About me


Recent News

  • April 12, 2018. New preprint: “CoT: Cooperative Training for Generative Modeling”, a new paradigm for training tractable density generative model that is parallel to adversarial training. Available on arXiv.
  • November 28, 2017. A paper was accepted in the NIPS-17 Aligned Artificial Intelligence Workshop.
  • November 12, 2017. A paper was accepted in the AAAI-18 Artificial Intelligence for Imperfect-Information Games Workshop.
  • September 17, 2017. New preprint: An Empirical Study of AI Population Dynamics with Million-agent Reinforcement Learning. Available on arXiv
  • August 25, 2017. We started the Multi-Agent Reinforcement Learning reading group.
  • August 15, 2017. I started to work as a research intern at Carnegie Mellon University for the next six months.
  • August 9, 2017. I won the Best Paper Award Honorable Mention at SIGIR 2017.
  • August 6 - August 12, 2017. I attended the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval held in Tokyo, Japan.
  • July 26, 2017. I gave an online talk on “Generative Adversarial Networks for Discrete Data” at PaperWeekly.
  • May 19, 2017. A paper titled “A Dynamic Attention Deep Model for Article Recommendation by Learning Human Editors’ Demonstration” was accepted at KDD 2017.
  • April 19, 2017. I gave a talk on applying adversarial training techniques for information retrieval at Apex Lab, Shanghai Jiao Tong University.
  • April 11, 2017. A paper titled “IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models” was accepted at SIGIR 2017.
  • February 4 - February 9, 2017. I attended the Thirty-First AAAI Conference on Artificial Intelligence held in San Francisco, California, US and gave a talk on applying adversarial training for generating sequential data.
  • November 11, 2016. A paper titled “SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient” was accepted at AAAI 2017.