I was a Ph.D. student in Computer Science Department, Stanford University working with Prof. Daphne Koller from 2009 to 2014.
I helped build intelligent machines at Vicarious from 2014 to 2018.
Now I'm leading Kwai Silicon Valley Lab.
Contact: huayanw at cs dot stanford dot edu
Dileep George, Wolfgang Lehrach, Ken Kansky, Miguel Lázaro-Gredilla, Christopher Laan, Bhaskara Marthi, Xinghua Lou, Zhaoshi Meng, Yi Liu, Huayan Wang, Alex Lavin, D. Scott Phoenix: A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs, Science Vol. 358, Issue 6368, 08 Dec 2017
Austin Stone, Huayan Wang, Michael Stark, Yi Liu, D. Scott Phoenix, Dileep George: Teaching Compositionality to CNNs, (CVPR 2017)
Huayan Wang and Daphne Koller: A Fast and Exact Energy Minimization Algorithm for Cycle MRFs, The 30th International Conference on Machine Learning (ICML 2013) [PDF] [Code]
Huayan Wang and Daphne Koller: Subproblem-Tree Calibration: A Unified Approach to Max-Product Message Passing, The 30th International Conference on Machine Learning (ICML 2013) [PDF] [Long version with proofs] [Code]
Andrew Chou, Huayan Wang, Michael Stark, and Daphne Koller: Modeling Instance Appearance for Recognition - Can We Do Better Than EM? CVPR-SPTLI (workshop) 2013 [LINK]
Huayan Wang, Stephen Gould, and Daphne Koller: Discriminative Learning with Latent Variables for Cluttered Indoor Scene Understanding, Communications of the ACM, Research Highlights, April 2013 [LINK]
Huayan Wang and Daphne Koller: Multi-Level Inference by Relaxed Dual Decomposition for Human Pose Segmentation, Computer Vision and Pattern Recognition (CVPR 2011) [PDF]
Huayan Wang and Qiang Yang: Transfer Learning by Structural Analogy, The Twenty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2011) [PDF]
Huayan Wang, Stephen Gould, and Daphne Koller: Discriminative Learning with Latent Variables for Cluttered Indoor Scene Understanding, The 11th European Conference on Computer Vision (ECCV 2010, Oral presentation) [PDF]
Yi Liu, Xu-Lei Wang, Hua-Yan Wang, Hongbin Zha, Hong Qin: Learning Robust Similarity Measures for 3D Partial Shape Retrieval, International Journal of Computer Vision , Volume 89, Numbers 2-3, (IJCV 2010). [LINK]
Hua-Yan Wang, Vincent W. Zheng, Junhui Zhao and Qiang Yang: Indoor Localization in Multi-Floor Environments with Reduced Effort, The 8th Annual IEEE International Conference on Pervasive Computing and Communications (PerCom 2010) [PDF]
Hua-Yan Wang, Qiang Yang, Hongbin Zha: Adaptive p-Posterior Mixture-Model Kernels for Multiple Instance Learning, The 25th International Conference on Machine Learning (ICML 2008) [PDF]
Hua-Yan Wang, Qiang Yang, Hong Qin, Hongbin Zha: Dirichlet Component Analysis: Feature Extraction for Compositional Data, The 25th International Conference on Machine Learning (ICML 2008) [PDF]
Hua-Yan Wang, Hongbin Zha, Hong Qin: Dirichlet aggregation: unsupervised learning towards an optimal metric for proportional data, The 24th International Conference on Machine Learning (ICML 2007) [PDF]
We developed a tool for MAP inference (energy minimization). It is based on our two ICML 2013 papers. The code
[Download Code] | [README] | [Brief intro]
We also collected 29 datasets with 2,757 MAP inference tasks from a variety of sources.
[Download Datasets] | [Description] | [Summary Stats] | [Embeded]
Winter Qtr 2011: TA for Prof. Daphne Koller 's course CS228: Probabilistic Graphical Models: Principles and Techniques.
Winter Qtr 2010: TA for Prof. Li Fei-Fei's course CS223B: Introduction to Computer Vision .
Research Assistant, Hong Kong University of Science and Technology (HKUST), 2007~2009. Supervisor: Prof. Qiang Yang
M.E. in Signal and Information Processing, Peking University, 2005~2008, Advisor: Prof. Hongbin Zha
B.S. in Mathematics, Peking University, 2001~2005
Last modified Mar 5 2019