I'm working on applied reinforcement learning for several Facebook's products at the ReAgent Team.
Previously, I studied Computer Science and Mathematics at Carnegie Mellon University.

See my publications and projects below!

C.V. / Github / Google Scholar / Calendar

NEWS






PUBLICATIONS
Scalable and provably accurate algorithms for differentially private distributed decision tree learning
Kai Wen Wang, Travis Dick, Nina Balcan
The AAAI Workshop on Privacy-Preserving Machine Learning @ AAAI-20 (Oral, 20% acceptance)
arxiv
code
proceedings
Image-derived generative modeling of pseudo-macromolecular structures --- towards statistical assessment of electron cryotomography template matching
Kai Wen Wang, Xiangrui Zeng, Xiaodan Liang, Zhiguang Huo, Eric P. Xing
British Machine Vision Conference 2018
arxiv
proceedings
poster
Respond-CAM: Analyzing deep models for 3D imaging data by visualizations
Guannan Zhao, Bo Zhou, Kai Wen Wang, Rui Jiang, Min Xu
International Conference On Medical Image Computing & Computer Assisted Intervention 2018
arxiv
proceedings
Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography
Chang Liu, Xiangrui Zeng, Kai Wen Wang, Qiang Guo, Min Xu
British Machine Vision Conference 2018
arxiv
proceedings



PROJECTS
Hyperboard: Tracking productivity in edge-based image discovery with Eureka
Research Project with Professor Satya
report
poster
Reinforcement Learning Assembly (ReLA)
Internship Project from the RL Team at FAIR.
Includes Ape-X and R2D2, the 2018 and 2019 SOTA distributed RL algorithms on Atari.
code
Classifying Blazars and Cataclysmic Variables from the Catalina Real-Time Transient Survey
10-701 Class Project
paper