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 Zhewei Yao

Zhewei Yao
Alert button

What's Hidden in a One-layer Randomly Weighted Transformer?


Sep 08, 2021
Sheng Shen, Zhewei Yao, Douwe Kiela, Kurt Keutzer, Michael W. Mahoney

Add code
Alert button

Figure 1 for What's Hidden in a One-layer Randomly Weighted Transformer?
Figure 2 for What's Hidden in a One-layer Randomly Weighted Transformer?
Figure 3 for What's Hidden in a One-layer Randomly Weighted Transformer?
Figure 4 for What's Hidden in a One-layer Randomly Weighted Transformer?
* EMNLP 2021 (short) 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

How Much Can CLIP Benefit Vision-and-Language Tasks?


Jul 13, 2021
Sheng Shen, Liunian Harold Li, Hao Tan, Mohit Bansal, Anna Rohrbach, Kai-Wei Chang, Zhewei Yao, Kurt Keutzer

Add code
Alert button

Figure 1 for How Much Can CLIP Benefit Vision-and-Language Tasks?
Figure 2 for How Much Can CLIP Benefit Vision-and-Language Tasks?
Figure 3 for How Much Can CLIP Benefit Vision-and-Language Tasks?
Figure 4 for How Much Can CLIP Benefit Vision-and-Language Tasks?
* 14 pages 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

MLPruning: A Multilevel Structured Pruning Framework for Transformer-based Models


May 30, 2021
Zhewei Yao, Linjian Ma, Sheng Shen, Kurt Keutzer, Michael W. Mahoney

Add code
Alert button

Figure 1 for MLPruning: A Multilevel Structured Pruning Framework for Transformer-based Models
Figure 2 for MLPruning: A Multilevel Structured Pruning Framework for Transformer-based Models
Figure 3 for MLPruning: A Multilevel Structured Pruning Framework for Transformer-based Models
Figure 4 for MLPruning: A Multilevel Structured Pruning Framework for Transformer-based Models
* 20 pages, 4 figures, 9 tables 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training


Apr 29, 2021
Jianfei Chen, Lianmin Zheng, Zhewei Yao, Dequan Wang, Ion Stoica, Michael W. Mahoney, Joseph E. Gonzalez

Add code
Alert button

Figure 1 for ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
Figure 2 for ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
Figure 3 for ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
Figure 4 for ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training

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

Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition


Mar 31, 2021
Sehoon Kim, Amir Gholami, Zhewei Yao, Anirudda Nrusimha, Bohan Zhai, Tianren Gao, Michael W. Mahoney, Kurt Keutzer

Add code
Alert button

Figure 1 for Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition
Figure 2 for Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition
Figure 3 for Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition
Figure 4 for Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition

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

A Survey of Quantization Methods for Efficient Neural Network Inference


Mar 25, 2021
Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer

Add code
Alert button

Figure 1 for A Survey of Quantization Methods for Efficient Neural Network Inference
Figure 2 for A Survey of Quantization Methods for Efficient Neural Network Inference
Figure 3 for A Survey of Quantization Methods for Efficient Neural Network Inference
Figure 4 for A Survey of Quantization Methods for Efficient Neural Network Inference
* Book Chapter: Low-Power Computer Vision: Improving the Efficiency of Artificial Intelligence 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

I-BERT: Integer-only BERT Quantization


Feb 11, 2021
Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer

Add code
Alert button

Figure 1 for I-BERT: Integer-only BERT Quantization
Figure 2 for I-BERT: Integer-only BERT Quantization
Figure 3 for I-BERT: Integer-only BERT Quantization
Figure 4 for I-BERT: Integer-only BERT Quantization

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

Hessian-Aware Pruning and Optimal Neural Implant


Feb 06, 2021
Shixing Yu, Zhewei Yao, Amir Gholami, Zhen Dong, Michael W Mahoney, Kurt Keutzer

Add code
Alert button

Figure 1 for Hessian-Aware Pruning and Optimal Neural Implant
Figure 2 for Hessian-Aware Pruning and Optimal Neural Implant
Figure 3 for Hessian-Aware Pruning and Optimal Neural Implant
Figure 4 for Hessian-Aware Pruning and Optimal Neural Implant

   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
3
4
5
>>