Modern deep neural networks, particularly recent large language models, come with
massive model sizes that require significant computational and storage resources. To …

Recent years have witnessed an exponential increase in the use of mobile and embedded
devices. With the great success of deep learning in many fields, there is an emerging trend …

Structural pruning enables model acceleration by removing structurally-grouped parameters
from neural networks. However, the parameter-grou** patterns vary widely across …

We present a simple but powerful architecture of convolutional neural network, which has a
VGG-like inference-time body composed of nothing but a stack of 3x3 convolution and …

Neural network pruning---the task of reducing the size of a network by removing parameters--
-has been the subject of a great deal of work in recent years. We provide a meta-analysis of …

Abstract As designing appropriate Convolutional Neural Network (CNN) architecture in the
context of a given application usually involves heavy human works or numerous GPU hours …

In this paper, we present CORING, which is short for effiCient tensOr decomposition-based
filteR prunING, a novel filter pruning methodology for neural networks. CORING is crafted to …

We propose ResRep, a novel method for lossless channel pruning (aka filter pruning), which
slims down a CNN by reducing the width (number of output channels) of convolutional …

Regularization has long been utilized to learn sparsity in deep neural network pruning.
However, its role is mainly explored in the small penalty strength regime. In this work, we …

Neural image compression has surpassed state-of-the-art traditional codecs (H. 266/VVC)
for rate-distortion (RD) performance, but suffers from large complexity and separate models …