George Pu

Currently, I am a Software/Developer Engineer at Amazon.

Previously, I was a research assistant at the NSF Center for Big Learning at the University of Florida, where I did my undergraduate degree in Computer Science. I published papers on robotics and federated learning.

I am broadly interested in all aspects of deep learning, particularly deep reinforcement learning, robust and scalable intelligent systems, and its applications in robotics. I blog about these topics at https://georgerpu.github.io/blog/ along with other computer science topics, mathematics (my first ), and whatever else I find interesting that week.

In my free time, I enjoy watching and playing sports (mainly and video games), trying new food, reading history and social science, and learning new subjects.

news

Dec 01, 2023	I am thrilled to announce that I have been promoted to Software Development Engineer II (SDE II) at Amazon! I would like to express my sincere gratitude to my colleagues, mentors, and managers who have supported me throughout my journey. Their guidance, feedback, and work is as responsible for any success as my own efforts.
May 31, 2021	My senior project was featured in the University of Florida news!
Dec 01, 2020	Communication-efficient federated learning via dataset distillation was accepted to NeurIPS 2020 SpicyFL!

latest posts

Jan 06, 2024	The Inflection Point of the Exponential Function
Dec 31, 2023	2023 in Film
Sep 28, 2023	Blogging for 4 Years

selected publications

ArXiv

Distilled one-shot federated learning

Yanlin Zhou^*, George Pu^*, Xiyao Ma , and 2 more authors

arXiv preprint arXiv:2009.07999, Sep 2020

Bib HTML

@article{zhou2020distilled,
  title = {Distilled one-shot federated learning},
  author = {Zhou, Yanlin and Pu, George and Ma, Xiyao and Li, Xiaolin and Wu, Dapeng},
  journal = {arXiv preprint arXiv:2009.07999},
  year = {2020},
  month = sep,
}

IROS

Adaptive leader-follower formation control and obstacle avoidance via deep reinforcement learning

Yanlin Zhou^*, Fan Lu^*, George Pu^* , and 4 more authors

In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , Nov 2019

Bib HTML

@inproceedings{zhou2019adaptive,
  title = {Adaptive leader-follower formation control and obstacle avoidance via deep reinforcement learning},
  author = {Zhou, Yanlin and Lu, Fan and Pu, George and Ma, Xiyao and Sun, Runhan and Chen, Hsi-Yuan and Li, Xiaolin},
  booktitle = {2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  pages = {4273--4280},
  year = {2019},
  month = nov,
  organization = {IEEE},
}