• Resume
  • Print CV
  • Contact me
  • View photo


Princeton UniversitySept. 2014 - Current

Ph. D. Candidate

Research interests:
  Automated neural network architecture synthesis
  Deep neural network compression
  Efficient DNN for mobile
Advisor: Prof. Niraj K. Jha

Peking UniversitySept. 2010 - Jul. 2014

Bachelor of Science

Work and Research Experience

Facebook Research (AI Mobile Vision) May 2018 - Current

Research Intern
  Efficient DNN for mobile
  Paper and code available at https://github.com/facebookresearch/mobile-vision

Princeton University Sept. 2014 - Current

Automated architecture synthesis for CNN, RNN, and LSTM
  Train both weights and architecture with gradient descent
  Enable neural network to adaptively adjust their structure during training
  Generate compact yet accurate neural network in an automated flow

Convolutional neural network compression
  Propose an architecture compression algorithm based on a grow-and-prune paradigm
  Reduce both memory and computation cost of deep neural networks
  Achieve 15.7x (4.6x) parameters (FLOPs) reduction on AlexNet (current state-of-the-art)

Online learning with reconfigurable neural networks
  Design reconfigurable neural networks that can grow and prune neurons/connections
  Allow online learning systems to adaptively adjust neural network capability
  Generate inference models with high accuracy/cost ratio in real-time

Tensilica at Cadence Design System Inc. May 2016 - Aug. 2016

DSP Software Engineer Intern

Simultaneous localization and mapping (SLAM)
  Targeted at map establishment and localization problem in robot navigation
  Implemented scan-matching, extended Kalman filter, and computer vision based solutions
  Built and tested a real SLAM platform with LIDAR and camera in a real indoor environment


X. Dai, P. Zhang, B. Wu, H. Yin, F. Sun, Y. Wang, M. Dukhan, Y. Hu, Y. Wu, Y. Jia, P. Vajda, M. Uyttendaele, and N. K. Jha, "ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation." in Proc. IEEE Conf. CVPR, 2019
B. Wu, X. Dai, P. Zhang, Y. Wang, Y., F. Sun, Y. Wu, Y. Tian, P. Vajda, Y. Jia, and K. Keutzer,"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search." in Proc. IEEE Conf. CVPR, 2019
X. Dai, H. Yin, and N. K. Jha, "Grow and Prune Compact, Fast, and Accurate LSTMs" arXiv prepring arXiv:1805.11797, May 2018.
X. Dai, H. Yin, and N. K. Jha, “Nest: A Neural network synthesis tool based on a grow-and-prune paradigm” arXiv preprint arXiv:1711.02017, Sept. 2017.
X. Dai and N. K. Jha, “Device state library: Mechanism to burst the productivity of TCAD mixed-mode simulation,” IEEE Trans. VLSI Syst., May. 2017.
X. Dai and N. K. Jha, “Improving convergence and simulation time of quantum hydrodynamic simulation: Application to extraction of best 10-nm FinFET parameter values” IEEE Trans. VLSI Syst., vol. pp, no. 99, pp. 1–11, May 2016.
A. M. Nia, X. Dai, P. Mittal, and N. K. Jha, ”PinMe: Tracking a smartphone user around the world”, IEEE Trans. Multi-scale Computing, Nov. 2016.
J. Wu, D. Hou, Z. Qin, X. Dai, Z. Zhang, and J. Zhao“Erbium-fiber-laser-based direct frequency comb spectroscopy of Rb two-photon transitions,” Optics Lett., Vol. 38, Issue 23, pp. 5028-5031, Sept. 2013.