Zhe Gan

I am a Senior Researcher at Microsoft Cloud and AI, primarily working on Vision-and-Language Representation Learning, and Generative Pre-training Models. I also have broad interests on various machine learning topics. I received my Ph.D. degree from Duke University in Spring 2018. Before that, I received my Master's and B.Sc. from Peking University in 2013 and 2010, respectively. My Ph.D. advisor is Lawrence Carin. I can be reached at zhe.gan@microsoft.com.

I will give a tutorial on Recent Advances in Vision-and-Language Research at CVPR 2020. I will serve as an Area Chair for NeurIPS 2020. I will serve as an Interactive Arts Chair at ACM Multimedia 2020. I received AAAI-20 Outstanding SPC Award. I served as an Area Chair for NeurIPS 2019, and a Senior Program Committee (SPC) member for AAAI 2020.

Research Highlights:

[2020/04] Two CVPR and three ACL papers got accepted, respectively. CVPR papers cover topics including: (i) high-resolution image synthesis from salient object layout, and (ii) a new dataset for video-and-language understanding. ACL papers cover topics include: (i) text summarization based on discourse units, (ii) BERT for text generation, and (iii) text generation that models the distant future.

[2020/03] Will serve as an Area Chair for NeurIPS 2020.

[2020/02] Will give a tutorial on Recent Advances in Vision-and-Language Research at CVPR 2020.

[2020/01] I received AAAI-20 Outstanding SPC Award.

[2019/11] Two papers accepted to AAAI 2020.

[2019/09] Our new work UNITER achieves SOTA on 6 Vision-and-Language tasks across 9 datasets (VQA, VCR, NLVR, Img-Txt Retrieval, Visual Entailment, Referring Expression).

[2019/09] Our latest Adversarial Training model has beaten Facebook's RoBERTa on GLUE benchmark. Paper is available here.

[2019/09] One paper got accepted to NeurIPS.

[2019/08] 4 papers got accepted to EMNLP. Topics include (i) BERT model compression, (ii) domain adaptation for MRC, (iii) domain adaptation for text style transfer, and (iv) image caption evaluation.

[2019/07] One paper got accepted to ICCV, using relation-aware graph attention for VQA.

[2019/06] Will serve as a Senior Program Committee (SPC) member for AAAI 2020.

[2019/02] Will serve as an Area Chair for NeurIPS 2019.

[2018/09] Two papers got accepted to NIPS 2018. The first one proposes Adversarial Information Maximization (AIM) for conversational response generation. The second one proposes feature mover GAN for neural text generation. The acceptance ratio this year is 1011/4856=20.82%.

[2018/02/20] PhD thesis defended.

[2018/02] One paper accepted to CVPR 2018. GAN plus attention results in our AttnGAN, generates realistic images on birds and COCO datasets. See the news coverage here: Drawing AI, among other places.

[2017/09] 4 papers got accepted to NIPS 2017; three of them are on deep generative models, including VAE and GAN variants; the other one is on deconvolutional paragraph representation learning. The acceptance ratio of NIPS 2017 is 678/3240= 20.93%.

[2017/05] I got two papers accepted to ICML this year. One proposes a new GAN model for text generation that handles the discrete nature of text inputs and uses adversarial feature matching, based on our NIPS workshop paper. The other proposes a new SG-MCMC algorithm.

[2017/03] Two papers on image captioning are accepted by CVPR 2017. One proposes semantic compositional network for visual captioning, and the other proposes StyleNet that can generate stylized captions.

[2016/12] Our NIPS workshop paper "Generating text via Adversarial Training" made some initial progress on training a generative adversarial network for generating realistic sentences.

[2016/09] The camera-ready version of our NIPS 2016 paper "Variational Autoencoder for Deep Learning of Images, Labels and Captions" is online now.