide Your Layout to Cross-Modal Generative Modeling
Zeyu Wang, Jingyu Lin, Yifei Qian +8
Diffusion models have made significant strides in language-driven and layout-driven image generation. However, most diffusion models are limited to visible RGB image generation. In…