Alert button
Picture for Yanyang Li

Yanyang Li

Alert button

Bag of Tricks for Optimizing Transformer Efficiency

Sep 09, 2021
Ye Lin, Yanyang Li, Tong Xiao, Jingbo Zhu

Figure 1 for Bag of Tricks for Optimizing Transformer Efficiency
Figure 2 for Bag of Tricks for Optimizing Transformer Efficiency
Figure 3 for Bag of Tricks for Optimizing Transformer Efficiency
Figure 4 for Bag of Tricks for Optimizing Transformer Efficiency
Viaarxiv icon

Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders

May 12, 2021
Chen Xu, Bojie Hu, Yanyang Li, Yuhao Zhang, shen huang, Qi Ju, Tong Xiao, Jingbo Zhu

Figure 1 for Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders
Figure 2 for Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders
Figure 3 for Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders
Figure 4 for Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders
Viaarxiv icon

An Efficient Transformer Decoder with Compressed Sub-layers

Jan 03, 2021
Yanyang Li, Ye Lin, Tong Xiao, Jingbo Zhu

Figure 1 for An Efficient Transformer Decoder with Compressed Sub-layers
Figure 2 for An Efficient Transformer Decoder with Compressed Sub-layers
Figure 3 for An Efficient Transformer Decoder with Compressed Sub-layers
Figure 4 for An Efficient Transformer Decoder with Compressed Sub-layers
Viaarxiv icon

A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction

Nov 30, 2020
Yanyang Li, Yingfeng Luo, Ye Lin, Quan Du, Huizhen Wang, Shujian Huang, Tong Xiao, Jingbo Zhu

Figure 1 for A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction
Figure 2 for A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction
Figure 3 for A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction
Figure 4 for A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction
Viaarxiv icon

Weight Distillation: Transferring the Knowledge in Neural Network Parameters

Sep 19, 2020
Ye Lin, Yanyang Li, Ziyang Wang, Bei Li, Quan Du, Tong Xiao, Jingbo Zhu

Figure 1 for Weight Distillation: Transferring the Knowledge in Neural Network Parameters
Figure 2 for Weight Distillation: Transferring the Knowledge in Neural Network Parameters
Figure 3 for Weight Distillation: Transferring the Knowledge in Neural Network Parameters
Figure 4 for Weight Distillation: Transferring the Knowledge in Neural Network Parameters
Viaarxiv icon

Towards Fully 8-bit Integer Inference for the Transformer Model

Sep 18, 2020
Ye Lin, Yanyang Li, Tengbo Liu, Tong Xiao, Tongran Liu, Jingbo Zhu

Figure 1 for Towards Fully 8-bit Integer Inference for the Transformer Model
Figure 2 for Towards Fully 8-bit Integer Inference for the Transformer Model
Figure 3 for Towards Fully 8-bit Integer Inference for the Transformer Model
Figure 4 for Towards Fully 8-bit Integer Inference for the Transformer Model
Viaarxiv icon

Neural Machine Translation with Joint Representation

Feb 18, 2020
Yanyang Li, Qiang Wang, Tong Xiao, Tongran Liu, Jingbo Zhu

Figure 1 for Neural Machine Translation with Joint Representation
Figure 2 for Neural Machine Translation with Joint Representation
Figure 3 for Neural Machine Translation with Joint Representation
Figure 4 for Neural Machine Translation with Joint Representation
Viaarxiv icon

Multi-layer Representation Fusion for Neural Machine Translation

Feb 16, 2020
Qiang Wang, Fuxue Li, Tong Xiao, Yanyang Li, Yinqiao Li, Jingbo Zhu

Figure 1 for Multi-layer Representation Fusion for Neural Machine Translation
Figure 2 for Multi-layer Representation Fusion for Neural Machine Translation
Figure 3 for Multi-layer Representation Fusion for Neural Machine Translation
Figure 4 for Multi-layer Representation Fusion for Neural Machine Translation
Viaarxiv icon