65 citations · 72 across the 7 of their papers we have counts for
7 papers
An Analytical Range-Angle Dependent Beam Focusing Model for Terahertz Linear Antenna Array
Lingxiang Li, Haoran Li, Zhi Chen +2
This paper considers a scenario in which the Terahertz (THz) transmitter equipped with a linear antenna array wishes to focus its beam to a desired spatial region in the array near…
Shfl-BW: Accelerating Deep Neural Network Inference with Tensor-Core Aware Weight Pruning
Guyue Huang, Haoran Li, Minghai Qin +3
Weight pruning in deep neural networks (DNNs) can reduce storage and computation cost, but struggles to bring practical speedup to the model inference time. Tensor-cores can signif…
Load-balanced Gather-scatter Patterns for Sparse Deep Neural Networks
Fei Sun, Minghai Qin, Tianyun Zhang +6
Deep neural networks (DNNs) have been proven to be effective in solving many real-life problems, but its high computation cost prohibits those models from being deployed to edge de…
ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint Search
Jiaqi Li, Haoran Li, Yaran Chen +5
Currently, an increasing number of model pruning methods are proposed to resolve the contradictions between the computer powers required by the deep learning models and the resourc…
Lifelong Learning with Sketched Structural Regularization
Haoran Li, Aditya Krishnan, Jingfeng Wu +3
Preventing catastrophic forgetting while continually learning new tasks is an essential problem in lifelong learning. Structural regularization (SR) refers to a family of algorithm…
AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
Yonggan Fu, Wuyang Chen, Haotao Wang +3
The compression of Generative Adversarial Networks (GANs) has lately drawn attention, due to the increasing demand for deploying GANs into mobile devices for numerous applications…
Multi-modal Datasets for Super-resolution
Haoran Li, Weihong Quan, Meijun Yan +3
Nowdays, most datasets used to train and evaluate super-resolution models are single-modal simulation datasets. However, due to the variety of image degradation types in the real w…