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 Hang Liu

Hang Liu

Stevens Institute of Technology

Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm


Oct 18, 2021
Shaoyi Huang, Dongkuan Xu, Ian E. H. Yen, Sung-en Chang, Bingbing Li, Shiyang Chen, Mimi Xie, Hang Liu, Caiwen Ding

Figure 1 for Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm
Figure 2 for Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm
Figure 3 for Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm
Figure 4 for Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm

  Access Paper or Ask Questions

Detecting Gender Bias in Transformer-based Models: A Case Study on BERT


Oct 15, 2021
Bingbing Li, Hongwu Peng, Rajat Sainju, Junhuan Yang, Lei Yang, Yueying Liang, Weiwen Jiang, Binghui Wang, Hang Liu, Caiwen Ding

Figure 1 for Detecting Gender Bias in Transformer-based Models: A Case Study on BERT
Figure 2 for Detecting Gender Bias in Transformer-based Models: A Case Study on BERT
Figure 3 for Detecting Gender Bias in Transformer-based Models: A Case Study on BERT
Figure 4 for Detecting Gender Bias in Transformer-based Models: A Case Study on BERT

  Access Paper or Ask Questions

Dr. Top-k: Delegate-Centric Top-k on GPUs


Sep 16, 2021
Anil Gaihre, Da Zheng, Scott Weitze, Lingda Li, Shuaiwen Leon Song, Caiwen Ding, Xiaoye S Li, Hang Liu

Figure 1 for Dr. Top-k: Delegate-Centric Top-k on GPUs
Figure 2 for Dr. Top-k: Delegate-Centric Top-k on GPUs
Figure 3 for Dr. Top-k: Delegate-Centric Top-k on GPUs
Figure 4 for Dr. Top-k: Delegate-Centric Top-k on GPUs
* To be published in The International Conference for High Performance Computing, Networking, Storage and Analysis (SC 21) 
  Access Paper or Ask Questions

Reconfigurable Intelligent Surface Empowered Over-the-Air Federated Edge Learning


Sep 06, 2021
Hang Liu, Zehong Lin, Xiaojun Yuan, Ying-Jun Angela Zhang

Figure 1 for Reconfigurable Intelligent Surface Empowered Over-the-Air Federated Edge Learning
Figure 2 for Reconfigurable Intelligent Surface Empowered Over-the-Air Federated Edge Learning
Figure 3 for Reconfigurable Intelligent Surface Empowered Over-the-Air Federated Edge Learning
Figure 4 for Reconfigurable Intelligent Surface Empowered Over-the-Air Federated Edge Learning
* This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 
  Access Paper or Ask Questions

Binary Complex Neural Network Acceleration on FPGA


Aug 10, 2021
Hongwu Peng, Shanglin Zhou, Scott Weitze, Jiaxin Li, Sahidul Islam, Tong Geng, Ang Li, Wei Zhang, Minghu Song, Mimi Xie, Hang Liu, Caiwen Ding

Figure 1 for Binary Complex Neural Network Acceleration on FPGA
Figure 2 for Binary Complex Neural Network Acceleration on FPGA
Figure 3 for Binary Complex Neural Network Acceleration on FPGA
Figure 4 for Binary Complex Neural Network Acceleration on FPGA
* ASAP 2021, 8 pages 
  Access Paper or Ask Questions

Angel's Girl for Blind Painters: an Efficient Painting Navigation System Validated by Multimodal Evaluation Approach


Jul 27, 2021
Hang Liu, Menghan Hu, Yuzhen Chen, Qingli Li, Guangtao Zhai, Simon X. Yang, Xiao-Ping Zhang, Xiaokang Yang

Figure 1 for Angel's Girl for Blind Painters: an Efficient Painting Navigation System Validated by Multimodal Evaluation Approach
Figure 2 for Angel's Girl for Blind Painters: an Efficient Painting Navigation System Validated by Multimodal Evaluation Approach
Figure 3 for Angel's Girl for Blind Painters: an Efficient Painting Navigation System Validated by Multimodal Evaluation Approach
Figure 4 for Angel's Girl for Blind Painters: an Efficient Painting Navigation System Validated by Multimodal Evaluation Approach
* 13 pages, 18 figures 
  Access Paper or Ask Questions

Relay-Assisted Cooperative Federated Learning


Jul 20, 2021
Zehong Lin, Hang Liu, Ying-Jun Angela Zhang

Figure 1 for Relay-Assisted Cooperative Federated Learning
Figure 2 for Relay-Assisted Cooperative Federated Learning
Figure 3 for Relay-Assisted Cooperative Federated Learning
Figure 4 for Relay-Assisted Cooperative Federated Learning
* This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 
  Access Paper or Ask Questions

FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator


Jun 16, 2021
Geng Yuan, Payman Behnam, Zhengang Li, Ali Shafiee, Sheng Lin, Xiaolong Ma, Hang Liu, Xuehai Qian, Mahdi Nazm Bojnordi, Yanzhi Wang, Caiwen Ding

Figure 1 for FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator
Figure 2 for FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator
Figure 3 for FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator
Figure 4 for FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator
* In Proceedings of the 48th Annual International Symposium on Computer Architecture (ISCA), 2021 
  Access Paper or Ask Questions

SimNet: Computer Architecture Simulation using Machine Learning


May 12, 2021
Lingda Li, Santosh Pandey, Thomas Flynn, Hang Liu, Noel Wheeler, Adolfy Hoisie

Figure 1 for SimNet: Computer Architecture Simulation using Machine Learning
Figure 2 for SimNet: Computer Architecture Simulation using Machine Learning
Figure 3 for SimNet: Computer Architecture Simulation using Machine Learning
Figure 4 for SimNet: Computer Architecture Simulation using Machine Learning

  Access Paper or Ask Questions

CSIT-Free Federated Edge Learning via Reconfigurable Intelligent Surface


Feb 22, 2021
Hang Liu, Xiaojun Yuan, Ying-Jun Angela Zhang

Figure 1 for CSIT-Free Federated Edge Learning via Reconfigurable Intelligent Surface
Figure 2 for CSIT-Free Federated Edge Learning via Reconfigurable Intelligent Surface
Figure 3 for CSIT-Free Federated Edge Learning via Reconfigurable Intelligent Surface
Figure 4 for CSIT-Free Federated Edge Learning via Reconfigurable Intelligent Surface
* This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 
  Access Paper or Ask Questions

Conversational Query Rewriting with Self-supervised Learning


Feb 19, 2021
Hang Liu, Meng Chen, Youzheng Wu, Xiaodong He, Bowen Zhou

Figure 1 for Conversational Query Rewriting with Self-supervised Learning
Figure 2 for Conversational Query Rewriting with Self-supervised Learning
Figure 3 for Conversational Query Rewriting with Self-supervised Learning
Figure 4 for Conversational Query Rewriting with Self-supervised Learning
* Accepted by ICASSP 2021 
  Access Paper or Ask Questions

Reconfigurable Intelligent Surface Enabled Federated Learning: A Unified Communication-Learning Design Approach


Dec 08, 2020
Hang Liu, Xiaojun Yuan, Ying-Jun Angela Zhang

Figure 1 for Reconfigurable Intelligent Surface Enabled Federated Learning: A Unified Communication-Learning Design Approach
Figure 2 for Reconfigurable Intelligent Surface Enabled Federated Learning: A Unified Communication-Learning Design Approach
Figure 3 for Reconfigurable Intelligent Surface Enabled Federated Learning: A Unified Communication-Learning Design Approach
Figure 4 for Reconfigurable Intelligent Surface Enabled Federated Learning: A Unified Communication-Learning Design Approach
* This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 
  Access Paper or Ask Questions

Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning


Oct 08, 2020
Bingbing Li, Zhenglun Kong, Tianyun Zhang, Ji Li, Zhengang Li, Hang Liu, Caiwen Ding

Figure 1 for Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning
Figure 2 for Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning
Figure 3 for Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning
Figure 4 for Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning
* Accepted to Findings of EMNLP 2020 
  Access Paper or Ask Questions

SAPAG: A Self-Adaptive Privacy Attack From Gradients


Sep 14, 2020
Yijue Wang, Jieren Deng, Dan Guo, Chenghong Wang, Xianrui Meng, Hang Liu, Caiwen Ding, Sanguthevar Rajasekaran

Figure 1 for SAPAG: A Self-Adaptive Privacy Attack From Gradients
Figure 2 for SAPAG: A Self-Adaptive Privacy Attack From Gradients
Figure 3 for SAPAG: A Self-Adaptive Privacy Attack From Gradients
Figure 4 for SAPAG: A Self-Adaptive Privacy Attack From Gradients

  Access Paper or Ask Questions

MCMIA: Model Compression Against Membership Inference Attack in Deep Neural Networks


Aug 28, 2020
Yijue Wang, Chenghong Wang, Zigeng Wang, Shanglin Zhou, Hang Liu, Jinbo Bi, Caiwen Ding, Sanguthevar Rajasekaran

Figure 1 for MCMIA: Model Compression Against Membership Inference Attack in Deep Neural Networks
Figure 2 for MCMIA: Model Compression Against Membership Inference Attack in Deep Neural Networks
Figure 3 for MCMIA: Model Compression Against Membership Inference Attack in Deep Neural Networks
Figure 4 for MCMIA: Model Compression Against Membership Inference Attack in Deep Neural Networks
* Machine Learning (cs.LG); Cryptography and Security (cs.CR); Machine Learning (stat.ML) 
  Access Paper or Ask Questions

EZLDA: Efficient and Scalable LDA on GPUs


Jul 17, 2020
Shilong Wang, Hang Liu, Anil Gaihre, Hengyong Yu

Figure 1 for EZLDA: Efficient and Scalable LDA on GPUs
Figure 2 for EZLDA: Efficient and Scalable LDA on GPUs
Figure 3 for EZLDA: Efficient and Scalable LDA on GPUs
Figure 4 for EZLDA: Efficient and Scalable LDA on GPUs

  Access Paper or Ask Questions

FTRANS: Energy-Efficient Acceleration of Transformers using FPGA


Jul 16, 2020
Bingbing Li, Santosh Pandey, Haowen Fang, Yanjun Lyv, Ji Li, Jieyang Chen, Mimi Xie, Lipeng Wan, Hang Liu, Caiwen Ding

Figure 1 for FTRANS: Energy-Efficient Acceleration of Transformers using FPGA
Figure 2 for FTRANS: Energy-Efficient Acceleration of Transformers using FPGA
Figure 3 for FTRANS: Energy-Efficient Acceleration of Transformers using FPGA
Figure 4 for FTRANS: Energy-Efficient Acceleration of Transformers using FPGA
* 7 pages, 7 figures 
  Access Paper or Ask Questions

Information Freshness-Aware Task Offloading in Air-Ground Integrated Edge Computing Systems


Jul 15, 2020
Xianfu Chen, Celimuge Wu, Tao Chen, Zhi Liu, Honggang Zhang, Mehdi Bennis, Hang Liu, Yusheng Ji

Figure 1 for Information Freshness-Aware Task Offloading in Air-Ground Integrated Edge Computing Systems
Figure 2 for Information Freshness-Aware Task Offloading in Air-Ground Integrated Edge Computing Systems
Figure 3 for Information Freshness-Aware Task Offloading in Air-Ground Integrated Edge Computing Systems
Figure 4 for Information Freshness-Aware Task Offloading in Air-Ground Integrated Edge Computing Systems

  Access Paper or Ask Questions

A Novel Method for Extrinsic Calibration of Multiple RGB-D Cameras Using Descriptor-Based Patterns


Sep 10, 2018
Hang Liu, Hengyu Li, Xiahua Liu, Jun Luo, Shaorong Xie, Yu Sun

Figure 1 for A Novel Method for Extrinsic Calibration of Multiple RGB-D Cameras Using Descriptor-Based Patterns
Figure 2 for A Novel Method for Extrinsic Calibration of Multiple RGB-D Cameras Using Descriptor-Based Patterns
Figure 3 for A Novel Method for Extrinsic Calibration of Multiple RGB-D Cameras Using Descriptor-Based Patterns
Figure 4 for A Novel Method for Extrinsic Calibration of Multiple RGB-D Cameras Using Descriptor-Based Patterns
* 6 pages, 7 figures, under review by IEEE Robotics and Automation Letters & ICRA 
  Access Paper or Ask Questions

Construction of all-in-focus images assisted by depth sensing


Jun 05, 2018
Hang Liu, Hengyu Li, Jun Luo, Shaorong Xie, Yu Sun

Figure 1 for Construction of all-in-focus images assisted by depth sensing
Figure 2 for Construction of all-in-focus images assisted by depth sensing
Figure 3 for Construction of all-in-focus images assisted by depth sensing
Figure 4 for Construction of all-in-focus images assisted by depth sensing
* 18 pages. This paper has been submitted to Computer Vision and Image Understanding 
  Access Paper or Ask Questions