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 Yang Liu

Yang Liu

Demystifying How Self-Supervised Features Improve Training from Noisy Labels


Oct 18, 2021
Hao Cheng, Zhaowei Zhu, Xing Sun, Yang Liu

Figure 1 for Demystifying How Self-Supervised Features Improve Training from Noisy Labels
Figure 2 for Demystifying How Self-Supervised Features Improve Training from Noisy Labels
Figure 3 for Demystifying How Self-Supervised Features Improve Training from Noisy Labels
Figure 4 for Demystifying How Self-Supervised Features Improve Training from Noisy Labels

  Access Paper or Ask Questions

Think Before You Speak: Using Self-talk to Generate Implicit Commonsense Knowledge for Response Generation


Oct 16, 2021
Pei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia, Seokhwan Kim, Jay Pujara, Xiang Ren, Yang Liu, Dilek Hakkani-Tur

Figure 1 for Think Before You Speak: Using Self-talk to Generate Implicit Commonsense Knowledge for Response Generation
Figure 2 for Think Before You Speak: Using Self-talk to Generate Implicit Commonsense Knowledge for Response Generation
Figure 3 for Think Before You Speak: Using Self-talk to Generate Implicit Commonsense Knowledge for Response Generation
Figure 4 for Think Before You Speak: Using Self-talk to Generate Implicit Commonsense Knowledge for Response Generation
* 13 pages, 2 figures, 7 tables 
  Access Paper or Ask Questions

A Short Study on Compressing Decoder-Based Language Models


Oct 16, 2021
Tianda Li, Yassir El Mesbahi, Ivan Kobyzev, Ahmad Rashid, Atif Mahmud, Nithin Anchuri, Habib Hajimolahoseini, Yang Liu, Mehdi Rezagholizadeh

Figure 1 for A Short Study on Compressing Decoder-Based Language Models
Figure 2 for A Short Study on Compressing Decoder-Based Language Models
Figure 3 for A Short Study on Compressing Decoder-Based Language Models
Figure 4 for A Short Study on Compressing Decoder-Based Language Models

  Access Paper or Ask Questions

End-to-End Segmentation-based News Summarization


Oct 15, 2021
Yang Liu, Chenguang Zhu, Michael Zeng

Figure 1 for End-to-End Segmentation-based News Summarization
Figure 2 for End-to-End Segmentation-based News Summarization
Figure 3 for End-to-End Segmentation-based News Summarization
Figure 4 for End-to-End Segmentation-based News Summarization

  Access Paper or Ask Questions

DirectQuote: A Dataset for Direct Quotation Extraction and Attribution in News Articles


Oct 15, 2021
Yuanchi Zhang, Yang Liu

Figure 1 for DirectQuote: A Dataset for Direct Quotation Extraction and Attribution in News Articles
Figure 2 for DirectQuote: A Dataset for Direct Quotation Extraction and Attribution in News Articles
Figure 3 for DirectQuote: A Dataset for Direct Quotation Extraction and Attribution in News Articles
Figure 4 for DirectQuote: A Dataset for Direct Quotation Extraction and Attribution in News Articles

  Access Paper or Ask Questions

MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators


Oct 13, 2021
Zhixing Tan, Xiangwen Zhang, Shuo Wang, Yang Liu

Figure 1 for MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators
Figure 2 for MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators
Figure 3 for MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators
Figure 4 for MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators
* Work in progress 
  Access Paper or Ask Questions

A Good Representation Detects Noisy Labels


Oct 12, 2021
Zhaowei Zhu, Zihao Dong, Hao Cheng, Yang Liu

Figure 1 for A Good Representation Detects Noisy Labels
Figure 2 for A Good Representation Detects Noisy Labels
Figure 3 for A Good Representation Detects Noisy Labels
Figure 4 for A Good Representation Detects Noisy Labels

  Access Paper or Ask Questions

The Rich Get Richer: Disparate Impact of Semi-Supervised Learning


Oct 12, 2021
Zhaowei Zhu, Tianyi Luo, Yang Liu

Figure 1 for The Rich Get Richer: Disparate Impact of Semi-Supervised Learning
Figure 2 for The Rich Get Richer: Disparate Impact of Semi-Supervised Learning
Figure 3 for The Rich Get Richer: Disparate Impact of Semi-Supervised Learning
Figure 4 for The Rich Get Richer: Disparate Impact of Semi-Supervised Learning

  Access Paper or Ask Questions

Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generation


Oct 11, 2021
Sashank Santhanam, Behnam Hedayatnia, Spandana Gella, Aishwarya Padmakumar, Seokhwan Kim, Yang Liu, Dilek Hakkani-Tur

Figure 1 for Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generation
Figure 2 for Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generation
Figure 3 for Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generation
Figure 4 for Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generation

  Access Paper or Ask Questions

HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning


Oct 08, 2021
Shiming Chen, Guo-Sen Xie, Yang Liu, Qinmu Peng, Baigui Sun, Hao Li, Xinge You, Ling Shao

Figure 1 for HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning
Figure 2 for HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning
Figure 3 for HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning
Figure 4 for HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning
* Accepted by NeurIPS 2021 
  Access Paper or Ask Questions

Stochastic Anderson Mixing for Nonconvex Stochastic Optimization


Oct 04, 2021
Fuchao Wei, Chenglong Bao, Yang Liu

Figure 1 for Stochastic Anderson Mixing for Nonconvex Stochastic Optimization
Figure 2 for Stochastic Anderson Mixing for Nonconvex Stochastic Optimization
Figure 3 for Stochastic Anderson Mixing for Nonconvex Stochastic Optimization
Figure 4 for Stochastic Anderson Mixing for Nonconvex Stochastic Optimization
* Accepted by the 35th Conference on Neural Information Processing Systems (NeurIPS 2021) 
  Access Paper or Ask Questions

FLASHE: Additively Symmetric Homomorphic Encryption for Cross-Silo Federated Learning


Sep 29, 2021
Zhifeng Jiang, Wei Wang, Yang Liu

Figure 1 for FLASHE: Additively Symmetric Homomorphic Encryption for Cross-Silo Federated Learning
Figure 2 for FLASHE: Additively Symmetric Homomorphic Encryption for Cross-Silo Federated Learning
Figure 3 for FLASHE: Additively Symmetric Homomorphic Encryption for Cross-Silo Federated Learning
Figure 4 for FLASHE: Additively Symmetric Homomorphic Encryption for Cross-Silo Federated Learning
* 12 pages, 13 figures 
  Access Paper or Ask Questions

"How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations


Sep 28, 2021
Seokhwan Kim, Yang Liu, Di Jin, Alexandros Papangelis, Karthik Gopalakrishnan, Behnam Hedayatnia, Dilek Hakkani-Tur

Figure 1 for "How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations
Figure 2 for "How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations
Figure 3 for "How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations
Figure 4 for "How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations
* To be presented at ASRU 2021 
  Access Paper or Ask Questions

Learning to Selectively Learn for Weakly-supervised Paraphrase Generation


Sep 25, 2021
Kaize Ding, Dingcheng Li, Alexander Hanbo Li, Xing Fan, Chenlei Guo, Yang Liu, Huan Liu

Figure 1 for Learning to Selectively Learn for Weakly-supervised Paraphrase Generation
Figure 2 for Learning to Selectively Learn for Weakly-supervised Paraphrase Generation
Figure 3 for Learning to Selectively Learn for Weakly-supervised Paraphrase Generation
Figure 4 for Learning to Selectively Learn for Weakly-supervised Paraphrase Generation
* Accepted by EMNLP 2021 (long) 
  Access Paper or Ask Questions

A survey of Bayesian Network structure learning


Sep 23, 2021
Neville K. Kitson, Anthony C. Constantinou, Zhigao Guo, Yang Liu, Kiattikun Chobtham

Figure 1 for A survey of Bayesian Network structure learning
Figure 2 for A survey of Bayesian Network structure learning
Figure 3 for A survey of Bayesian Network structure learning
Figure 4 for A survey of Bayesian Network structure learning

  Access Paper or Ask Questions

Commonsense-Focused Dialogues for Response Generation: An Empirical Study


Sep 21, 2021
Pei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia, Seokhwan Kim, Jay Pujara, Xiang Ren, Yang Liu, Dilek Hakkani-Tur

Figure 1 for Commonsense-Focused Dialogues for Response Generation: An Empirical Study
Figure 2 for Commonsense-Focused Dialogues for Response Generation: An Empirical Study
Figure 3 for Commonsense-Focused Dialogues for Response Generation: An Empirical Study
Figure 4 for Commonsense-Focused Dialogues for Response Generation: An Empirical Study
* Accepted at SIGDIAL 2021. 12 pages, 5 tables 
  Access Paper or Ask Questions

Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems


Sep 18, 2021
Di Jin, Shuyang Gao, Seokhwan Kim, Yang Liu, Dilek Hakkani-Tur

Figure 1 for Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems
Figure 2 for Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems
Figure 3 for Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems
Figure 4 for Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems
* To appear at NLP4ConvAI workshop of EMNLP 2021 
  Access Paper or Ask Questions

Non-smooth Bayesian Optimization in Tuning Problems


Sep 15, 2021
Hengrui Luo, James W. Demmel, Younghyun Cho, Xiaoye S. Li, Yang Liu

Figure 1 for Non-smooth Bayesian Optimization in Tuning Problems
Figure 2 for Non-smooth Bayesian Optimization in Tuning Problems
Figure 3 for Non-smooth Bayesian Optimization in Tuning Problems
Figure 4 for Non-smooth Bayesian Optimization in Tuning Problems
* 61 pages 
  Access Paper or Ask Questions

Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search


Sep 12, 2021
Jialu Wang, Yang Liu, Xin Eric Wang

Figure 1 for Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search
Figure 2 for Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search
Figure 3 for Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search
Figure 4 for Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search
* 14 pages, EMNLP 2021 
  Access Paper or Ask Questions

DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization


Sep 06, 2021
Ming Zhong, Yang Liu, Yichong Xu, Chenguang Zhu, Michael Zeng

Figure 1 for DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization
Figure 2 for DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization
Figure 3 for DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization
Figure 4 for DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization
* Preprint 
  Access Paper or Ask Questions

GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning


Sep 05, 2021
Zelei Liu, Yuanyuan Chen, Han Yu, Yang Liu, Lizhen Cui

Figure 1 for GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning
Figure 2 for GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning
Figure 3 for GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning
Figure 4 for GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning

  Access Paper or Ask Questions

SEC4SR: A Security Analysis Platform for Speaker Recognition


Sep 04, 2021
Guangke Chen, Zhe Zhao, Fu Song, Sen Chen, Lingling Fan, Yang Liu

Figure 1 for SEC4SR: A Security Analysis Platform for Speaker Recognition
Figure 2 for SEC4SR: A Security Analysis Platform for Speaker Recognition
Figure 3 for SEC4SR: A Security Analysis Platform for Speaker Recognition
Figure 4 for SEC4SR: A Security Analysis Platform for Speaker Recognition

  Access Paper or Ask Questions

Generative Models for Multi-Illumination Color Constancy


Sep 02, 2021
Partha Das, Yang Liu, Sezer Karaoglu, Theo Gevers

Figure 1 for Generative Models for Multi-Illumination Color Constancy
Figure 2 for Generative Models for Multi-Illumination Color Constancy
Figure 3 for Generative Models for Multi-Illumination Color Constancy
Figure 4 for Generative Models for Multi-Illumination Color Constancy
* Accepted in International Conference on Computer Vision Workshop (ICCVW) 2021 
  Access Paper or Ask Questions

Want To Reduce Labeling Cost? GPT-3 Can Help


Aug 30, 2021
Shuohang Wang, Yang Liu, Yichong Xu, Chenguang Zhu, Michael Zeng

Figure 1 for Want To Reduce Labeling Cost? GPT-3 Can Help
Figure 2 for Want To Reduce Labeling Cost? GPT-3 Can Help
Figure 3 for Want To Reduce Labeling Cost? GPT-3 Can Help
Figure 4 for Want To Reduce Labeling Cost? GPT-3 Can Help
* Findings of EMNLP 2021, 11 pages 
  Access Paper or Ask Questions

SynthIA: A Synthetic Inversion Approximation for the Stokes Vector Fusing SDO and Hinode into a Virtual Observatory


Aug 27, 2021
Richard E. L. Higgins, David F. Fouhey, Spiro K. Antiochos, Graham Barnes, Mark C. M. Cheung, J. Todd Hoeksema, KD Leka, Yang Liu, Peter W. Schuck, Tamas I. Gombosi

Figure 1 for SynthIA: A Synthetic Inversion Approximation for the Stokes Vector Fusing SDO and Hinode into a Virtual Observatory
Figure 2 for SynthIA: A Synthetic Inversion Approximation for the Stokes Vector Fusing SDO and Hinode into a Virtual Observatory
Figure 3 for SynthIA: A Synthetic Inversion Approximation for the Stokes Vector Fusing SDO and Hinode into a Virtual Observatory
Figure 4 for SynthIA: A Synthetic Inversion Approximation for the Stokes Vector Fusing SDO and Hinode into a Virtual Observatory

  Access Paper or Ask Questions

PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic


Aug 20, 2021
Weicong Ding, Hanlin Tang, Jingshuo Feng, Lei Yuan, Sen Yang, Guangxu Yang, Jie Zheng, Jing Wang, Qiang Su, Dong Zheng, Xuezhong Qiu, Yongqi Liu, Yuxuan Chen, Yang Liu, Chao Song, Dongying Kong, Kai Ren, Peng Jiang, Qiao Lian, Ji Liu

Figure 1 for PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic
Figure 2 for PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic
Figure 3 for PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic
Figure 4 for PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic

  Access Paper or Ask Questions

Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation


Aug 17, 2021
Jiabo Huang, Yang Liu, Shaogang Gong, Hailin Jin

Figure 1 for Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation
Figure 2 for Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation
Figure 3 for Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation
Figure 4 for Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation
* International Conference on Computer Vision (ICCV'21) 
  Access Paper or Ask Questions

Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks


Aug 16, 2021
Yu-Qi Yang, Peng-Shuai Wang, Yang Liu

Figure 1 for Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks
Figure 2 for Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks
Figure 3 for Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks
Figure 4 for Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks

  Access Paper or Ask Questions