Weiyang Liu

Google Scholar   Github


College of Computing
Georgia Institute of Technology


Email: wyliu [at] gatech [dot] edu

About Me

I am fortunate to conduct research at Georgia Tech with Prof. Le Song and Prof. Jim Rehg. During my study, I have the great pleasure to work with and learn from many talented researchers. I also spent great time in NVIDIA Research and MERL. I was honored to be a recipient of Baidu Scholarship.


My research interest broadly lies in machine learning and computer vision. My research aims to tackle challenging practical problems, and develop "light-and-sweet" algorithms: (i) light: conceptually simple in methodology and easy to implement in practice, (ii) sweet: having clear intuitions and non-trivial theoretical guarantees.


"Everything should be made as simple as possible, but not simpler."


Disjoint Mapping Network for Cross-modal Matching of Voices and Faces
Yandong Wen, Mahmoud Alismail, Weiyang Liu, Bhiksha Raj, Rita Singh

ICLR 2019

arXiv | code | openreview | bib

      title={Disjoint Mapping Network for Cross-modal Matching of Voices and Faces},
      author={Wen, Yandong and Alismail, Mahmoud and Liu, Weiyang and Raj, Bhiksha and Singh, Rita},

Learning towards Minimum Hyperspherical Energy
Weiyang Liu*, Rongmei Lin*, Zhen Liu*, Lixin Liu, Zhiding Yu, Bo Dai, Le Song

NIPS 2018

arXiv | code | project | sphereface+ | talk | slides | bib

      title={Learning towards Minimum Hyperspherical Energy},
      author={Liu, Weiyang and Lin, Rongmei and Liu, Zhen and Liu, Lixin and Yu, Zhiding and Dai, Bo and Song, Le},

Coupled Variational Bayes via Optimization Embedding
Bo Dai, Hanjun Dai, Niao He, Weiyang Liu, Zhen Liu, Jianshu Chen, Lin Xiao, Le Song

NIPS 2018

arXiv | code | poster | bib

      title={Coupled Variational Bayes via Optimization Embedding},
      author={Dai, Bo and Dai, Hanjun and He, Niao and Liu, Weiyang 
       and Liu, Zhen and Chen, Jianshu and Xiao, Lin and Song, Le},

Simultaneous Edge Alignment and Learning
Zhiding Yu, Weiyang Liu, Yang Zou, Chen Feng, Srikumar Ramalingam, Vijaya Kumar, Jan Kautz

ECCV 2018

arXiv | code | project | demo | slides | bib

      title={Simultaneous Edge Alignment and Learning},
      author={Yu, Zhiding and Liu, Weiyang and Zou, Yang and Feng, Chen
       and Ramalingam, Srikumar and Kumar, Vijaya and Kautz, Jan},
      journal={arXiv preprint arXiv:1807.04836},

Towards Black-box Iterative Machine Teaching
Weiyang Liu, Bo Dai, Xingguo Li, Zhen Liu, James Rehg, Le Song

ICML 2018    

arXiv | talk | slides | bib

      author={Liu, Weiyang and Dai, Bo and Li, Xingguo and Rehg, James M and Song, Le},
      title = {Towards Black-box Iterative Machine Teaching},
      booktitle = {ICML},
      year = {2018}}

Decoupled Networks
Weiyang Liu*, Zhen Liu*, Zhiding Yu, Bo Dai, Rongmei Lin, Yisen Wang, James Rehg, Le Song

CVPR 2018   Spotlight

arXiv | code | talk | slides | bib

      author = {Liu, Weiyang and Liu, Zhen and Yu, Zhiding and Dai, Bo and Lin, Rongmei
       and Wang, Yisen and Rehg, James M. and Song, Le},
      title = {Decoupled Networks},
      booktitle = {CVPR},
      year = {2018}}

Iterative Learning with Open-set Noisy Labels
Yisen Wang, Weiyang Liu, Xingjun Ma, James Bailey, Hongyuan Zha, Le Song, Shu-Tao Xia

CVPR 2018   Spotlight

arXiv | code | slides | bib

      author={Wang, Yisen and Liu, Weiyang and Ma, Xingjun and Bailey, James
       and Zha, Hongyuan and Song, Le and Xia, Shu-Tao},
      title={Iterative Learning with Open-set Noisy Labels},
      booktitle = {CVPR},
      year = {2018}}

Deep Hyperspherical Learning
Weiyang Liu, Yan-Ming Zhang, Xingguo Li, Zhiding Yu, Bo Dai, Tuo Zhao, Le Song

NIPS 2017   Spotlight

arXiv | code | project | talk | slides | bib

      title={Deep Hyperspherical Learning},
      author={Liu, Weiyang and Zhang, Yan-Ming and Li, Xingguo and Yu, Zhiding and Dai, Bo and Zhao, Tuo and Song, Le},

Iterative Machine Teaching
Weiyang Liu, Bo Dai, Ahmad Humayun, Charlene Tay, Yu Chen, Linda Smith, James Rehg, Le Song

ICML 2017

arXiv | code | demo | talk | slides | bib

      title={Iterative Machine Teaching},
      author={Liu, Weiyang and Dai, Bo and Humayun, Ahmad and Tay, Charlene and Yu, Chen
       and Smith, Linda B and Rehg, James M and Song, Le},

SphereFace: Deep Hypersphere Embedding for Face Recognition
Weiyang Liu, Yandong Wen, Zhiding Yu, Ming Li, Bhiksha Raj, Le Song
CVPR 2017

arXiv | code | project | demo | slides | bib

      title = {SphereFace: Deep Hypersphere Embedding for Face Recognition},
      author = {Liu, Weiyang and Wen, Yandong and Yu, Zhiding and Li, Ming and Raj, Bhiksha and Song, Le},
      booktitle = {CVPR},
      year = {2017}}

Large-Margin Softmax Loss for Convolutional Neural Networks
Weiyang Liu, Yandong Wen, Zhiding Yu, Meng Yang
ICML 2016

arXiv | code | project | talk | slides | bib

      title={Large-Margin Softmax Loss for Convolutional Neural Networks},
      author={Liu, Weiyang and Wen, Yandong and Yu, Zhiding and Yang, Meng},

Preprints / Workshops

Bayesian Meta-network Architecture Learning
Albert Shaw, Bo Dai, Weiyang Liu, Le Song

NIPS 2018 Workshop on Bayesian Deep Learning

arXiv | code | bib

      title={Bayesian Meta-network Architecture Learning},
      author={Shaw, Albert and Dai, Bo and Liu, Weiyang and Song, Le},
      journal={NIPS Workshop on Bayesian Deep Learning},

Additive Margin Softmax for Face Verification
Feng Wang, Weiyang Liu, Haijun Liu, Jian Cheng

ICLR 2018 Workshop    

arXiv | code | bib

      title = {Additive Margin Softmax for Face Verification},
      author = {Wang, Feng and Liu, Weiyang and Liu, Haijun and Cheng, Jian},
      journal = {arXiv preprint arXiv:1801.05599},
      year = {2018}}

Academic Service

  • Journal Reviewer: TPAMI, IJCV, etc.
  • Conference Reviewer: ICML 2019/2018, NIPS 2018/2016, CVPR 2019/2018, ICCV 2019/2015, etc.


    • 2018    Baidu Scholarship
    • 2016    PKU Best Master Thesis Award
    • 2016    Beijing Outstanding Graduate Award
  • 2015    PKU Academic Innovation Award
  • 2013    Best Bachelor Thesis Award
    • 2011    Outstanding Winner in Mathematical Contest in Modeling (MCM/ICM)


Prof. Le Song, Georgia Tech

Prof. James Rehg, Georgia Tech

Dr. Zhiding Yu, Research Scientist, NVIDIA

Dr. Bo Dai, Research Scientist, Google Brain

Prof. Tuo Zhao, Georgia Tech

Prof. Chen Feng, NYU

Prof. Meng Yang, Sun Yat-Sen University

Prof. Yuexian Zou, Peking University

Prof. Yan-Ming Zhang, NLPR, CASIA

Yandong Wen, Ph.D. candidate, CMU

Zhen Liu, M.S. student, Georgia Tech

Hanjun Dai, Ph.D. candidate, Georgia Tech

Xingguo Li, Ph.D. candidate, University of Minnesota Twin Cities

Zhehui Chen, Ph.D. candidate, Georgia Tech

Jianhan Mei, Ph.D. candidate, Nanyang Technological University

Rongmei Lin, Ph.D. student, Emory University

Yisen Wang, Ph.D. candidate, Tsinghua University

Feng Wang, Ph.D. candidate, UESTC

Last updated on 26th Oct. 2018.
This site has been visisted Free Web Counter times in total.