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 Chunyuan Li

RegionCLIP: Region-based Language-Image Pretraining


Dec 16, 2021
Yiwu Zhong, Jianwei Yang, Pengchuan Zhang, Chunyuan Li, Noel Codella, Liunian Harold Li, Luowei Zhou, Xiyang Dai, Lu Yuan, Yin Li, Jianfeng Gao

* Technical report 

  Access Paper or Ask Questions

LAFITE: Towards Language-Free Training for Text-to-Image Generation


Dec 13, 2021
Yufan Zhou, Ruiyi Zhang, Changyou Chen, Chunyuan Li, Chris Tensmeyer, Tong Yu, Jiuxiang Gu, Jinhui Xu, Tong Sun

* The code and pre-trained models will be publicly available soon 

  Access Paper or Ask Questions

Grounded Language-Image Pre-training


Dec 07, 2021
Liunian Harold Li, Pengchuan Zhang, Haotian Zhang, Jianwei Yang, Chunyuan Li, Yiwu Zhong, Lijuan Wang, Lu Yuan, Lei Zhang, Jenq-Neng Hwang, Kai-Wei Chang, Jianfeng Gao

* Code will be released at https://github.com/microsoft/GLIP 

  Access Paper or Ask Questions

A Generic Approach for Enhancing GANs by Regularized Latent Optimization


Dec 07, 2021
Yufan Zhou, Chunyuan Li, Changyou Chen, Jinhui Xu


  Access Paper or Ask Questions

Florence: A New Foundation Model for Computer Vision


Nov 22, 2021
Lu Yuan, Dongdong Chen, Yi-Ling Chen, Noel Codella, Xiyang Dai, Jianfeng Gao, Houdong Hu, Xuedong Huang, Boxin Li, Chunyuan Li, Ce Liu, Mengchen Liu, Zicheng Liu, Yumao Lu, Yu Shi, Lijuan Wang, Jianfeng Wang, Bin Xiao, Zhen Xiao, Jianwei Yang, Michael Zeng, Luowei Zhou, Pengchuan Zhang


  Access Paper or Ask Questions

SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching


Oct 21, 2021
Baolin Peng, Chunyuan Li, Zhu Zhang, Jinchao Li, Chenguang Zhu, Jianfeng Gao

* 8 pages 

  Access Paper or Ask Questions

Focal Self-attention for Local-Global Interactions in Vision Transformers


Jul 01, 2021
Jianwei Yang, Chunyuan Li, Pengchuan Zhang, Xiyang Dai, Bin Xiao, Lu Yuan, Jianfeng Gao


  Access Paper or Ask Questions

Efficient Self-supervised Vision Transformers for Representation Learning


Jun 17, 2021
Chunyuan Li, Jianwei Yang, Pengchuan Zhang, Mei Gao, Bin Xiao, Xiyang Dai, Lu Yuan, Jianfeng Gao

* 24 pages, 12 figures, file size 13.6MB 

  Access Paper or Ask Questions

Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation


May 23, 2021
Jinyu Yang, Chunyuan Li, Weizhi An, Hehuan Ma, Yuzhi Guo, Yu Rong, Peilin Zhao, Junzhou Huang

* 10 pages, 4 figures 

  Access Paper or Ask Questions

Contrastive Conditional Transport for Representation Learning


May 08, 2021
Huangjie Zheng, Xu Chen, Jiangchao Yao, Hongxia Yang, Chunyuan Li, Ya Zhang, Hao Zhang, Ivor Tsang, Jingren Zhou, Mingyuan Zhou


  Access Paper or Ask Questions

Partition-Guided GANs


Apr 02, 2021
Mohammadreza Armandpour, Ali Sadeghian, Chunyuan Li, Mingyuan Zhou


  Access Paper or Ask Questions

Leveraging User Behavior History for Personalized Email Search


Mar 17, 2021
Keping Bi, Pavel Metrikov, Chunyuan Li, Byungki Byun

* In proceedings of the Web Conference 2021 

  Access Paper or Ask Questions

Self-supervised Pre-training with Hard Examples Improves Visual Representations


Jan 04, 2021
Chunyuan Li, Xiujun Li, Lei Zhang, Baolin Peng, Mingyuan Zhou, Jianfeng Gao


  Access Paper or Ask Questions

SDA: Improving Text Generation with Self Data Augmentation


Jan 02, 2021
Ping Yu, Ruiyi Zhang, Yang Zhao, Yizhe Zhang, Chunyuan Li, Changyou Chen


  Access Paper or Ask Questions

Few-Shot Named Entity Recognition: A Comprehensive Study


Dec 29, 2020
Jiaxin Huang, Chunyuan Li, Krishan Subudhi, Damien Jose, Shobana Balakrishnan, Weizhu Chen, Baolin Peng, Jianfeng Gao, Jiawei Han


  Access Paper or Ask Questions

RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems


Dec 29, 2020
Baolin Peng, Chunyuan Li, Zhu Zhang, Chenguang Zhu, Jinchao Li, Jianfeng Gao

* 12 pages; Project website at aka.ms/raddle 

  Access Paper or Ask Questions

Hierarchical Graph Capsule Network


Dec 16, 2020
Jinyu Yang, Peilin Zhao, Yu Rong, Chaochao Yan, Chunyuan Li, Hehuan Ma, Junzhou Huang

* AAAI 2021 

  Access Paper or Ask Questions

ReMP: Rectified Metric Propagation for Few-Shot Learning


Dec 02, 2020
Yang Zhao, Chunyuan Li, Ping Yu, Changyou Chen

* Tech Report, 11 pages 

  Access Paper or Ask Questions

Improving Text Generation with Student-Forcing Optimal Transport


Oct 12, 2020
Guoyin Wang, Chunyuan Li, Jianqiao Li, Hao Fu, Yuh-Chen Lin, Liqun Chen, Yizhe Zhang, Chenyang Tao, Ruiyi Zhang, Wenlin Wang, Dinghan Shen, Qian Yang, Lawrence Carin

* To appear at EMNLP 2020 

  Access Paper or Ask Questions

Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference


Sep 20, 2020
Bang An, Jie Lyu, Zhenyi Wang, Chunyuan Li, Changwei Hu, Fei Tan, Ruiyi Zhang, Yifan Hu, Changyou Chen

* accepted by EMNLP2020 

  Access Paper or Ask Questions

Robust Conversational AI with Grounded Text Generation


Sep 07, 2020
Jianfeng Gao, Baolin Peng, Chunyuan Li, Jinchao Li, Shahin Shayandeh, Lars Liden, Heung-Yeung Shum


  Access Paper or Ask Questions

Weakly supervised cross-domain alignment with optimal transport


Aug 14, 2020
Siyang Yuan, Ke Bai, Liqun Chen, Yizhe Zhang, Chenyang Tao, Chunyuan Li, Guoyin Wang, Ricardo Henao, Lawrence Carin

* Accepted to BMVC 2020 (Oral) 

  Access Paper or Ask Questions

Structure-Aware Human-Action Generation


Jul 16, 2020
Ping Yu, Yang Zhao, Chunyuan Li, Junsong Yuan, Changyou Chen

* accepted by ECCV 2020 

  Access Paper or Ask Questions

Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks


May 18, 2020
Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, Yejin Choi, Jianfeng Gao

* Code and pre-trained models are released: https://github.com/microsoft/Oscar 

  Access Paper or Ask Questions

SOLOIST: Few-shot Task-Oriented Dialog with A Single Pre-trained Auto-regressive Model


May 14, 2020
Baolin Peng, Chunyuan Li, Jinchao Li, Shahin Shayandeh, Lars Liden, Jianfeng Gao

* 10 pages; Project Website: https://aka.ms/soloist 

  Access Paper or Ask Questions