Ruiyi Zhang @ Duke CS

Modified: 2014/08/25 22:19 by admin - Uncategorized
Image
Ruiyi Zhang
Chinese name
Ph.D. Candidate
Department of Computer Science
Duke University

Laboratory: D344, LSRC and iiD, Gross Hall, West Campus of Duke University
Email: ryzhang # cs.duke.edu
ImageImage

I am currently a third-year Ph.D. candidate at Department of Computer Science, Duke University.

Edit

About Me

Before that, I received B.Sc. degree in the Department of Computer Science from Nanjing University in 2016. I was a member of LAMDA Group, led by Dr. Zhi-Hua Zhou. I was a research intern at The University of Hong Kong advised by Dr. Reynold Cheng (Summer, 2015), Algorithm Engineer Intern at AntAI Group@Alibaba, led by Dr. Yuan (Alan) Qi (Summer, 2016), and a research intern at Adobe Research advised by Dr. Zheng Wen (Summer, 2018).

Supervisor: Professor Lawrence Carin.
Committee Members: Professor Ron Parr and Professor Rong Ge.

Currently I focused on the subfields:
  • Uncertainty Estimation in Deep Reinforcement Learning (RL);
  • Sequence Matching with deep RL and generative models;
  • Scalable Bayesian sampling and inference.

Edit

News

  • Sep. 2019: One paper (with Adobe Research) has been accepted to WACV 2020.
  • Sep. 2019: Two papers have been accepted to NeurIPS 2019.
  • Jul. 2019: One paper (with Samsung Research) has been accepted to ACMMM 2019.
  • Jun. 2019: I am lucky to be invited to present our recent works in Workshop on Stein's Method @ ICML2019 [Slides]
  • May 2019: I finished the internship with Samsung Research America and start working in Google Brain.
  • May 2019: I passed my Preliminary Exam, and become a Ph.D. Candidate!
  • Apr. 2019: Two papers have been accepted to ICML 2019.
  • Feb. 2019: One paper has been accepted to NAACL 2019.
  • Dec. 2018: One paper (with Adobe Research) has been accepted to AISTATS 2019.
  • Nov. 2018: One paper has been accepted to ICLR 2019.

Edit

Publications

  1. Improving Sequence-to-Sequence Learning via Optimal Transport [Paper] [Code]
    Liqun Chen, Yizhe Zhang, Ruiyi Zhang, Chenyang Tao, Zhe Gan, Bai Li, Dinghan Shen, Changyou Chen, Lawrence Carin
    International Conference for Learning Representations (ICLR), 2019. 
  2. Vision-Language Recommendation via Attribute Augmented Multimodal Reinforcement Learning [Paper]
    Tong Yu, Yilin Shen, Ruiyi Zhang, Xiangyu Zeng, Hongxia Jin
    ACM International Conference on Multimedia (ACMMM), 2019. 
  3. Sequence Generation with a Guider Network [Paper] [Reviews]
    Ruiyi Zhang, Changyou Chen, Zhe Gan, Wenlin Wang, Zheng Wen, Lawrence Carin

    Real-World SDM Workshop, International Conference on Machine Learning (ICML), 2019. 
  4. Figure Captioning with Reasoning and Sequence-Level Training [Preprint]
    Charles Chen, Ruiyi Zhang, Eunyee Koh, Sungchul Kim, Scott Cohen, Ryan Rossi
    Winter Conference on Applications of Computer Vision (WACV), 2020. 
  5. Self-Enhanced Inverse Reinforcement Learning for Text Generation (Oral) [Paper]
    Ping Yu, Ruiyi Zhang, Chunyuan Li, Yizhe Zhang, Changyou Chen
    Imitation, Intent, and Interaction (I3), International Conference on Machine Learning (ICML), 2019. 
  6. Topic-Guided Variational Auto-Encoders for Text Generation (Oral) [Paper]
    Wenlin Wang, Zhe Gan, Hongteng Xu, Ruiyi Zhang, Dinghan Shen, Guoyin Wang, Changyou Chen, Lawrence Carin
    North American Chapter of the Association for Computational Linguistics (NAACL), 2019. 
  7. Scalable Thompson Sampling via Optimal Transport [Paper] [Poster] [Code]
    Ruiyi Zhang, Zheng Wen, Changyou Chen, Chen Fang, Tong Yu, Lawrence Carin
    Artificial Intelligence and Statistics (AISTATS), 2019. 
    Abridged in NeurIPS 2018, Workshop on Infer to Control
  8. Understand and Accelerate Particle-based Variational Inference [Paper] [Poster] [Code]
    Chang Liu, Jingwei Zhang, Pengyu Cheng, Ruiyi Zhang, Jun Zhu, Lawrence Carin
    International Conference on Machine Learning (ICML), 2019. 
  9. Variational Annealing of GANs: A Langevin Perspective [Paper]
    Chenyang Tao, Shuyang Dai, Liqun Chen, Ke Bai, Junya Chen, Chang Liu, Ruiyi Zhang, Georgiy Bobashev, Lawrence Carin
    International Conference on Machine Learning (ICML), 2019. 
  10. Policy Optimization as Wasswerstein Gradient Flows [Paper] [Poster] [Appendix] [Demo]
    Ruiyi Zhang, Changyou Chen, Chunyuan Li, Lawrence Carin
    International Conference on Machine Learning (ICML), 2018. 
    Abridged in NIPS 2017, Workshop on Deep Reinforcement Learning
  11. Learning Structural Weight Uncertainty for Sequential Decision-Making [Paper] [Poster] [Code]
    Ruiyi Zhang, Chunyuan Li, Changyou Chen, Lawrence Carin
    Artificial Intelligence and Statistics (AISTATS), 2018. 
  12. Adverarial Text Generation via Feature-Mover Distance [Paper] [Poster]
    Liqun Chen, Shuyang Dai, Chenyang Tao, Zhe Gan, Dinghan Shen, Yizhe Zhang, Ruiyi Zhang, Guoyin Wang, Lawrence Carin
    Neural Information Processing Systems (NeurIPS), 2018. 
  13. Variational Inference and Model Selection with Generalized Evidence Bounds [Paper] [Appendix]
    Chenyang Tao, Liqun Chen, Ruiyi Zhang, Ricardo Henao, Lawrence Carin
    International Conference on Machine Learning (ICML), 2018. 
  14. A Unified Particle-Optimization Framework for Scalable Bayesian Sampling (Oral) [Paper]
    Changyou Chen, Ruiyi Zhang, Wenlin Wang, Lawrence Carin
    The Conference on Uncertainty in Artificial Intelligence (UAI), 2018. 
  15. Bayesian Deep Q-Learning via Continuous-Time Flows [Paper]
    Ruiyi Zhang, Changyou Chen, Chunyuan Li, Lawrence Carin
    Deep Reinforcement Learning Symposium, Neural Information Processing Systems (NIPS), 2017. 

  16. Edit

    Preprints

  1. Towards Convergence Property of Particle-based Bayesian Sampling Methods [Preprint]
    Jianyi Zhang, Ruiyi Zhang, Changyou Chen

Edit

Professional Sevices


Edit

Awards & Honors

  • Outstanding Graduate Student of Nanjing University, GPA 1st/143 in CS, 2016
  • CCF (China Computer Federation) Outstanding Undergraduate Award 2015
  • Microsoft Young Fellowship by Microsoft Research Aisa 2015
  • Pacemaker of Outstanding Student of Nanjing University (30/12000+) 2014
  • National Undergraduate Scholarship for consecutive three years. 2013




Mail:
D344 LSRC, Box 90129, Duke University, Durham, North Carolina 27708-0129

The end