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 Wei Yang

Wei Yang

State Grid Customer Service Center

Towards Playing Full MOBA Games with Deep Reinforcement Learning


Dec 31, 2020
Deheng Ye, Guibin Chen, Wen Zhang, Sheng Chen, Bo Yuan, Bo Liu, Jia Chen, Zhao Liu, Fuhao Qiu, Hongsheng Yu, Yinyuting Yin, Bei Shi, Liang Wang, Tengfei Shi, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu

Figure 1 for Towards Playing Full MOBA Games with Deep Reinforcement Learning
Figure 2 for Towards Playing Full MOBA Games with Deep Reinforcement Learning
Figure 3 for Towards Playing Full MOBA Games with Deep Reinforcement Learning
Figure 4 for Towards Playing Full MOBA Games with Deep Reinforcement Learning
* NeurIPS 2020 
  Access Paper or Ask Questions

Optimizing Deeper Transformers on Small Datasets: An Application on Text-to-SQL Semantic Parsing


Dec 30, 2020
Peng Xu, Wei Yang, Wenjie Zi, Keyi Tang, Chengyang Huang, Jackie Chi Kit Cheung, Yanshuai Cao

Figure 1 for Optimizing Deeper Transformers on Small Datasets: An Application on Text-to-SQL Semantic Parsing
Figure 2 for Optimizing Deeper Transformers on Small Datasets: An Application on Text-to-SQL Semantic Parsing
Figure 3 for Optimizing Deeper Transformers on Small Datasets: An Application on Text-to-SQL Semantic Parsing
Figure 4 for Optimizing Deeper Transformers on Small Datasets: An Application on Text-to-SQL Semantic Parsing
* Work in progress 
  Access Paper or Ask Questions

Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search


Dec 18, 2020
Sheng Chen, Menghui Zhu, Deheng Ye, Weinan Zhang, Qiang Fu, Wei Yang

Figure 1 for Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search
Figure 2 for Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search
Figure 3 for Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search
Figure 4 for Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search

  Access Paper or Ask Questions

RaP-Net: A Region-wise and Point-wise Weighting Network to Extract Robust Keypoints for Indoor Localization


Dec 01, 2020
Dongjiang Li, Jinyu Miao, Xuesong Shi, Yuxin Tian, Qiwei Long, Ping Guo, Hongfei Yu, Wei Yang, Haosong Yue, Qi Wei, Fei Qiao

Figure 1 for RaP-Net: A Region-wise and Point-wise Weighting Network to Extract Robust Keypoints for Indoor Localization
Figure 2 for RaP-Net: A Region-wise and Point-wise Weighting Network to Extract Robust Keypoints for Indoor Localization
Figure 3 for RaP-Net: A Region-wise and Point-wise Weighting Network to Extract Robust Keypoints for Indoor Localization
Figure 4 for RaP-Net: A Region-wise and Point-wise Weighting Network to Extract Robust Keypoints for Indoor Localization

  Access Paper or Ask Questions

Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings


Nov 25, 2020
Deheng Ye, Guibin Chen, Peilin Zhao, Fuhao Qiu, Bo Yuan, Wen Zhang, Sheng Chen, Mingfei Sun, Xiaoqian Li, Siqin Li, Jing Liang, Zhenjie Lian, Bei Shi, Liang Wang, Tengfei Shi, Qiang Fu, Wei Yang, Lanxiao Huang

Figure 1 for Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings
Figure 2 for Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings
Figure 3 for Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings
Figure 4 for Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings
* IEEE Transactions on Neural Networks and Learning Systems (TNNLS) 
  Access Paper or Ask Questions

Reactive Human-to-Robot Handovers of Arbitrary Objects


Nov 17, 2020
Wei Yang, Chris Paxton, Arsalan Mousavian, Yu-Wei Chao, Maya Cakmak, Dieter Fox

Figure 1 for Reactive Human-to-Robot Handovers of Arbitrary Objects
Figure 2 for Reactive Human-to-Robot Handovers of Arbitrary Objects
Figure 3 for Reactive Human-to-Robot Handovers of Arbitrary Objects
Figure 4 for Reactive Human-to-Robot Handovers of Arbitrary Objects

  Access Paper or Ask Questions

DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features


Aug 12, 2020
Dongjiang Li, Xuesong Shi, Qiwei Long, Shenghui Liu, Wei Yang, Fangshi Wang, Qi Wei, Fei Qiao

Figure 1 for DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features
Figure 2 for DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features
Figure 3 for DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features
Figure 4 for DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features
* 8 pages, 5 figures, to be published in IROS 2020 
  Access Paper or Ask Questions

Segment as Points for Efficient Online Multi-Object Tracking and Segmentation


Jul 03, 2020
Zhenbo Xu, Wei Zhang, Xiao Tan, Wei Yang, Huan Huang, Shilei Wen, Errui Ding, Liusheng Huang

Figure 1 for Segment as Points for Efficient Online Multi-Object Tracking and Segmentation
Figure 2 for Segment as Points for Efficient Online Multi-Object Tracking and Segmentation
Figure 3 for Segment as Points for Efficient Online Multi-Object Tracking and Segmentation
Figure 4 for Segment as Points for Efficient Online Multi-Object Tracking and Segmentation
* ECCV2020 ORAL (top 2%). Code already available at https://github.com/detectRecog/PointTrack. A highly effective method for learning features based on instance segments 
  Access Paper or Ask Questions

PointTrack++ for Effective Online Multi-Object Tracking and Segmentation


Jul 03, 2020
Zhenbo Xu, Wei Zhang, Xiao Tan, Wei Yang, Xiangbo Su, Yuchen Yuan, Hongwu Zhang, Shilei Wen, Errui Ding, Liusheng Huang

Figure 1 for PointTrack++ for Effective Online Multi-Object Tracking and Segmentation
Figure 2 for PointTrack++ for Effective Online Multi-Object Tracking and Segmentation
Figure 3 for PointTrack++ for Effective Online Multi-Object Tracking and Segmentation
* CVPR2020 MOTS Challenge Winner. PointTrack++ ranks first on KITTI MOTS (http://www.cvlibs.net/datasets/kitti/eval_mots.php) 
  Access Paper or Ask Questions

Unsupervised Deformable Medical Image Registration via Pyramidal Residual Deformation Fields Estimation


Apr 16, 2020
Yujia Zhou, Shumao Pang, Jun Cheng, Yuhang Sun, Yi Wu, Lei Zhao, Yaqin Liu, Zhentai Lu, Wei Yang, Qianjin Feng

Figure 1 for Unsupervised Deformable Medical Image Registration via Pyramidal Residual Deformation Fields Estimation
Figure 2 for Unsupervised Deformable Medical Image Registration via Pyramidal Residual Deformation Fields Estimation
Figure 3 for Unsupervised Deformable Medical Image Registration via Pyramidal Residual Deformation Fields Estimation
Figure 4 for Unsupervised Deformable Medical Image Registration via Pyramidal Residual Deformation Fields Estimation

  Access Paper or Ask Questions

Human Grasp Classification for Reactive Human-to-Robot Handovers


Mar 12, 2020
Wei Yang, Chris Paxton, Maya Cakmak, Dieter Fox

Figure 1 for Human Grasp Classification for Reactive Human-to-Robot Handovers
Figure 2 for Human Grasp Classification for Reactive Human-to-Robot Handovers
Figure 3 for Human Grasp Classification for Reactive Human-to-Robot Handovers
Figure 4 for Human Grasp Classification for Reactive Human-to-Robot Handovers

  Access Paper or Ask Questions

ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection


Mar 01, 2020
Zhenbo Xu, Wei Zhang, Xiaoqing Ye, Xiao Tan, Wei Yang, Shilei Wen, Errui Ding, Ajin Meng, Liusheng Huang

Figure 1 for ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection
Figure 2 for ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection
Figure 3 for ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection
Figure 4 for ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection
* Accpeted by AAAI 2020 as Oral presentation; The github page will be updated in March,2020 
  Access Paper or Ask Questions

Integrating Discrete and Neural Features via Mixed-feature Trans-dimensional Random Field Language Models


Feb 14, 2020
Silin Gao, Zhijian Ou, Wei Yang, Huifang Xu

Figure 1 for Integrating Discrete and Neural Features via Mixed-feature Trans-dimensional Random Field Language Models
Figure 2 for Integrating Discrete and Neural Features via Mixed-feature Trans-dimensional Random Field Language Models
Figure 3 for Integrating Discrete and Neural Features via Mixed-feature Trans-dimensional Random Field Language Models
Figure 4 for Integrating Discrete and Neural Features via Mixed-feature Trans-dimensional Random Field Language Models
* 5 pages, 2 figures 
  Access Paper or Ask Questions

Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents


Feb 05, 2020
Ruixue Zhang, Wei Yang, Luyun Lin, Zhengkai Tu, Yuqing Xie, Zihang Fu, Yuhao Xie, Luchen Tan, Kun Xiong, Jimmy Lin

Figure 1 for Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents
Figure 2 for Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents
Figure 3 for Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents
Figure 4 for Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents

  Access Paper or Ask Questions

Mastering Complex Control in MOBA Games with Deep Reinforcement Learning


Jan 03, 2020
Deheng Ye, Zhao Liu, Mingfei Sun, Bei Shi, Peilin Zhao, Hao Wu, Hongsheng Yu, Shaojie Yang, Xipeng Wu, Qingwei Guo, Qiaobo Chen, Yinyuting Yin, Hao Zhang, Tengfei Shi, Liang Wang, Qiang Fu, Wei Yang, Lanxiao Huang

Figure 1 for Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
Figure 2 for Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
Figure 3 for Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
Figure 4 for Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
* accepted as a conference paper by AAAI-2020 
  Access Paper or Ask Questions

Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM


Nov 13, 2019
Xuesong Shi, Dongjiang Li, Pengpeng Zhao, Qinbin Tian, Yuxin Tian, Qiwei Long, Chunhao Zhu, Jingwei Song, Fei Qiao, Le Song, Yangquan Guo, Zhigang Wang, Yimin Zhang, Baoxing Qin, Wei Yang, Fangshi Wang, Rosa H. M. Chan, Qi She

Figure 1 for Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM
Figure 2 for Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM
Figure 3 for Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM
Figure 4 for Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM

  Access Paper or Ask Questions

Multi-Stage Document Ranking with BERT


Oct 31, 2019
Rodrigo Nogueira, Wei Yang, Kyunghyun Cho, Jimmy Lin

Figure 1 for Multi-Stage Document Ranking with BERT
Figure 2 for Multi-Stage Document Ranking with BERT
Figure 3 for Multi-Stage Document Ranking with BERT
Figure 4 for Multi-Stage Document Ranking with BERT

  Access Paper or Ask Questions

DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System


Oct 14, 2019
Ankur Handa, Karl Van Wyk, Wei Yang, Jacky Liang, Yu-Wei Chao, Qian Wan, Stan Birchfield, Nathan Ratliff, Dieter Fox

Figure 1 for DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System
Figure 2 for DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System
Figure 3 for DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System
Figure 4 for DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System
* 17 pages, first version of DexPilot 
  Access Paper or Ask Questions

Trajectory Optimization for Coordinated Human-Robot Collaboration


Oct 10, 2019
Adam Fishman, Chris Paxton, Wei Yang, Nathan Ratliff, Dieter Fox

Figure 1 for Trajectory Optimization for Coordinated Human-Robot Collaboration
Figure 2 for Trajectory Optimization for Coordinated Human-Robot Collaboration
Figure 3 for Trajectory Optimization for Coordinated Human-Robot Collaboration
Figure 4 for Trajectory Optimization for Coordinated Human-Robot Collaboration
* 3 figures, 7 pages 
  Access Paper or Ask Questions

Aggregating Votes with Local Differential Privacy: Usefulness, Soundness vs. Indistinguishability


Aug 14, 2019
Shaowei Wang, Jiachun Du, Wei Yang, Xinrong Diao, Zichun Liu, Yiwen Nie, Liusheng Huang, Hongli Xu

Figure 1 for Aggregating Votes with Local Differential Privacy: Usefulness, Soundness vs. Indistinguishability
Figure 2 for Aggregating Votes with Local Differential Privacy: Usefulness, Soundness vs. Indistinguishability
Figure 3 for Aggregating Votes with Local Differential Privacy: Usefulness, Soundness vs. Indistinguishability
Figure 4 for Aggregating Votes with Local Differential Privacy: Usefulness, Soundness vs. Indistinguishability

  Access Paper or Ask Questions

Document Expansion by Query Prediction


Apr 17, 2019
Rodrigo Nogueira, Wei Yang, Jimmy Lin, Kyunghyun Cho

Figure 1 for Document Expansion by Query Prediction
Figure 2 for Document Expansion by Query Prediction
Figure 3 for Document Expansion by Query Prediction
Figure 4 for Document Expansion by Query Prediction

  Access Paper or Ask Questions

Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering


Apr 14, 2019
Wei Yang, Yuqing Xie, Luchen Tan, Kun Xiong, Ming Li, Jimmy Lin

Figure 1 for Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering
Figure 2 for Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering
Figure 3 for Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering
Figure 4 for Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering

  Access Paper or Ask Questions

Simple Applications of BERT for Ad Hoc Document Retrieval


Mar 26, 2019
Wei Yang, Haotian Zhang, Jimmy Lin

Figure 1 for Simple Applications of BERT for Ad Hoc Document Retrieval
Figure 2 for Simple Applications of BERT for Ad Hoc Document Retrieval

  Access Paper or Ask Questions

End-to-End Open-Domain Question Answering with BERTserini


Feb 05, 2019
Wei Yang, Yuqing Xie, Aileen Lin, Xingyu Li, Luchen Tan, Kun Xiong, Ming Li, Jimmy Lin

Figure 1 for End-to-End Open-Domain Question Answering with BERTserini
Figure 2 for End-to-End Open-Domain Question Answering with BERTserini
Figure 3 for End-to-End Open-Domain Question Answering with BERTserini
Figure 4 for End-to-End Open-Domain Question Answering with BERTserini

  Access Paper or Ask Questions

A Simple Regularization-based Algorithm for Learning Cross-Domain Word Embeddings


Feb 01, 2019
Wei Yang, Wei Lu, Vincent W. Zheng

Figure 1 for A Simple Regularization-based Algorithm for Learning Cross-Domain Word Embeddings
Figure 2 for A Simple Regularization-based Algorithm for Learning Cross-Domain Word Embeddings
Figure 3 for A Simple Regularization-based Algorithm for Learning Cross-Domain Word Embeddings
* D17-1312, 2017, 2898-2904 
 * 7 pages, accepted by EMNLP 2017 
  Access Paper or Ask Questions

Hierarchical Macro Strategy Model for MOBA Game AI


Dec 19, 2018
Bin Wu, Qiang Fu, Jing Liang, Peng Qu, Xiaoqian Li, Liang Wang, Wei Liu, Wei Yang, Yongsheng Liu

Figure 1 for Hierarchical Macro Strategy Model for MOBA Game AI
Figure 2 for Hierarchical Macro Strategy Model for MOBA Game AI
Figure 3 for Hierarchical Macro Strategy Model for MOBA Game AI
Figure 4 for Hierarchical Macro Strategy Model for MOBA Game AI

  Access Paper or Ask Questions