6 papers
FastForward Pruning: Efficient LLM Pruning via Single-Step Reinforcement Learning
Xin Yuan, Siqi Li, Jiateng Wei +7
Pruning is an effective method for compressing Large Language Models, but finding an optimal, non-uniform layer-wise sparsity allocation remains a key challenge. While heuristic me…
OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks
Jingyang Xiang, Zuohui Chen, Siqi Li +2
Binary Neural Networks~(BNNs) have been proven to be highly effective for deploying deep neural networks on mobile and embedded platforms. Most existing works focus on minimizing q…
AutoDFP: Automatic Data-Free Pruning via Channel Similarity Reconstruction
Siqi Li, Jun Chen, Jingyang Xiang +2
Structured pruning methods are developed to bridge the gap between the massive scale of neural networks and the limited hardware resources. Most current structured pruning methods…
CR-SFP: Learning Consistent Representation for Soft Filter Pruning
Jingyang Xiang, Zhuangzhi Chen, Jianbiao Mei +3
Soft filter pruning~(SFP) has emerged as an effective pruning technique for allowing pruned filters to update and the opportunity for them to regrow to the network. However, this p…
MaxQ: Multi-Axis Query for N:M Sparsity Network
Jingyang Xiang, Siqi Li, Junhao Chen +4
N:M sparsity has received increasing attention due to its remarkable performance and latency trade-off compared with structured and unstructured sparsity. However, existing N:M spa…
SUBP: Soft Uniform Block Pruning for 1xN Sparse CNNs Multithreading Acceleration
Jingyang Xiang, Siqi Li, Jun Chen +4
The study of sparsity in Convolutional Neural Networks (CNNs) has become widespread to compress and accelerate models in environments with limited resources. By constraining N cons…