Alert button
Picture for Leyuan Wang

Leyuan Wang

Alert button

ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs

Oct 06, 2022
Yujia Zhai, Chengquan Jiang, Leyuan Wang, Xiaoying Jia, Shang Zhang, Zizhong Chen, Xin Liu, Yibo Zhu

Figure 1 for ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
Figure 2 for ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
Figure 3 for ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
Figure 4 for ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
Viaarxiv icon

Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance

Oct 25, 2021
Jiarong Xing, Leyuan Wang, Shang Zhang, Jack Chen, Ang Chen, Yibo Zhu

Figure 1 for Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance
Figure 2 for Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance
Figure 3 for Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance
Figure 4 for Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance
Viaarxiv icon

An End-to-End Autofocus Camera for Iris on the Move

Jun 29, 2021
Leyuan Wang, Kunbo Zhang, Yunlong Wang, Zhenan Sun

Figure 1 for An End-to-End Autofocus Camera for Iris on the Move
Figure 2 for An End-to-End Autofocus Camera for Iris on the Move
Figure 3 for An End-to-End Autofocus Camera for Iris on the Move
Figure 4 for An End-to-End Autofocus Camera for Iris on the Move
Viaarxiv icon

UNIT: Unifying Tensorized Instruction Compilation

Jan 21, 2021
Jian Weng, Animesh Jain, Jie Wang, Leyuan Wang, Yida Wang, Tony Nowatzki

Figure 1 for UNIT: Unifying Tensorized Instruction Compilation
Figure 2 for UNIT: Unifying Tensorized Instruction Compilation
Figure 3 for UNIT: Unifying Tensorized Instruction Compilation
Figure 4 for UNIT: Unifying Tensorized Instruction Compilation
Viaarxiv icon

HAWQV3: Dyadic Neural Network Quantization

Nov 20, 2020
Zhewei Yao, Zhen Dong, Zhangcheng Zheng, Amir Gholami, Jiali Yu, Eric Tan, Leyuan Wang, Qijing Huang, Yida Wang, Michael W. Mahoney, Kurt Keutzer

Figure 1 for HAWQV3: Dyadic Neural Network Quantization
Figure 2 for HAWQV3: Dyadic Neural Network Quantization
Figure 3 for HAWQV3: Dyadic Neural Network Quantization
Figure 4 for HAWQV3: Dyadic Neural Network Quantization
Viaarxiv icon

Recognition Oriented Iris Image Quality Assessment in the Feature Space

Sep 27, 2020
Leyuan Wang, Kunbo Zhang, Min Ren, Yunlong Wang, Zhenan Sun

Figure 1 for Recognition Oriented Iris Image Quality Assessment in the Feature Space
Figure 2 for Recognition Oriented Iris Image Quality Assessment in the Feature Space
Figure 3 for Recognition Oriented Iris Image Quality Assessment in the Feature Space
Figure 4 for Recognition Oriented Iris Image Quality Assessment in the Feature Space
Viaarxiv icon

Face Anti-Spoofing by Learning Polarization Cues in a Real-World Scenario

Mar 19, 2020
Yu Tian, Kunbo Zhang, Leyuan Wang, Zhenan Sun

Figure 1 for Face Anti-Spoofing by Learning Polarization Cues in a Real-World Scenario
Figure 2 for Face Anti-Spoofing by Learning Polarization Cues in a Real-World Scenario
Figure 3 for Face Anti-Spoofing by Learning Polarization Cues in a Real-World Scenario
Figure 4 for Face Anti-Spoofing by Learning Polarization Cues in a Real-World Scenario
Viaarxiv icon

TVM: An Automated End-to-End Optimizing Compiler for Deep Learning

Oct 05, 2018
Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Meghan Cowan, Haichen Shen, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, Arvind Krishnamurthy

Figure 1 for TVM: An Automated End-to-End Optimizing Compiler for Deep Learning
Figure 2 for TVM: An Automated End-to-End Optimizing Compiler for Deep Learning
Figure 3 for TVM: An Automated End-to-End Optimizing Compiler for Deep Learning
Figure 4 for TVM: An Automated End-to-End Optimizing Compiler for Deep Learning
Viaarxiv icon