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 Yuan Yao

Yuan Yao

Department of Mathematics, Hong Kong University of Science and Technology

CPM-2: Large-scale Cost-effective Pre-trained Language Models


Jun 20, 2021
Zhengyan Zhang, Yuxian Gu, Xu Han, Shengqi Chen, Chaojun Xiao, Zhenbo Sun, Yuan Yao, Fanchao Qi, Jian Guan, Pei Ke, Yanzheng Cai, Guoyang Zeng, Zhixing Tan, Zhiyuan Liu, Minlie Huang, Wentao Han, Yang Liu, Xiaoyan Zhu, Maosong Sun

Figure 1 for CPM-2: Large-scale Cost-effective Pre-trained Language Models
Figure 2 for CPM-2: Large-scale Cost-effective Pre-trained Language Models
Figure 3 for CPM-2: Large-scale Cost-effective Pre-trained Language Models
Figure 4 for CPM-2: Large-scale Cost-effective Pre-trained Language Models

  Access Paper or Ask Questions

Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution


Jun 11, 2021
Fanchao Qi, Yuan Yao, Sophia Xu, Zhiyuan Liu, Maosong Sun

Figure 1 for Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution
Figure 2 for Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution
Figure 3 for Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution
Figure 4 for Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution
* Accepted by the main conference of ACL-IJCNLP as a long paper. Camera-ready version 
  Access Paper or Ask Questions

Image-to-Video Generation via 3D Facial Dynamics


May 31, 2021
Xiaoguang Tu, Yingtian Zou, Jian Zhao, Wenjie Ai, Jian Dong, Yuan Yao, Zhikang Wang, Guodong Guo, Zhifeng Li, Wei Liu, Jiashi Feng

Figure 1 for Image-to-Video Generation via 3D Facial Dynamics
Figure 2 for Image-to-Video Generation via 3D Facial Dynamics
Figure 3 for Image-to-Video Generation via 3D Facial Dynamics
Figure 4 for Image-to-Video Generation via 3D Facial Dynamics

  Access Paper or Ask Questions

Visual Distant Supervision for Scene Graph Generation


Mar 29, 2021
Yuan Yao, Ao Zhang, Xu Han, Mengdi Li, Cornelius Weber, Zhiyuan Liu, Stefan Wermter, Maosong Sun

Figure 1 for Visual Distant Supervision for Scene Graph Generation
Figure 2 for Visual Distant Supervision for Scene Graph Generation
Figure 3 for Visual Distant Supervision for Scene Graph Generation
Figure 4 for Visual Distant Supervision for Scene Graph Generation
* 14 pages, 6 figures 
  Access Paper or Ask Questions

UPRec: User-Aware Pre-training for Recommender Systems


Feb 22, 2021
Chaojun Xiao, Ruobing Xie, Yuan Yao, Zhiyuan Liu, Maosong Sun, Xu Zhang, Leyu Lin

Figure 1 for UPRec: User-Aware Pre-training for Recommender Systems
Figure 2 for UPRec: User-Aware Pre-training for Recommender Systems
Figure 3 for UPRec: User-Aware Pre-training for Recommender Systems
Figure 4 for UPRec: User-Aware Pre-training for Recommender Systems
* This paper has been submitted to IEEE TKDE 
  Access Paper or Ask Questions

Polyimide-Based Flexible Coupled-Coils Design and Load-Shift Keying Analysis


Feb 02, 2021
Yuan Yao, Wing-Hung Ki, Chi-Ying Tsui

Figure 1 for Polyimide-Based Flexible Coupled-Coils Design and Load-Shift Keying Analysis
Figure 2 for Polyimide-Based Flexible Coupled-Coils Design and Load-Shift Keying Analysis
Figure 3 for Polyimide-Based Flexible Coupled-Coils Design and Load-Shift Keying Analysis
Figure 4 for Polyimide-Based Flexible Coupled-Coils Design and Load-Shift Keying Analysis
* 4 pages, 8 figures 
  Access Paper or Ask Questions

StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding


Jan 11, 2021
Jinshan Zeng, Qi Chen, Yunxin Liu, Mingwen Wang, Yuan Yao

Figure 1 for StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding
Figure 2 for StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding
Figure 3 for StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding
Figure 4 for StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding
* AAAI 2021 
 * 10 pages, our codes and data are available at: https://github.com/JinshanZeng/StrokeGAN 
  Access Paper or Ask Questions

On Stochastic Variance Reduced Gradient Method for Semidefinite Optimization


Jan 01, 2021
Jinshan Zeng, Yixuan Zha, Ke Ma, Yuan Yao

Figure 1 for On Stochastic Variance Reduced Gradient Method for Semidefinite Optimization
Figure 2 for On Stochastic Variance Reduced Gradient Method for Semidefinite Optimization
Figure 3 for On Stochastic Variance Reduced Gradient Method for Semidefinite Optimization
Figure 4 for On Stochastic Variance Reduced Gradient Method for Semidefinite Optimization
* 27 pages, 5 figures 
  Access Paper or Ask Questions

An exact solution in Markov decision process with multiplicative rewards as a general framework


Dec 15, 2020
Yuan Yao, Xiaolin Sun

* 11 pages 
  Access Paper or Ask Questions

Denoising Relation Extraction from Document-level Distant Supervision


Nov 08, 2020
Chaojun Xiao, Yuan Yao, Ruobing Xie, Xu Han, Zhiyuan Liu, Maosong Sun, Fen Lin, Leyu Lin

Figure 1 for Denoising Relation Extraction from Document-level Distant Supervision
Figure 2 for Denoising Relation Extraction from Document-level Distant Supervision
Figure 3 for Denoising Relation Extraction from Document-level Distant Supervision
Figure 4 for Denoising Relation Extraction from Document-level Distant Supervision
* EMNLP 2020 short paper 
  Access Paper or Ask Questions

Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients


Sep 28, 2020
Yifei Huang, Yaodong Yu, Hongyang Zhang, Yi Ma, Yuan Yao

Figure 1 for Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients
Figure 2 for Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients
Figure 3 for Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients
Figure 4 for Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients
* 16 pages 
  Access Paper or Ask Questions

Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect


Sep 19, 2020
Zheni Zeng, Chaojun Xiao, Yuan Yao, Ruobing Xie, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun

Figure 1 for Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect
Figure 2 for Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect
Figure 3 for Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect
Figure 4 for Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect
* This paper is submitted to Frontiers in Big Data and is under review 
  Access Paper or Ask Questions

Robust Autoencoder GAN for Cryo-EM Image Denoising


Aug 17, 2020
Hanlin Gu, Ilona Christy Unarta, Xuhui Huang, Yuan Yao

Figure 1 for Robust Autoencoder GAN for Cryo-EM Image Denoising
Figure 2 for Robust Autoencoder GAN for Cryo-EM Image Denoising
Figure 3 for Robust Autoencoder GAN for Cryo-EM Image Denoising
Figure 4 for Robust Autoencoder GAN for Cryo-EM Image Denoising
* 25 pages 
  Access Paper or Ask Questions

Multi-source Heterogeneous Domain Adaptation with Conditional Weighting Adversarial Network


Aug 06, 2020
Yuan Yao, Xutao Li, Yu Zhang, Yunming Ye

Figure 1 for Multi-source Heterogeneous Domain Adaptation with Conditional Weighting Adversarial Network
Figure 2 for Multi-source Heterogeneous Domain Adaptation with Conditional Weighting Adversarial Network
Figure 3 for Multi-source Heterogeneous Domain Adaptation with Conditional Weighting Adversarial Network
Figure 4 for Multi-source Heterogeneous Domain Adaptation with Conditional Weighting Adversarial Network
* 12 pages, 7 figures 
  Access Paper or Ask Questions

How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learning


Jul 17, 2020
Yikai Wang, Li Zhang, Yuan Yao, Yanwei Fu

Figure 1 for How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learning
Figure 2 for How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learning
Figure 3 for How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learning
Figure 4 for How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learning
* Journal extension of arXiv:2003.11853 that appears in CVPR 2020 
  Access Paper or Ask Questions

Leveraging both Lesion Features and Procedural Bias in Neuroimaging: An Dual-Task Split dynamics of inverse scale space


Jul 17, 2020
Xinwei Sun, Wenjing Han, Lingjing Hu, Yuan Yao, Yizhou Wang

Figure 1 for Leveraging both Lesion Features and Procedural Bias in Neuroimaging: An Dual-Task Split dynamics of inverse scale space
Figure 2 for Leveraging both Lesion Features and Procedural Bias in Neuroimaging: An Dual-Task Split dynamics of inverse scale space
Figure 3 for Leveraging both Lesion Features and Procedural Bias in Neuroimaging: An Dual-Task Split dynamics of inverse scale space
Figure 4 for Leveraging both Lesion Features and Procedural Bias in Neuroimaging: An Dual-Task Split dynamics of inverse scale space
* Thanks to Xinwei's girlfriend Yue Cao, for her love and support 
  Access Paper or Ask Questions

DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths


Jul 04, 2020
Yanwei Fu, Chen Liu, Donghao Li, Xinwei Sun, Jinshan Zeng, Yuan Yao

Figure 1 for DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths
Figure 2 for DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths
Figure 3 for DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths
Figure 4 for DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths
* ICML 2020 
 * conference , 23 pages https://github.com/corwinliu9669/dS2LBI 
  Access Paper or Ask Questions

Crossmodal Language Grounding in an Embodied Neurocognitive Model


Jun 24, 2020
Stefan Heinrich, Yuan Yao, Tobias Hinz, Zhiyuan Liu, Thomas Hummel, Matthias Kerzel, Cornelius Weber, Stefan Wermter

Figure 1 for Crossmodal Language Grounding in an Embodied Neurocognitive Model
Figure 2 for Crossmodal Language Grounding in an Embodied Neurocognitive Model
Figure 3 for Crossmodal Language Grounding in an Embodied Neurocognitive Model
Figure 4 for Crossmodal Language Grounding in an Embodied Neurocognitive Model
* Under review, 25 pages 
  Access Paper or Ask Questions

Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning


Jun 20, 2020
Yuan Yao, Chang Liu, Dezhao Luo, Yu Zhou, Qixiang Ye

Figure 1 for Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning
Figure 2 for Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning
Figure 3 for Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning
Figure 4 for Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning
* CVPR 2020 
  Access Paper or Ask Questions

Exploring Private Federated Learning with Laplacian Smoothing


May 01, 2020
Zhicong Liang, Bao Wang, Quanquan Gu, Stanley Osher, Yuan Yao

Figure 1 for Exploring Private Federated Learning with Laplacian Smoothing
Figure 2 for Exploring Private Federated Learning with Laplacian Smoothing
Figure 3 for Exploring Private Federated Learning with Laplacian Smoothing
Figure 4 for Exploring Private Federated Learning with Laplacian Smoothing

  Access Paper or Ask Questions

Boosting Semantic Human Matting with Coarse Annotations


Apr 10, 2020
Jinlin Liu, Yuan Yao, Wendi Hou, Miaomiao Cui, Xuansong Xie, Changshui Zhang, Xian-sheng Hua

Figure 1 for Boosting Semantic Human Matting with Coarse Annotations
Figure 2 for Boosting Semantic Human Matting with Coarse Annotations
Figure 3 for Boosting Semantic Human Matting with Coarse Annotations
Figure 4 for Boosting Semantic Human Matting with Coarse Annotations

  Access Paper or Ask Questions

Learning the mapping $\mathbf{x}\mapsto \sum_{i=1}^d x_i^2$: the cost of finding the needle in a haystack


Feb 24, 2020
Jiefu Zhang, Leonardo Zepeda-Núñez, Yuan Yao, Lin Lin

Figure 1 for Learning the mapping $\mathbf{x}\mapsto \sum_{i=1}^d x_i^2$: the cost of finding the needle in a haystack
Figure 2 for Learning the mapping $\mathbf{x}\mapsto \sum_{i=1}^d x_i^2$: the cost of finding the needle in a haystack
Figure 3 for Learning the mapping $\mathbf{x}\mapsto \sum_{i=1}^d x_i^2$: the cost of finding the needle in a haystack
Figure 4 for Learning the mapping $\mathbf{x}\mapsto \sum_{i=1}^d x_i^2$: the cost of finding the needle in a haystack

  Access Paper or Ask Questions

Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction


Jan 31, 2020
Yuan Yao, Nico Schertler, Enrique Rosales, Helge Rhodin, Leonid Sigal, Alla Sheffer

Figure 1 for Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction
Figure 2 for Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction
Figure 3 for Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction
Figure 4 for Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction

  Access Paper or Ask Questions

SMAUG: End-to-End Full-Stack Simulation Infrastructure for Deep Learning Workloads


Dec 11, 2019
Sam Likun Xi, Yuan Yao, Kshitij Bhardwaj, Paul Whatmough, Gu-Yeon Wei, David Brooks

Figure 1 for SMAUG: End-to-End Full-Stack Simulation Infrastructure for Deep Learning Workloads
Figure 2 for SMAUG: End-to-End Full-Stack Simulation Infrastructure for Deep Learning Workloads
Figure 3 for SMAUG: End-to-End Full-Stack Simulation Infrastructure for Deep Learning Workloads
Figure 4 for SMAUG: End-to-End Full-Stack Simulation Infrastructure for Deep Learning Workloads
* 14 pages, 20 figures 
  Access Paper or Ask Questions

Fast Stochastic Ordinal Embedding with Variance Reduction and Adaptive Step Size


Dec 01, 2019
Ke Ma, Jinshan Zeng, Qianqian Xu, Xiaochun Cao, Wei Liu, Yuan Yao

Figure 1 for Fast Stochastic Ordinal Embedding with Variance Reduction and Adaptive Step Size
Figure 2 for Fast Stochastic Ordinal Embedding with Variance Reduction and Adaptive Step Size
Figure 3 for Fast Stochastic Ordinal Embedding with Variance Reduction and Adaptive Step Size
Figure 4 for Fast Stochastic Ordinal Embedding with Variance Reduction and Adaptive Step Size
* 19 pages, 5 figures, accepted by IEEE Transaction on Knowledge and Data Engineering, Conference Version: arXiv:1711.06446 
  Access Paper or Ask Questions

Adversarial Language Games for Advanced Natural Language Intelligence


Nov 08, 2019
Yuan Yao, Haoxi Zhong, Zhengyan Zhang, Xu Han, Xiaozhi Wang, Chaojun Xiao, Guoyang Zeng, Zhiyuan Liu, Maosong Sun

Figure 1 for Adversarial Language Games for Advanced Natural Language Intelligence
Figure 2 for Adversarial Language Games for Advanced Natural Language Intelligence
Figure 3 for Adversarial Language Games for Advanced Natural Language Intelligence
* Work in progress 
  Access Paper or Ask Questions