49 citations · 65 across the 15 of their papers we have counts for
16 papers
Rethinking Residual Errors in Compensation-based LLM Quantization
Shuaiting Li, Juncan Deng, Kedong Xu +5
Methods based on weight compensation, which iteratively apply quantization and weight compensation to minimize the output error, have recently demonstrated remarkable success in qu…
SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting
Shuaiting Li, Juncan Deng, Chenxuan Wang +5
Vector Quantization (VQ) has emerged as a prominent weight compression technique, showcasing substantially lower quantization errors than uniform quantization across diverse models…
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…
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…
TMN: A Lightweight Neuron Model for Efficient Nonlinear Spike Representation
Yiwen Gu, Junchuan Gu, Haibin Shen +1
Spike trains serve as the primary medium for information transmission in Spiking Neural Networks, playing a crucial role in determining system efficiency. Existing encoding schemes…
Thermal Infrared Image Inpainting via Edge-Aware Guidance
Zeyu Wang, Haibin Shen, Changyou Men +2
Image inpainting has achieved fundamental advances with deep learning. However, almost all existing inpainting methods aim to process natural images, while few target Thermal Infra…
A Barrier Pair Method for Safe Human-Robot Shared Autonomy
Binghan He, Mahsa Ghasemi, Ufuk Topcu +1
Shared autonomy provides a framework where a human and an automated system, such as a robot, jointly control the system's behavior, enabling an effective solution for various appli…
A Blockchain-Enabled Incentivised Framework for Cyber Threat Intelligence Sharing in ICS
Kathy Nguyen, Shantanu Pal, Zahra Jadidi +2
In recent years Industrial Control Systems (ICS) have been targeted increasingly by sophisticated cyberattacks. Improving ICS security has drawn significant attention in the litera…
A Low Power In-Memory Multiplication andAccumulation Array with Modified Radix-4 Inputand Canonical Signed Digit Weights
Rui Xiao, Kejie Huang, Yewei Zhang +1
A mass of data transfer between the processing and storage units has been the leading bottleneck in modern Von-Neuman computing systems, especially when used for Artificial Intelli…
A Reconfigurable Convolution-in-Pixel CMOS Image Sensor Architecture
Ruibing Song, Kejie Huang, Zongsheng Wang +1
The separation of the data capture and analysis in modern vision systems has led to a massive amount of data transfer between the end devices and cloud computers, resulting in long…
C2F-FWN: Coarse-to-Fine Flow Warping Network for Spatial-Temporal Consistent Motion Transfer
Dongxu Wei, Xiaowei Xu, Haibin Shen +1
Human video motion transfer (HVMT) aims to synthesize videos that one person imitates other persons' actions. Although existing GAN-based HVMT methods have achieved great success,…
An 8-bit In Resistive Memory Computing Core with Regulated Passive Neuron and Bit Line Weight Mapping
Yewei Zhang, Kejie Huang, Rui Xiao +1
The rapid development of Artificial Intelligence (AI) and Internet of Things (IoT) increases the requirement for edge computing with low power and relatively high processing speed…
A GAN-based Tunable Image Compression System
Lirong Wu, Kejie Huang, Haibin Shen
The method of importance map has been widely adopted in DNN-based lossy image compression to achieve bit allocation according to the importance of image contents. However, insuffic…
An Efficient Hardware Accelerator for Structured Sparse Convolutional Neural Networks on FPGAs
Chaoyang Zhu, Kejie Huang, Shuyuan Yang +3
Deep Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in a wide range of applications. However, deeper CNN models, which are usually computation cons…
A Foreground-background Parallel Compression with Residual Encoding for Surveillance Video
Lirong Wu, Kejie Huang, Haibin Shen +1
The data storage has been one of the bottlenecks in surveillance systems. The conventional video compression algorithms such as H.264 and H.265 do not fully utilize the low informa…
GAC-GAN: A General Method for Appearance-Controllable Human Video Motion Transfer
Dongxu Wei, Xiaowei Xu, Haibin Shen +1
Human video motion transfer has a wide range of applications in multimedia, computer vision and graphics. Recently, due to the rapid development of Generative Adversarial Networks…