Research

My research interests include statistical modeling, machine learning, and computer vision. My current research mainly focuses on generative modeling and deep learning.

•2012.9 - now. Center for Vision, Cognition, Learning, and Autonomy, UCLA.
 Generative modeling and deep learning.

•2010.7 - 2012.7 Lotus Hill Institute and BUPT, Wuhan and Beijing.
 Vehicle detection.

•2009.7 - 2012.3 Lab for Optoelectronics and Information System, BIT.
 Augmented reality.

  Projects

Cooperative Training of Descriptor and Generator Networks

JIanwen Xie, Yang Lu, Song-Chun Zhu , and Ying Nian Wu

arXiv 1609.09408.   [pdf]

[Project page]

Alternating Back-Propagation for Generator Network

Tian Han*, Yang Lu* , Song-Chun Zhu , and Ying Nian Wu
*Equal Contributions

AAAI, 2017 (Accepted).   [pdf]

[Project page]

A Theory of Generative ConvNet

Jianwen Xie*, Yang Lu* , Song-Chun Zhu , and Ying Nian Wu
*Equal Contributions

ICML, 2016.   [pdf]

[Project page]

Learning FRAME Models Using CNN Filters

Yang Lu, Song-Chun Zhu, and Ying Nian Wu

AAAI, 2016.   [pdf]

[Project page]

Inducing Wavelets into Random Fields via Generative Boosting

Jianwen Xie, Yang Lu, Song-Chun Zhu, Ying Nian Wu

Applied and Computational Harmonic Analysis, 2015.   [pdf]

[Project page]

Generative Modeling of Convolutional Neural Networks

Jifeng Dai, Yang Lu, and Ying Nian Wu

ICLR, 2015.  [pdf]

[Project page ]

Online Object Tracking, Learning and Parsing with And-Or Graphs

Yang Lu, Tianfu Wu and Song-Chun Zhu

CVPR, 2014.  [pdf]

[Project page]

Reconfigurable Templates for Robust Vehicle Detection and Classification

Y. Lu, B. Yao, Y. Wang and S.C. Zhu

Workshop on Application of Computer Vision (WACV), Colorado, 2012.  [pdf]

  Publications

1. J Xie, Yang Lu, Song-Chun Zhu, Ying Nian Wu. Cooperative Training of Descriptor and Generator Networks. arXiv, 2016.
2. Tian Han*, Yang Lu*, Song-Chun Zhu, Ying Nian Wu. Alternating Back-Propagation for Generator Network. AAAI, 2017(Accepted). (* equal contribution)
3. Jianwen Xie*, Yang Lu*, Song-Chun Zhu, Ying Nian Wu. A Theory of Generative ConvNet. ICML, 2016. (* equal contribution)
4. Yang Lu, Song-Chun Zhu, Ying Nian Wu. Learning FRAME Models Using CNN Filters. AAAI, 2016.
5. Jianwen Xie, Yang Lu, Song-Chun Zhu, Ying Nian Wu. Inducing Wavelets into Random Fields via Generative Boosting. Applied and Computational Harmonic Analysis, 2015.
6. Jifeng Dai, Yang Lu, Ying Nian Wu. Generative Modeling of Convolutional Neural Networks Boosting. ICLR, 2015.
7. Jifeng Dai, Yang Lu, Ying Nian Wu. Generative Modeling of Convolutional Neural Networks Boosting. Statistics and Its Interface, 2015.
8. Yang Lu, Tianfu Wu, Song-Chun Zhu. Online Object Tracking, Learning and Parsing with And-Or Graphs. CVPR, 2014.
9. Yang Lu, B. Yao, Y. Wang, Song-Chun Zhu. Reconfigurable Templates for Robust Vehicle Detection and Classification. WACV, 2012.

  Under Review

1. Yang Lu, Song-Chun Zhu, Ying Nian Wu. Exploring Generative Perspective of Convolutional Neural Networks by Learning Random Field Models. 2016.
2. Jianwen Xie*, Yang Lu*, Song-Chun Zhu, Ying Nian Wu. A Theory of Generative ConvNet. 2016. (* equal contribution. Short version appeared in ICML 2016)
3. Tianfu Wu, Yang Lu, Song-Chun Zhu. Online Object Tracking, Learning and Parsing with And-Or Graphs. 2016. (Short version appeared in CVPR 2014)

  Teaching

Teaching Assistant:
Stat 231--- CS 276A
Professor Song-Chun Zhu

Project supplementary materials:
1. Geoffrey Hinton, A Practical Guide to Training Restricted Boltzmann Machines. [pdf]

  Education

•2012.9 - now. PhD candidate, Department of Statistics, University of California, Los Angeles, United States.
•2009.9 - 2012.3. M.S., Department of Computer Science, Beijing Institute of Technology, Beijing, China.
•2005.9 - 2009.7. B.S., Department of Computer Science, Beijing Institute of Technology, Beijing, China.