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 Di Wu

Di Wu

Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup


Nov 30, 2021
Siyuan Li, Zicheng Liu, Di Wu, Zihan Liu, Stan Z. Li

Figure 1 for Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
Figure 2 for Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
Figure 3 for Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
Figure 4 for Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
* Preprint under review. 8 pages main body, 6 pages appendix, 3 pages reference 
  Access Paper or Ask Questions

Environment-Aware Beam Selection for IRS-Aided Communication with Channel Knowledge Map


Nov 22, 2021
Dingyang Ding, Di Wu, Yong Zeng, Shi Jin, Rui Zhang

Figure 1 for Environment-Aware Beam Selection for IRS-Aided Communication with Channel Knowledge Map
Figure 2 for Environment-Aware Beam Selection for IRS-Aided Communication with Channel Knowledge Map
Figure 3 for Environment-Aware Beam Selection for IRS-Aided Communication with Channel Knowledge Map
Figure 4 for Environment-Aware Beam Selection for IRS-Aided Communication with Channel Knowledge Map

  Access Paper or Ask Questions

ModelLight: Model-Based Meta-Reinforcement Learning for Traffic Signal Control


Nov 15, 2021
Xingshuai Huang, Di Wu, Michael Jenkin, Benoit Boulet

Figure 1 for ModelLight: Model-Based Meta-Reinforcement Learning for Traffic Signal Control
Figure 2 for ModelLight: Model-Based Meta-Reinforcement Learning for Traffic Signal Control
Figure 3 for ModelLight: Model-Based Meta-Reinforcement Learning for Traffic Signal Control
Figure 4 for ModelLight: Model-Based Meta-Reinforcement Learning for Traffic Signal Control

  Access Paper or Ask Questions

FedFly: Towards Migration in Edge-based Distributed Federated Learning


Nov 02, 2021
Rehmat Ullah, Di Wu, Paul Harvey, Peter Kilpatrick, Ivor Spence, Blesson Varghese

Figure 1 for FedFly: Towards Migration in Edge-based Distributed Federated Learning
Figure 2 for FedFly: Towards Migration in Edge-based Distributed Federated Learning
Figure 3 for FedFly: Towards Migration in Edge-based Distributed Federated Learning
Figure 4 for FedFly: Towards Migration in Edge-based Distributed Federated Learning
* 7 pages, 5 figures 
  Access Paper or Ask Questions

GenURL: A General Framework for Unsupervised Representation Learning


Oct 27, 2021
Siyuan Li, Zelin Zang, Di Wu, Zhiyuan Chen, Stan Z. Li

Figure 1 for GenURL: A General Framework for Unsupervised Representation Learning
Figure 2 for GenURL: A General Framework for Unsupervised Representation Learning
Figure 3 for GenURL: A General Framework for Unsupervised Representation Learning
Figure 4 for GenURL: A General Framework for Unsupervised Representation Learning
* Preprint with 11 pages, 6 figures 
  Access Paper or Ask Questions

C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction


Oct 26, 2021
Di Wu, Yi Shi, Ziyu Wang, Jie Yang, Mohamad Sawan

Figure 1 for C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
Figure 2 for C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
Figure 3 for C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
Figure 4 for C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction

  Access Paper or Ask Questions

WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition


Oct 18, 2021
Binbin Zhang, Hang Lv, Pengcheng Guo, Qijie Shao, Chao Yang, Lei Xie, Xin Xu, Hui Bu, Xiaoyu Chen, Chenchen Zeng, Di Wu, Zhendong Peng

Figure 1 for WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
Figure 2 for WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
Figure 3 for WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
Figure 4 for WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition

  Access Paper or Ask Questions

Improving Neural Machine Translation by Bidirectional Training


Sep 16, 2021
Liang Ding, Di Wu, Dacheng Tao

Figure 1 for Improving Neural Machine Translation by Bidirectional Training
Figure 2 for Improving Neural Machine Translation by Bidirectional Training
Figure 3 for Improving Neural Machine Translation by Bidirectional Training
Figure 4 for Improving Neural Machine Translation by Bidirectional Training
* EMNLP 2021. arXiv admin note: text overlap with arXiv:2107.11572 
  Access Paper or Ask Questions

The USYD-JD Speech Translation System for IWSLT 2021


Jul 24, 2021
Liang Ding, Di Wu, Dacheng Tao

Figure 1 for The USYD-JD Speech Translation System for IWSLT 2021
Figure 2 for The USYD-JD Speech Translation System for IWSLT 2021
Figure 3 for The USYD-JD Speech Translation System for IWSLT 2021
Figure 4 for The USYD-JD Speech Translation System for IWSLT 2021
* IWSLT 2021 winning system of the low-resource speech translation track 
  Access Paper or Ask Questions

Time Series Anomaly Detection for Smart Grids: A Survey


Jul 16, 2021
Jiuqi, Zhang, Di Wu, Benoit Boulet

Figure 1 for Time Series Anomaly Detection for Smart Grids: A Survey
* 6 pages; Preprint Submitted to IEEE Canadian Electrical Power and Energy Conference (EPEC2021) 
  Access Paper or Ask Questions

FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning


Jul 09, 2021
Di Wu, Rehmat Ullah, Paul Harvey, Peter Kilpatrick, Ivor Spence, Blesson Varghese

Figure 1 for FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning
Figure 2 for FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning
Figure 3 for FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning
Figure 4 for FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning
* 13 pages 
  Access Paper or Ask Questions

U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition


Jul 07, 2021
Di Wu, Binbin Zhang, Chao Yang, Zhendong Peng, Wenjing Xia, Xiaoyu Chen, Xin Lei

Figure 1 for U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition
Figure 2 for U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition
Figure 3 for U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition
Figure 4 for U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition

  Access Paper or Ask Questions

Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacy


Jul 05, 2021
Yipeng Zhou, Xuezheng Liu, Yao Fu, Di Wu, Chao Li, Shui Yu

Figure 1 for Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacy
Figure 2 for Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacy
Figure 3 for Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacy
Figure 4 for Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacy

  Access Paper or Ask Questions

Align Yourself: Self-supervised Pre-training for Fine-grained Recognition via Saliency Alignment


Jun 30, 2021
Di Wu, Siyuan Li, Zelin Zang, Kai Wang, Lei Shang, Baigui Sun, Hao Li, Stan Z. Li

Figure 1 for Align Yourself: Self-supervised Pre-training for Fine-grained Recognition via Saliency Alignment
Figure 2 for Align Yourself: Self-supervised Pre-training for Fine-grained Recognition via Saliency Alignment
Figure 3 for Align Yourself: Self-supervised Pre-training for Fine-grained Recognition via Saliency Alignment
Figure 4 for Align Yourself: Self-supervised Pre-training for Fine-grained Recognition via Saliency Alignment

  Access Paper or Ask Questions

Unsupervised Deep Manifold Attributed Graph Embedding


Apr 27, 2021
Zelin Zang, Siyuan Li, Di Wu, Jianzhu Guo, Yongjie Xu, Stan Z. Li

Figure 1 for Unsupervised Deep Manifold Attributed Graph Embedding
Figure 2 for Unsupervised Deep Manifold Attributed Graph Embedding
Figure 3 for Unsupervised Deep Manifold Attributed Graph Embedding
Figure 4 for Unsupervised Deep Manifold Attributed Graph Embedding
* arXiv admin note: text overlap with arXiv:2007.01594 by other authors 
  Access Paper or Ask Questions

Software-Defined Edge Computing: A New Architecture Paradigm to Support IoT Data Analysis


Apr 26, 2021
Di Wu, Xiaofeng Xie, Xiang Ni, Bin Fu, Hanhui Deng, Haibo Zeng, Zhijin Qin

Figure 1 for Software-Defined Edge Computing: A New Architecture Paradigm to Support IoT Data Analysis
Figure 2 for Software-Defined Edge Computing: A New Architecture Paradigm to Support IoT Data Analysis
Figure 3 for Software-Defined Edge Computing: A New Architecture Paradigm to Support IoT Data Analysis
Figure 4 for Software-Defined Edge Computing: A New Architecture Paradigm to Support IoT Data Analysis

  Access Paper or Ask Questions

Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding


Apr 13, 2021
Di Wu, Yiren Chen, Liang Ding, Dacheng Tao

Figure 1 for Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding
Figure 2 for Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding
Figure 3 for Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding
Figure 4 for Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding
* Work in progress 
  Access Paper or Ask Questions

Representation range needs for 16-bit neural network training


Apr 06, 2021
Valentina Popescu, Abhinav Venigalla, Di Wu, Robert Schreiber

Figure 1 for Representation range needs for 16-bit neural network training
Figure 2 for Representation range needs for 16-bit neural network training
Figure 3 for Representation range needs for 16-bit neural network training
Figure 4 for Representation range needs for 16-bit neural network training
* 7 pages, 3 figures, 4 tables; conference 
  Access Paper or Ask Questions

AutoMix: Unveiling the Power of Mixup


Mar 24, 2021
Zicheng Liu, Siyuan Li, Di Wu, Zhiyuan Chen, Lirong Wu, Jianzhu Guo, Stan Z. Li

Figure 1 for AutoMix: Unveiling the Power of Mixup
Figure 2 for AutoMix: Unveiling the Power of Mixup
Figure 3 for AutoMix: Unveiling the Power of Mixup
Figure 4 for AutoMix: Unveiling the Power of Mixup
* The first version of AutoMix. 13 pages, 11 figures 
  Access Paper or Ask Questions

Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models


Mar 09, 2021
Linghan Meng, Yanhui Li, Lin Chen, Zhi Wang, Di Wu, Yuming Zhou, Baowen Xu

Figure 1 for Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models
Figure 2 for Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models
Figure 3 for Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models
Figure 4 for Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models
* ICSE'2021 
  Access Paper or Ask Questions

SLUA: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning


Mar 07, 2021
Di Wu, Liang Ding, Shuo Yang, Dacheng Tao

Figure 1 for SLUA: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning
Figure 2 for SLUA: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning
Figure 3 for SLUA: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning
Figure 4 for SLUA: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning
* Work in progress 
  Access Paper or Ask Questions

Environment-Aware and Training-Free Beam Alignment for mmWave Massive MIMO via Channel Knowledge Map


Feb 19, 2021
Di Wu, Yong Zeng, Shi jin, Rui Zhang

Figure 1 for Environment-Aware and Training-Free Beam Alignment for mmWave Massive MIMO via Channel Knowledge Map
Figure 2 for Environment-Aware and Training-Free Beam Alignment for mmWave Massive MIMO via Channel Knowledge Map
Figure 3 for Environment-Aware and Training-Free Beam Alignment for mmWave Massive MIMO via Channel Knowledge Map
Figure 4 for Environment-Aware and Training-Free Beam Alignment for mmWave Massive MIMO via Channel Knowledge Map

  Access Paper or Ask Questions

WeNet: Production First and Production Ready End-to-End Speech Recognition Toolkit


Feb 02, 2021
Binbin Zhang, Di Wu, Chao Yang, Xiaoyu Chen, Zhendong Peng, Xiangming Wang, Zhuoyuan Yao, Xiong Wang, Fan Yu, Lei Xie, Xin Lei

Figure 1 for WeNet: Production First and Production Ready End-to-End Speech Recognition Toolkit
Figure 2 for WeNet: Production First and Production Ready End-to-End Speech Recognition Toolkit
Figure 3 for WeNet: Production First and Production Ready End-to-End Speech Recognition Toolkit
Figure 4 for WeNet: Production First and Production Ready End-to-End Speech Recognition Toolkit
* 5 pages, 2 figures, 4 tables 
  Access Paper or Ask Questions

On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times


Jan 11, 2021
Yao Fu, Yipeng Zhou, Di Wu, Shui Yu, Yonggang Wen, Chao Li

Figure 1 for On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times
Figure 2 for On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times
Figure 3 for On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times
Figure 4 for On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times

  Access Paper or Ask Questions

Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition


Dec 10, 2020
Binbin Zhang, Di Wu, Zhuoyuan Yao, Xiong Wang, Fan Yu, Chao Yang, Liyong Guo, Yaguang Hu, Lei Xie, Xin Lei

Figure 1 for Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition
Figure 2 for Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition
Figure 3 for Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition
Figure 4 for Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition

  Access Paper or Ask Questions

Context-Aware Cross-Attention for Non-Autoregressive Translation


Nov 02, 2020
Liang Ding, Longyue Wang, Di Wu, Dacheng Tao, Zhaopeng Tu

Figure 1 for Context-Aware Cross-Attention for Non-Autoregressive Translation
Figure 2 for Context-Aware Cross-Attention for Non-Autoregressive Translation
Figure 3 for Context-Aware Cross-Attention for Non-Autoregressive Translation
Figure 4 for Context-Aware Cross-Attention for Non-Autoregressive Translation
* To appear in COLING 2020 
  Access Paper or Ask Questions