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 Yanyu Li

Yanyu Li
Alert button

Rethinking Vision Transformers for MobileNet Size and Speed


Dec 15, 2022
Yanyu Li, Ju Hu, Yang Wen, Georgios Evangelidis, Kamyar Salahi, Yanzhi Wang, Sergey Tulyakov, Jian Ren

Add code
Alert button

Figure 1 for Rethinking Vision Transformers for MobileNet Size and Speed
Figure 2 for Rethinking Vision Transformers for MobileNet Size and Speed
Figure 3 for Rethinking Vision Transformers for MobileNet Size and Speed
Figure 4 for Rethinking Vision Transformers for MobileNet Size and Speed
* Code is available at: https://github.com/snap-research/EfficientFormer 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training


Sep 22, 2022
Geng Yuan, Yanyu Li, Sheng Li, Zhenglun Kong, Sergey Tulyakov, Xulong Tang, Yanzhi Wang, Jian Ren

Add code
Alert button

Figure 1 for Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training
Figure 2 for Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training
Figure 3 for Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training
Figure 4 for Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training
* Published in 36th Conference on Neural Information Processing Systems (NeurIPS 2022) 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

PIM-QAT: Neural Network Quantization for Processing-In-Memory (PIM) Systems


Sep 18, 2022
Qing Jin, Zhiyu Chen, Jian Ren, Yanyu Li, Yanzhi Wang, Kaiyuan Yang

Add code
Alert button

Figure 1 for PIM-QAT: Neural Network Quantization for Processing-In-Memory (PIM) Systems
Figure 2 for PIM-QAT: Neural Network Quantization for Processing-In-Memory (PIM) Systems
Figure 3 for PIM-QAT: Neural Network Quantization for Processing-In-Memory (PIM) Systems
Figure 4 for PIM-QAT: Neural Network Quantization for Processing-In-Memory (PIM) Systems
* 25 pages, 12 figures, 8 tables 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization


Aug 10, 2022
Zhengang Li, Mengshu Sun, Alec Lu, Haoyu Ma, Geng Yuan, Yanyue Xie, Hao Tang, Yanyu Li, Miriam Leeser, Zhangyang Wang, Xue Lin, Zhenman Fang

Add code
Alert button

Figure 1 for Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization
Figure 2 for Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization
Figure 3 for Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization
Figure 4 for Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization
* Published in FPL2022 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution


Jul 25, 2022
Yushu Wu, Yifan Gong, Pu Zhao, Yanyu Li, Zheng Zhan, Wei Niu, Hao Tang, Minghai Qin, Bin Ren, Yanzhi Wang

Add code
Alert button

Figure 1 for Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution
Figure 2 for Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution
Figure 3 for Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution
Figure 4 for Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Real-Time Portrait Stylization on the Edge


Jun 02, 2022
Yanyu Li, Xuan Shen, Geng Yuan, Jiexiong Guan, Wei Niu, Hao Tang, Bin Ren, Yanzhi Wang

Add code
Alert button

Figure 1 for Real-Time Portrait Stylization on the Edge
Figure 2 for Real-Time Portrait Stylization on the Edge
Figure 3 for Real-Time Portrait Stylization on the Edge
Figure 4 for Real-Time Portrait Stylization on the Edge

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization


Jun 02, 2022
Yanyu Li, Pu Zhao, Geng Yuan, Xue Lin, Yanzhi Wang, Xin Chen

Add code
Alert button

Figure 1 for Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization
Figure 2 for Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization
Figure 3 for Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization
Figure 4 for Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

EfficientFormer: Vision Transformers at MobileNet Speed


Jun 02, 2022
Yanyu Li, Geng Yuan, Yang Wen, Eric Hu, Georgios Evangelidis, Sergey Tulyakov, Yanzhi Wang, Jian Ren

Add code
Alert button

Figure 1 for EfficientFormer: Vision Transformers at MobileNet Speed
Figure 2 for EfficientFormer: Vision Transformers at MobileNet Speed
Figure 3 for EfficientFormer: Vision Transformers at MobileNet Speed
Figure 4 for EfficientFormer: Vision Transformers at MobileNet Speed

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Neural Network-based OFDM Receiver for Resource Constrained IoT Devices


May 12, 2022
Nasim Soltani, Hai Cheng, Mauro Belgiovine, Yanyu Li, Haoqing Li, Bahar Azari, Salvatore D'Oro, Tales Imbiriba, Tommaso Melodia, Pau Closas, Yanzhi Wang, Deniz Erdogmus, Kaushik Chowdhury

Add code
Alert button

Figure 1 for Neural Network-based OFDM Receiver for Resource Constrained IoT Devices
Figure 2 for Neural Network-based OFDM Receiver for Resource Constrained IoT Devices
Figure 3 for Neural Network-based OFDM Receiver for Resource Constrained IoT Devices
Figure 4 for Neural Network-based OFDM Receiver for Resource Constrained IoT Devices

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

AirNN: Neural Networks with Over-the-Air Convolution via Reconfigurable Intelligent Surfaces


Feb 07, 2022
Sara Garcia Sanchez, Guillem Reus Muns, Carlos Bocanegra, Yanyu Li, Ufuk Muncuk, Yousof Naderi, Yanzhi Wang, Stratis Ioannidis, Kaushik R. Chowdhury

Add code
Alert button


   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>