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 Zhe Gan

CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning


Apr 13, 2021
Luowei Zhou, Jingjing Liu, Yu Cheng, Zhe Gan, Lei Zhang

* 12 pages, 4 figures 

  Access Paper or Ask Questions

The Elastic Lottery Ticket Hypothesis


Mar 30, 2021
Xiaohan Chen, Yu Cheng, Shuohang Wang, Zhe Gan, Jingjing Liu, Zhangyang Wang


  Access Paper or Ask Questions

Adversarial Feature Augmentation and Normalization for Visual Recognition


Mar 22, 2021
Tianlong Chen, Yu Cheng, Zhe Gan, Jianfeng Wang, Lijuan Wang, Zhangyang Wang, Jingjing Liu


  Access Paper or Ask Questions

Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning


Mar 17, 2021
Siyang Yuan, Pengyu Cheng, Ruiyi Zhang, Weituo Hao, Zhe Gan, Lawrence Carin

* To appear in ICLR 2021 

  Access Paper or Ask Questions

Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly


Feb 28, 2021
Tianlong Chen, Yu Cheng, Zhe Gan, Jingjing Liu, Zhangyang Wang


  Access Paper or Ask Questions

Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling


Feb 11, 2021
Jie Lei, Linjie Li, Luowei Zhou, Zhe Gan, Tamara L. Berg, Mohit Bansal, Jingjing Liu

* 12 pages, 5 figures, 11 tables. - Happy Chinese New Year! 

  Access Paper or Ask Questions

EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets


Dec 31, 2020
Xiaohan Chen, Yu Cheng, Shuohang Wang, Zhe Gan, Zhangyang Wang, Jingjing Liu


  Access Paper or Ask Questions

Wasserstein Contrastive Representation Distillation


Dec 15, 2020
Liqun Chen, Zhe Gan, Dong Wang, Jingjing Liu, Ricardo Henao, Lawrence Carin


  Access Paper or Ask Questions

A Closer Look at the Robustness of Vision-and-Language Pre-trained Models


Dec 15, 2020
Linjie Li, Zhe Gan, Jingjing Liu


  Access Paper or Ask Questions

InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective


Oct 14, 2020
Boxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li, Jingjing Liu

* 20 pages, 8 tables, 2 figures 

  Access Paper or Ask Questions

Cross-Thought for Sentence Encoder Pre-training


Oct 07, 2020
Shuohang Wang, Yuwei Fang, Siqi Sun, Zhe Gan, Yu Cheng, Jing Jiang, Jingjing Liu

* Accepted by EMNLP 2020 

  Access Paper or Ask Questions

Multi-Fact Correction in Abstractive Text Summarization


Oct 06, 2020
Yue Dong, Shuohang Wang, Zhe Gan, Yu Cheng, Jackie Chi Kit Cheung, Jingjing Liu

* 12 pages, accepted at EMNLP2020 

  Access Paper or Ask Questions

MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network


Oct 03, 2020
Yi Wei, Zhe Gan, Wenbo Li, Siwei Lyu, Ming-Ching Chang, Lei Zhang, Jianfeng Gao, Pengchuan Zhang

* published at ACCV2020 

  Access Paper or Ask Questions

Efficient Robust Training via Backward Smoothing


Oct 03, 2020
Jinghui Chen, Yu Cheng, Zhe Gan, Quanquan Gu, Jingjing Liu

* 12 pages, 11 tables, 5 figures 

  Access Paper or Ask Questions

Contrastive Distillation on Intermediate Representations for Language Model Compression


Sep 29, 2020
Siqi Sun, Zhe Gan, Yu Cheng, Yuwei Fang, Shuohang Wang, Jingjing Liu

* Accepted by EMNLP 2020 

  Access Paper or Ask Questions

FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding


Sep 17, 2020
Yuwei Fang, Shuohang Wang, Zhe Gan, Siqi Sun, Jingjing Liu

* Top-1 Performance on XTREME (https://sites.research.google/xtreme, September 8, 2020) and XGLUE (https://microsoft.github.io/XGLUE, September 14, 2020) benchmark 

  Access Paper or Ask Questions

Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding


Sep 13, 2020
Shuohang Wang, Luowei Zhou, Zhe Gan, Yen-Chun Chen, Yuwei Fang, Siqi Sun, Yu Cheng, Jingjing Liu

* 10 pages 

  Access Paper or Ask Questions

Accelerating Real-Time Question Answering via Question Generation


Sep 10, 2020
Yuwei Fang, Shuohang Wang, Zhe Gan, Siqi Sun, Jingjing Liu


  Access Paper or Ask Questions

CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information


Jul 14, 2020
Pengyu Cheng, Weituo Hao, Shuyang Dai, Jiachang Liu, Zhe Gan, Lawrence Carin

* Accepted by the 37th International Conference on Machine Learing (ICML2020) 

  Access Paper or Ask Questions

Graph Optimal Transport for Cross-Domain Alignment


Jun 29, 2020
Liqun Chen, Zhe Gan, Yu Cheng, Linjie Li, Lawrence Carin, Jingjing Liu

* ICML 2020 

  Access Paper or Ask Questions

Adaptive Learning Rates with Maximum Variation Averaging


Jun 21, 2020
Chen Zhu, Yu Cheng, Zhe Gan, Furong Huang, Jingjing Liu, Tom Goldstein


  Access Paper or Ask Questions

Large-Scale Adversarial Training for Vision-and-Language Representation Learning


Jun 11, 2020
Zhe Gan, Yen-Chun Chen, Linjie Li, Chen Zhu, Yu Cheng, Jingjing Liu


  Access Paper or Ask Questions

Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models


May 15, 2020
Jize Cao, Zhe Gan, Yu Cheng, Licheng Yu, Yen-Chun Chen, Jingjing Liu


  Access Paper or Ask Questions

Improving Adversarial Text Generation by Modeling the Distant Future


May 04, 2020
Ruiyi Zhang, Changyou Chen, Zhe Gan, Wenlin Wang, Dinghan Shen, Guoyin Wang, Zheng Wen, Lawrence Carin

* ACL 2020. arXiv admin note: substantial text overlap with arXiv:1811.00696 

  Access Paper or Ask Questions