Gautam Singh

Ph.D. Student, Department of Computer Science, Rutgers University · CV

617 Bowser Road

Piscataway

New Jersey

I am a Ph.D. student in Computer Science at Rutgers University focusing on Machine Learning, advised by Prof. Sungjin Ahn.

I am interested in unsupervised scene representation learning and I am focusing on object-centric scene representations. I am also interested in the applications of object-centric scene representations in reinforcement learning.

Before joining Ph.D. in 2018, I worked at IBM Research India for 3 years. I received a Bachelor of Technology degree from Indian Institute of Technology (IIT) Guwahati in 2015. I also spent a summer at Korea Advanced Institute of Science and Technology (KAIST) as a research intern in 2014.

News

May 24, 2021 Joined Amazon as an Applied Scientist Intern for the summer of 2021.
May 8, 2021 Our paper Structured World Belief for Reinforcement Learning in POMDP is accepted at ICML 2021.

Selected Publications

* denotes equal contribution.

  1. ICML 2021
    Structured World Belief for Reinforcement Learning in POMDP
    Gautam Singh, Skand Peri, Junghyun Kim, Hyunseok Kim, and Sungjin Ahn
    International Conference on Machine Learning 2021
  2. ICML 2020
    Robustifying Sequential Neural Processes
    Jaesik Yoon, Gautam Singh, and Sungjin Ahn
    International Conference on Machine Learning 2020
  3. ICLR 2020
    SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition
    Zhixuan Lin*, Yi-Fu Wu*, Skand Vishwanath Peri*, Weihao Sun, Gautam Singh, Fei Deng, Jindong Jiang, and Sungjin Ahn
    International Conference on Learning Representations 2020
  4. NeurIPS 2019
    Spotlight
    Sequential Neural Processes
    Gautam Singh*, Jaesik Yoon*, Youngsung Son, and Sungjin Ahn
    Advances in Neural Information Processing Systems 2019