Picture for Lei Li

Lei Li

Carnegie Mellon University

Multi-Modality Cardiac Image Analysis with Deep Learning

Add code
Nov 08, 2021
Figure 1 for Multi-Modality Cardiac Image Analysis with Deep Learning
Figure 2 for Multi-Modality Cardiac Image Analysis with Deep Learning
Figure 3 for Multi-Modality Cardiac Image Analysis with Deep Learning
Figure 4 for Multi-Modality Cardiac Image Analysis with Deep Learning
Viaarxiv icon

LightSeq2: Accelerated Training for Transformer-based Models on GPUs

Add code
Oct 27, 2021
Figure 1 for LightSeq2: Accelerated Training for Transformer-based Models on GPUs
Figure 2 for LightSeq2: Accelerated Training for Transformer-based Models on GPUs
Figure 3 for LightSeq2: Accelerated Training for Transformer-based Models on GPUs
Figure 4 for LightSeq2: Accelerated Training for Transformer-based Models on GPUs
Viaarxiv icon

CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level

Add code
Oct 21, 2021
Figure 1 for CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level
Figure 2 for CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level
Figure 3 for CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level
Figure 4 for CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level
Viaarxiv icon

Well-classified Examples are Underestimated in Classification with Deep Neural Networks

Add code
Oct 15, 2021
Figure 1 for Well-classified Examples are Underestimated in Classification with Deep Neural Networks
Figure 2 for Well-classified Examples are Underestimated in Classification with Deep Neural Networks
Figure 3 for Well-classified Examples are Underestimated in Classification with Deep Neural Networks
Figure 4 for Well-classified Examples are Underestimated in Classification with Deep Neural Networks
Viaarxiv icon

Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision

Add code
Oct 14, 2021
Figure 1 for Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision
Figure 2 for Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision
Figure 3 for Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision
Figure 4 for Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision
Viaarxiv icon

The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21

Add code
Sep 24, 2021
Figure 1 for The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21
Figure 2 for The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21
Figure 3 for The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21
Figure 4 for The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21
Viaarxiv icon

Dynamic Knowledge Distillation for Pre-trained Language Models

Add code
Sep 23, 2021
Figure 1 for Dynamic Knowledge Distillation for Pre-trained Language Models
Figure 2 for Dynamic Knowledge Distillation for Pre-trained Language Models
Figure 3 for Dynamic Knowledge Distillation for Pre-trained Language Models
Figure 4 for Dynamic Knowledge Distillation for Pre-trained Language Models
Viaarxiv icon

Learning Kernel-Smoothed Machine Translation with Retrieved Examples

Add code
Sep 21, 2021
Figure 1 for Learning Kernel-Smoothed Machine Translation with Retrieved Examples
Figure 2 for Learning Kernel-Smoothed Machine Translation with Retrieved Examples
Figure 3 for Learning Kernel-Smoothed Machine Translation with Retrieved Examples
Figure 4 for Learning Kernel-Smoothed Machine Translation with Retrieved Examples
Viaarxiv icon

UniST: Unified End-to-end Model for Streaming and Non-streaming Speech Translation

Add code
Sep 15, 2021
Figure 1 for UniST: Unified End-to-end Model for Streaming and Non-streaming Speech Translation
Figure 2 for UniST: Unified End-to-end Model for Streaming and Non-streaming Speech Translation
Figure 3 for UniST: Unified End-to-end Model for Streaming and Non-streaming Speech Translation
Figure 4 for UniST: Unified End-to-end Model for Streaming and Non-streaming Speech Translation
Viaarxiv icon

Multilingual Translation via Grafting Pre-trained Language Models

Add code
Sep 11, 2021
Figure 1 for Multilingual Translation via Grafting Pre-trained Language Models
Figure 2 for Multilingual Translation via Grafting Pre-trained Language Models
Figure 3 for Multilingual Translation via Grafting Pre-trained Language Models
Figure 4 for Multilingual Translation via Grafting Pre-trained Language Models
Viaarxiv icon