Experience

 
 
 
 
 
July 2018 – January 2019
Cambridge, USA

Research Assistant

Hardware Intelligence Lab (HAN’s lab), Massachusetts Institute of Technology

Advisor: Prof. Song Han

Efficient AutoML methods for specializing neural network architectures on edge devices.
 
 
 
 
 
January 2016 – July 2018
Shanghai, China

Research Assistant

APEX Data & Knowledge Management Lab, Shanghai Jiao Tong University

Advisors: Profs. Yong Yu, Weinan Zhang and Jun Wang

Deep reinforcement learning and its applications in real-world data mining scenarios such as computational advertising, recommender systems and etc.

Publications

Large-scale Interactive Recommendation with Tree-structured Policy Gradient.
. AAAI 2019.

pdf

Path-Level Network Transformation for Efficient Architecture Search.
. ICML 2018.

pdf

Activation Maximization Generative Adversarial Nets.
. ICLR 2018.

pdf

Efficient Architecture Search by Network Transformation.
. AAAI 2018.

pdf

Long Text Generation via Adversarial Training with Leaked Information.
. AAAI 2018.

pdf

MAgent: A Many-Agent Reinforcement Learning Research Platform for Artificial Collective Intelligence.
. NIPS 2017 Demo and AAAI 2018 Demo.

pdf

Volume Ranking and Sequential Selection in Programmatic Display Advertising.
. CIKM 2017.

pdf

Real-Time Bidding by Reinforcement Learning in Display Advertising.
. WSDM 2017.

pdf

Product-Based Neural Networks for User Response Prediction.
. ICDM 2016.

pdf

Contact