Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Yanzhi Wang

Yanzhi Wang

VAQF: Fully Automatic Software-hardware Co-design Framework for Low-bit Vision Transformer


Jan 17, 2022
Mengshu Sun, Haoyu Ma, Guoliang Kang, Yifan Jiang, Tianlong Chen, Xiaolong Ma, Zhangyang Wang, Yanzhi Wang


  Access Paper or Ask Questions

SPViT: Enabling Faster Vision Transformers via Soft Token Pruning


Dec 27, 2021
Zhenglun Kong, Peiyan Dong, Xiaolong Ma, Xin Meng, Wei Niu, Mengshu Sun, Bin Ren, Minghai Qin, Hao Tang, Yanzhi Wang

Figure 1 for SPViT: Enabling Faster Vision Transformers via Soft Token Pruning
Figure 2 for SPViT: Enabling Faster Vision Transformers via Soft Token Pruning
Figure 3 for SPViT: Enabling Faster Vision Transformers via Soft Token Pruning
Figure 4 for SPViT: Enabling Faster Vision Transformers via Soft Token Pruning
* 8 pages 
  Access Paper or Ask Questions

Compact Multi-level Sparse Neural Networks with Input Independent Dynamic Rerouting


Dec 21, 2021
Minghai Qin, Tianyun Zhang, Fei Sun, Yen-Kuang Chen, Makan Fardad, Yanzhi Wang, Yuan Xie

Figure 1 for Compact Multi-level Sparse Neural Networks with Input Independent Dynamic Rerouting
Figure 2 for Compact Multi-level Sparse Neural Networks with Input Independent Dynamic Rerouting
Figure 3 for Compact Multi-level Sparse Neural Networks with Input Independent Dynamic Rerouting
Figure 4 for Compact Multi-level Sparse Neural Networks with Input Independent Dynamic Rerouting

  Access Paper or Ask Questions

Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration


Nov 22, 2021
Yifan Gong, Geng Yuan, Zheng Zhan, Wei Niu, Zhengang Li, Pu Zhao, Yuxuan Cai, Sijia Liu, Bin Ren, Xue Lin, Xulong Tang, Yanzhi Wang

Figure 1 for Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration
Figure 2 for Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration
Figure 3 for Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration
Figure 4 for Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration

  Access Paper or Ask Questions

ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers


Nov 04, 2021
Husheng Han, Kaidi Xu, Xing Hu, Xiaobing Chen, Ling Liang, Zidong Du, Qi Guo, Yanzhi Wang, Yunji Chen

Figure 1 for ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers
Figure 2 for ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers
Figure 3 for ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers
Figure 4 for ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers
* Accepted at NeurIPS 2021 
  Access Paper or Ask Questions

ILMPQ : An Intra-Layer Multi-Precision Deep Neural Network Quantization framework for FPGA


Oct 30, 2021
Sung-En Chang, Yanyu Li, Mengshu Sun, Yanzhi Wang, Xue Lin

Figure 1 for ILMPQ : An Intra-Layer Multi-Precision Deep Neural Network Quantization framework for FPGA
Figure 2 for ILMPQ : An Intra-Layer Multi-Precision Deep Neural Network Quantization framework for FPGA
* Accepted by CogArch 2021: 5th Workshop on Cognitive Architectures 
  Access Paper or Ask Questions

RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisions


Oct 30, 2021
Sung-En Chang, Yanyu Li, Mengshu Sun, Weiwen Jiang, Sijia Liu, Yanzhi Wang, Xue Lin

Figure 1 for RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisions
Figure 2 for RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisions
Figure 3 for RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisions
Figure 4 for RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisions
* Accepted by International Conference on Computer Vision 2021 (ICCV 2021) 
  Access Paper or Ask Questions

MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge


Oct 26, 2021
Geng Yuan, Xiaolong Ma, Wei Niu, Zhengang Li, Zhenglun Kong, Ning Liu, Yifan Gong, Zheng Zhan, Chaoyang He, Qing Jin, Siyue Wang, Minghai Qin, Bin Ren, Yanzhi Wang, Sijia Liu, Xue Lin

Figure 1 for MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge
Figure 2 for MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge
Figure 3 for MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge
Figure 4 for MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge
* NeurIPS 2021 Spotlight Paper 
  Access Paper or Ask Questions

Enabling Level-4 Autonomous Driving on a Single $1k Off-the-Shelf Card


Oct 12, 2021
Hsin-Hsuan Sung, Yuanchao Xu, Jiexiong Guan, Wei Niu, Shaoshan Liu, Bin Ren, Yanzhi Wang, Xipeng Shen

Figure 1 for Enabling Level-4 Autonomous Driving on a Single $1k Off-the-Shelf Card
Figure 2 for Enabling Level-4 Autonomous Driving on a Single $1k Off-the-Shelf Card
Figure 3 for Enabling Level-4 Autonomous Driving on a Single $1k Off-the-Shelf Card
Figure 4 for Enabling Level-4 Autonomous Driving on a Single $1k Off-the-Shelf Card
* under conference review 
  Access Paper or Ask Questions

Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks


Sep 08, 2021
Cheng Gong, Ye Lu, Kunpeng Xie, Zongming Jin, Tao Li, Yanzhi Wang

Figure 1 for Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks
Figure 2 for Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks
Figure 3 for Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks
Figure 4 for Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks
* 15 pages, 14 figures 
  Access Paper or Ask Questions

DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion


Aug 30, 2021
Wei Niu, Jiexiong Guan, Yanzhi Wang, Gagan Agrawal, Bin Ren

Figure 1 for DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion
Figure 2 for DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion
Figure 3 for DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion
Figure 4 for DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion

  Access Paper or Ask Questions

GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity


Aug 25, 2021
Wei Niu, Zhengang Li, Xiaolong Ma, Peiyan Dong, Gang Zhou, Xuehai Qian, Xue Lin, Yanzhi Wang, Bin Ren

Figure 1 for GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity
Figure 2 for GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity
Figure 3 for GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity
Figure 4 for GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity
* Accepted in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 
  Access Paper or Ask Questions

Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search


Aug 18, 2021
Zheng Zhan, Yifan Gong, Pu Zhao, Geng Yuan, Wei Niu, Yushu Wu, Tianyun Zhang, Malith Jayaweera, David Kaeli, Bin Ren, Xue Lin, Yanzhi Wang

Figure 1 for Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search
Figure 2 for Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search
Figure 3 for Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search
Figure 4 for Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search

  Access Paper or Ask Questions

CAP-RAM: A Charge-Domain In-Memory Computing 6T-SRAM for Accurate and Precision-Programmable CNN Inference


Jul 06, 2021
Zhiyu Chen, Zhanghao Yu, Qing Jin, Yan He, Jingyu Wang, Sheng Lin, Dai Li, Yanzhi Wang, Kaiyuan Yang

Figure 1 for CAP-RAM: A Charge-Domain In-Memory Computing 6T-SRAM for Accurate and Precision-Programmable CNN Inference
Figure 2 for CAP-RAM: A Charge-Domain In-Memory Computing 6T-SRAM for Accurate and Precision-Programmable CNN Inference
Figure 3 for CAP-RAM: A Charge-Domain In-Memory Computing 6T-SRAM for Accurate and Precision-Programmable CNN Inference
Figure 4 for CAP-RAM: A Charge-Domain In-Memory Computing 6T-SRAM for Accurate and Precision-Programmable CNN Inference
* IEEE Journal of Solid-State Circuits, Volume: 56, Issue: 6, Pages: 1924 - 1935, June 2021 
 * This work has been accepted by IEEE Journal of Solid-State Circuits (JSSC 2021) 
  Access Paper or Ask Questions

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?


Jul 01, 2021
Xiaolong Ma, Geng Yuan, Xuan Shen, Tianlong Chen, Xuxi Chen, Xiaohan Chen, Ning Liu, Minghai Qin, Sijia Liu, Zhangyang Wang, Yanzhi Wang

Figure 1 for Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
Figure 2 for Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
Figure 3 for Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
Figure 4 for Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?

  Access Paper or Ask Questions

Achieving Real-Time Object Detection on MobileDevices with Neural Pruning Search


Jun 28, 2021
Pu Zhao, Wei Niu, Geng Yuan, Yuxuan Cai, Bin Ren, Yanzhi Wang, Xue Lin

Figure 1 for Achieving Real-Time Object Detection on MobileDevices with Neural Pruning Search
Figure 2 for Achieving Real-Time Object Detection on MobileDevices with Neural Pruning Search
* Presented on the HiPEAC 2021 workshop (cogarch 2021) 
  Access Paper or Ask Questions

Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI


Jun 18, 2021
Geng Yuan, Zhiheng Liao, Xiaolong Ma, Yuxuan Cai, Zhenglun Kong, Xuan Shen, Jingyan Fu, Zhengang Li, Chengming Zhang, Hongwu Peng, Ning Liu, Ao Ren, Jinhui Wang, Yanzhi Wang

Figure 1 for Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI
Figure 2 for Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI
Figure 3 for Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI
Figure 4 for Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI
* In Proceedings of the 22nd International Symposium on Quality Electronic Design (ISQED), 2021 
  Access Paper or Ask Questions

Effective Model Sparsification by Scheduled Grow-and-Prune Methods


Jun 18, 2021
Xiaolong Ma, Minghai Qin, Fei Sun, Zejiang Hou, Kun Yuan, Yi Xu, Yanzhi Wang, Yen-Kuang Chen, Rong Jin, Yuan Xie

Figure 1 for Effective Model Sparsification by Scheduled Grow-and-Prune Methods
Figure 2 for Effective Model Sparsification by Scheduled Grow-and-Prune Methods
Figure 3 for Effective Model Sparsification by Scheduled Grow-and-Prune Methods
Figure 4 for Effective Model Sparsification by Scheduled Grow-and-Prune Methods

  Access Paper or Ask Questions

FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator


Jun 16, 2021
Geng Yuan, Payman Behnam, Zhengang Li, Ali Shafiee, Sheng Lin, Xiaolong Ma, Hang Liu, Xuehai Qian, Mahdi Nazm Bojnordi, Yanzhi Wang, Caiwen Ding

Figure 1 for FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator
Figure 2 for FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator
Figure 3 for FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator
Figure 4 for FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator
* In Proceedings of the 48th Annual International Symposium on Computer Architecture (ISCA), 2021 
  Access Paper or Ask Questions

Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression


Jun 16, 2021
Sheng Lin, Wei Jiang, Wei Wang, Kaidi Xu, Yanzhi Wang, Shan Liu, Songnan Li

Figure 1 for Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression
Figure 2 for Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression
Figure 3 for Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression
Figure 4 for Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression
* 10 pages, 3 figures and 5 tables 
  Access Paper or Ask Questions

Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices


Jun 06, 2021
Xuan Shen, Geng Yuan, Wei Niu, Xiaolong Ma, Jiexiong Guan, Zhengang Li, Bin Ren, Yanzhi Wang

Figure 1 for Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices
Figure 2 for Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices
Figure 3 for Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices
Figure 4 for Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices

  Access Paper or Ask Questions

A Compression-Compilation Framework for On-mobile Real-time BERT Applications


Jun 06, 2021
Wei Niu, Zhenglun Kong, Geng Yuan, Weiwen Jiang, Jiexiong Guan, Caiwen Ding, Pu Zhao, Sijia Liu, Bin Ren, Yanzhi Wang

Figure 1 for A Compression-Compilation Framework for On-mobile Real-time BERT Applications
Figure 2 for A Compression-Compilation Framework for On-mobile Real-time BERT Applications
Figure 3 for A Compression-Compilation Framework for On-mobile Real-time BERT Applications
Figure 4 for A Compression-Compilation Framework for On-mobile Real-time BERT Applications
* arXiv admin note: substantial text overlap with arXiv:2009.06823 
  Access Paper or Ask Questions

Teachers Do More Than Teach: Compressing Image-to-Image Models


Mar 05, 2021
Qing Jin, Jian Ren, Oliver J. Woodford, Jiazhuo Wang, Geng Yuan, Yanzhi Wang, Sergey Tulyakov

Figure 1 for Teachers Do More Than Teach: Compressing Image-to-Image Models
Figure 2 for Teachers Do More Than Teach: Compressing Image-to-Image Models
Figure 3 for Teachers Do More Than Teach: Compressing Image-to-Image Models
Figure 4 for Teachers Do More Than Teach: Compressing Image-to-Image Models
* 18 pages, 10 figures, accepted by CVPR 2021 
  Access Paper or Ask Questions

Lottery Ticket Implies Accuracy Degradation, Is It a Desirable Phenomenon?


Feb 19, 2021
Ning Liu, Geng Yuan, Zhengping Che, Xuan Shen, Xiaolong Ma, Qing Jin, Jian Ren, Jian Tang, Sijia Liu, Yanzhi Wang

Figure 1 for Lottery Ticket Implies Accuracy Degradation, Is It a Desirable Phenomenon?
Figure 2 for Lottery Ticket Implies Accuracy Degradation, Is It a Desirable Phenomenon?
Figure 3 for Lottery Ticket Implies Accuracy Degradation, Is It a Desirable Phenomenon?
Figure 4 for Lottery Ticket Implies Accuracy Degradation, Is It a Desirable Phenomenon?

  Access Paper or Ask Questions

Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device


Dec 26, 2020
Pu Zhao, Wei Niu, Geng Yuan, Yuxuan Cai, Hsin-Hsuan Sung, Wujie Wen, Sijia Liu, Xipeng Shen, Bin Ren, Yanzhi Wang, Xue Lin

Figure 1 for Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device
Figure 2 for Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device
Figure 3 for Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device
Figure 4 for Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device

  Access Paper or Ask Questions

Learn-Prune-Share for Lifelong Learning


Dec 13, 2020
Zifeng Wang, Tong Jian, Kaushik Chowdhury, Yanzhi Wang, Jennifer Dy, Stratis Ioannidis

Figure 1 for Learn-Prune-Share for Lifelong Learning
Figure 2 for Learn-Prune-Share for Lifelong Learning
Figure 3 for Learn-Prune-Share for Lifelong Learning
Figure 4 for Learn-Prune-Share for Lifelong Learning
* Accepted to the IEEE International Conference on Data Mining 2020 (ICDM'20) 
  Access Paper or Ask Questions

Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework


Dec 12, 2020
Sung-En Chang, Yanyu Li, Mengshu Sun, Runbin Shi, Hayden K. -H. So, Xuehai Qian, Yanzhi Wang, Xue Lin

Figure 1 for Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework
Figure 2 for Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework
Figure 3 for Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework
Figure 4 for Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework
* Accepted by High-Performance Computer Architecture (HPCA'2021) 
  Access Paper or Ask Questions

6.7ms on Mobile with over 78% ImageNet Accuracy: Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration


Dec 01, 2020
Zhengang Li, Geng Yuan, Wei Niu, Yanyu Li, Pu Zhao, Yuxuan Cai, Xuan Shen, Zheng Zhan, Zhenglun Kong, Qing Jin, Zhiyu Chen, Sijia Liu, Kaiyuan Yang, Bin Ren, Yanzhi Wang, Xue Lin

Figure 1 for 6.7ms on Mobile with over 78% ImageNet Accuracy: Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
Figure 2 for 6.7ms on Mobile with over 78% ImageNet Accuracy: Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
Figure 3 for 6.7ms on Mobile with over 78% ImageNet Accuracy: Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
Figure 4 for 6.7ms on Mobile with over 78% ImageNet Accuracy: Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration

  Access Paper or Ask Questions