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 Hengzhi Pei

Hengzhi Pei
Alert button

Zero-Shot Classification by Logical Reasoning on Natural Language Explanations


Nov 07, 2022
Chi Han, Hengzhi Pei, Xinya Du, Heng Ji

Add code
Alert button

Figure 1 for Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
Figure 2 for Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
Figure 3 for Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
Figure 4 for Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
* 8 pages, 5 figures 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One


Jun 26, 2022
Yezhen Wang, Tong Che, Bo Li, Kaitao Song, Hengzhi Pei, Yoshua Bengio, Dongsheng Li

Add code
Alert button

Figure 1 for Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One
Figure 2 for Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One
Figure 3 for Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One
Figure 4 for Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One
* Preprint version 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Towards Generating Real-World Time Series Data


Nov 16, 2021
Hengzhi Pei, Kan Ren, Yuqing Yang, Chang Liu, Tao Qin, Dongsheng Li

Add code
Alert button

Figure 1 for Towards Generating Real-World Time Series Data
Figure 2 for Towards Generating Real-World Time Series Data
Figure 3 for Towards Generating Real-World Time Series Data
Figure 4 for Towards Generating Real-World Time Series Data
* Accepted in 21th IEEE International Conference on Data Mining (ICDM 2021). Code is available at https://seqml.github.io/rtsgan 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

End-to-end Robustness for Sensing-Reasoning Machine Learning Pipelines


Mar 06, 2020
Zhuolin Yang, Zhikuan Zhao, Hengzhi Pei, Boxin Wang, Bojan Karlas, Ji Liu, Heng Guo, Bo Li, Ce Zhang

Add code
Alert button

Figure 1 for End-to-end Robustness for Sensing-Reasoning Machine Learning Pipelines
Figure 2 for End-to-end Robustness for Sensing-Reasoning Machine Learning Pipelines
Figure 3 for End-to-end Robustness for Sensing-Reasoning Machine Learning Pipelines
Figure 4 for End-to-end Robustness for Sensing-Reasoning Machine Learning Pipelines
* 43 pages, 9 figures 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States


Feb 09, 2020
Yunan Ye, Hengzhi Pei, Boxin Wang, Pin-Yu Chen, Yada Zhu, Jun Xiao, Bo Li

Add code
Alert button

Figure 1 for Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States
Figure 2 for Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States
Figure 3 for Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States
Figure 4 for Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States
* AAAI 2020 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

AdvCodec: Towards A Unified Framework for Adversarial Text Generation


Dec 22, 2019
Boxin Wang, Hengzhi Pei, Han Liu, Bo Li

Add code
Alert button

Figure 1 for AdvCodec: Towards A Unified Framework for Adversarial Text Generation
Figure 2 for AdvCodec: Towards A Unified Framework for Adversarial Text Generation
Figure 3 for AdvCodec: Towards A Unified Framework for Adversarial Text Generation
Figure 4 for AdvCodec: Towards A Unified Framework for Adversarial Text Generation

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks


Nov 17, 2019
Yuheng Zhang, Ruoxi Jia, Hengzhi Pei, Wenxiao Wang, Bo Li, Dawn Song

Add code
Alert button

Figure 1 for The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks
Figure 2 for The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks
Figure 3 for The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks
Figure 4 for The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Multi-Criteria Chinese Word Segmentation with Transformer


Jun 28, 2019
Xipeng Qiu, Hengzhi Pei, Hang Yan, Xuanjing Huang

Add code
Alert button

Figure 1 for Multi-Criteria Chinese Word Segmentation with Transformer
Figure 2 for Multi-Criteria Chinese Word Segmentation with Transformer
Figure 3 for Multi-Criteria Chinese Word Segmentation with Transformer
Figure 4 for Multi-Criteria Chinese Word Segmentation with Transformer
* 18 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email