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 Yichong Xu

Automatic Rule Induction for Efficient Semi-Supervised Learning


May 19, 2022
Reid Pryzant, Ziyi Yang, Yichong Xu, Chenguang Zhu, Michael Zeng


  Access Paper or Ask Questions

i-Code: An Integrative and Composable Multimodal Learning Framework


May 05, 2022
Ziyi Yang, Yuwei Fang, Chenguang Zhu, Reid Pryzant, Dongdong Chen, Yu Shi, Yichong Xu, Yao Qian, Mei Gao, Yi-Ling Chen, Liyang Lu, Yujia Xie, Robert Gmyr, Noel Codella, Naoyuki Kanda, Bin Xiao, Lu Yuan, Takuya Yoshioka, Michael Zeng, Xuedong Huang


  Access Paper or Ask Questions

Integrating Rankings into Quantized Scores in Peer Review


Apr 05, 2022
Yusha Liu, Yichong Xu, Nihar B. Shah, Aarti Singh

* 14 main pages, 7 appendix pages 

  Access Paper or Ask Questions

Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data


Mar 16, 2022
Shuohang Wang, Yichong Xu, Yuwei Fang, Yang Liu, Siqi Sun, Ruochen Xu, Chenguang Zhu, Michael Zeng

* Accept to ACL 2022 main conference 

  Access Paper or Ask Questions

Unsupervised Summarization with Customized Granularities


Jan 29, 2022
Ming Zhong, Yang Liu, Suyu Ge, Yuning Mao, Yizhu Jiao, Xingxing Zhang, Yichong Xu, Chenguang Zhu, Michael Zeng, Jiawei Han

* Preprint 

  Access Paper or Ask Questions

Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention


Dec 14, 2021
Yichong Xu, Chenguang Zhu, Shuohang Wang, Siqi Sun, Hao Cheng, Xiaodong Liu, Jianfeng Gao, Pengcheng He, Michael Zeng, Xuedong Huang

* 11 pages, 1 figure, 7 tables 

  Access Paper or Ask Questions

An Empirical Study of Training End-to-End Vision-and-Language Transformers


Nov 25, 2021
Zi-Yi Dou, Yichong Xu, Zhe Gan, Jianfeng Wang, Shuohang Wang, Lijuan Wang, Chenguang Zhu, Pengchuan Zhang, Lu Yuan, Nanyun Peng, Zicheng Liu, Michael Zeng


  Access Paper or Ask Questions

Leveraging Knowledge in Multilingual Commonsense Reasoning


Oct 16, 2021
Yuwei Fang, Shuohang Wang, Yichong Xu, Ruochen Xu, Siqi Sun, Chenguang Zhu, Michael Zeng

* First place in XCSR Leaderboard: https://inklab.usc.edu//XCSR/leaderboard. Work in progress 

  Access Paper or Ask Questions

Dict-BERT: Enhancing Language Model Pre-training with Dictionary


Oct 13, 2021
Wenhao Yu, Chenguang Zhu, Yuwei Fang, Donghan Yu, Shuohang Wang, Yichong Xu, Michael Zeng, Meng Jiang

* Under Review 

  Access Paper or Ask Questions

KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering


Oct 08, 2021
Donghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu, Shuohang Wang, Yichong Xu, Xiang Ren, Yiming Yang, Michael Zeng


  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

* Preprint 

  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

* Findings of EMNLP 2021, 11 pages 

  Access Paper or Ask Questions

Retrieval Enhanced Model for Commonsense Generation


May 24, 2021
Han Wang, Yang Liu, Chenguang Zhu, Linjun Shou, Ming Gong, Yichong Xu, Michael Zeng

* Findings of ACL-IJCNLP 2021 

  Access Paper or Ask Questions

Fusing Context Into Knowledge Graph for Commonsense Reasoning


Dec 09, 2020
Yichong Xu, Chenguang Zhu, Ruochen Xu, Yang Liu, Michael Zeng, Xuedong Huang


  Access Paper or Ask Questions

Preference-based Reinforcement Learning with Finite-Time Guarantees


Jun 16, 2020
Yichong Xu, Ruosong Wang, Lin F. Yang, Aarti Singh, Artur Dubrawski

* 22 pages, 2 figures 

  Access Paper or Ask Questions

Zeroth Order Non-convex optimization with Dueling-Choice Bandits


Nov 03, 2019
Yichong Xu, Aparna Joshi, Aarti Singh, Artur Dubrawski

* 19 pages, 3 figures 

  Access Paper or Ask Questions

Active Learning for Graph Neural Networks via Node Feature Propagation


Oct 16, 2019
Yuexin Wu, Yichong Xu, Aarti Singh, Yiming Yang, Artur Dubrawski

* 16 pages, 5 figures 

  Access Paper or Ask Questions

Thresholding Bandit Problem with Both Duels and Pulls


Oct 14, 2019
Yichong Xu, Xi Chen, Aarti Singh, Artur Dubrawski

* 21 pages, 8 figures 

  Access Paper or Ask Questions

DoubleTransfer at MEDIQA 2019: Multi-Source Transfer Learning for Natural Language Understanding in the Medical Domain


Jun 11, 2019
Yichong Xu, Xiaodong Liu, Chunyuan Li, Hoifung Poon, Jianfeng Gao

* Proceedings of the BioNLP 2019 workshop, ACL 2019; 7 pages, 5 tables, 1 figure 

  Access Paper or Ask Questions

Multi-Task Learning for Machine Reading Comprehension


Sep 18, 2018
Yichong Xu, Xiaodong Liu, Yelong Shen, Jingjing Liu, Jianfeng Gao

* 9 pages, 2 figures, 7 tables 

  Access Paper or Ask Questions

On Strategyproof Conference Peer Review


Jun 16, 2018
Yichong Xu, Han Zhao, Xiaofei Shi, Nihar B. Shah


  Access Paper or Ask Questions

Nonparametric Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information


Jun 08, 2018
Yichong Xu, Hariank Muthakana, Sivaraman Balakrishnan, Aarti Singh, Artur Dubrawski

* 21 pages, 5 figures; International Conference on Machine Learning 2018 

  Access Paper or Ask Questions

Dynamic Fusion Networks for Machine Reading Comprehension


Feb 26, 2018
Yichong Xu, Jingjing Liu, Jianfeng Gao, Yelong Shen, Xiaodong Liu

* 13 pages, 5 figures, 5 tables 

  Access Paper or Ask Questions

Noise-Tolerant Interactive Learning from Pairwise Comparisons


May 19, 2017
Yichong Xu, Hongyang Zhang, Aarti Singh, Kyle Miller, Artur Dubrawski

* 28 pages, 1 figure, 3 tables 

  Access Paper or Ask Questions

The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification


Nov 24, 2014
Tianjun Xiao, Yichong Xu, Kuiyuan Yang, Jiaxing Zhang, Yuxin Peng, Zheng Zhang


  Access Paper or Ask Questions

Scale-Invariant Convolutional Neural Networks


Nov 24, 2014
Yichong Xu, Tianjun Xiao, Jiaxing Zhang, Kuiyuan Yang, Zheng Zhang

* This paper is submitted for CVPR2015 

  Access Paper or Ask Questions