Xin Wang

I am a Ph.D student in the Computer Science Department at UC Berkeley. I'm part of the RISE Lab (formerly AMP Lab). I'm fortunate to be advised by Prof. Joseph E. Gonzalez . Prior to that, I obtained my Bachelor's degree from Shanghai Jiao Tong University .

My research interest lies in the intersection of deep learning and data systems. My recent work focuses on model inference speedup and the design of neural networks that can adapt computation on a per-input basis.

Office: 465 Soda Hall, Berkeley, CA 94720
Email: xinw@eecs.berkeley.edu

Publications

SkipNet: Learning Dynamic Routing in Convolutional Networks
Xin Wang, Fisher Yu, Zi-Yi Dou, Joseph E. Gonzalez
Preprint
IDK Cascades: Fast Deep Learning by Learning not to Overthink
Xin Wang, Yujia Luo, Daniel Crankshaw, Alexey Tumanov, Fisher Yu, Joseph E. Gonzalez
Preprint
Clipper: A Low-Latency Online Prediction Serving System
Daniel Crankshaw, Xin Wang, Guilio Zhou, Michael J. Franklin, Joseph E. Gonzalez, Ion Stoica
USENIX Symposium on Networked Systems Design and Implementation (NSDI) 2017
Scalable Training and Serving of Personalized Models
Daniel Crankshaw, Xin Wang, Joseph E. Gonzalez, Michael J. Franklin
LearningSys 2015

Teaching

Experience