World's Best Scientists 2026 revealed!
Award Badge
Rising Stars
2025

D-Index & Metrics

Rising Stars

D-Index
34
Citations
15266
World Ranking
862
National Ranking
140

Computer Science

D-Index
34
Citations
14129
World Ranking
11875
National Ranking
4841

Research.com Recognitions

  • 2025 - Research.com Rising Stars Award

Overview

Shixiang Gu is a researcher affiliated with Google in the United States. Their work primarily spans the fields of Computer Science and Engineering, with a particular focus on Artificial Intelligence, Computer Vision and Pattern Recognition, Control and Systems Engineering, and Cognitive Neuroscience.

The main topics addressed in their research include Reinforcement Learning in Robotics, Robot Manipulation and Learning, Topic Modeling, Domain Adaptation and Few-Shot Learning, Multimodal Machine Learning Applications, and Modular Robots and Swarm Intelligence. These topics reflect a strong emphasis on the intersection of machine learning techniques and robotic systems.

Shixiang Gu has published extensively, contributing to 34 papers at arXiv (Cornell University), alongside works in Transactions of the Japanese Society for Artificial Intelligence, Advanced Robotics, IEEE Robotics and Automation Letters, and Journal of the Robotics Society of Japan.

Recent representative papers include:

  • Scaling Instruction-Finetuned Language Models, 2022, arXiv (Cornell University)
  • Large Language Models are Zero-Shot Reasoners, 2022, arXiv (Cornell University)
  • A Minimalist Approach to Offline Reinforcement Learning, 2021, arXiv (Cornell University)
  • Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization, 2020, arXiv (Cornell University)
  • Aligning Text-to-Image Models using Human Feedback, 2023, arXiv (Cornell University)

Their frequent co-authors include Yutaka Matsuo, Tatsuya Matsushima, Hiroki Furuta, and Yusuke Iwasawa, reflecting collaborative efforts in advancing research in AI and robotics.

Best Publications

  • Categorical Reparameterization with Gumbel-Softmax

    Eric Jang;Shixiang Gu;Ben Poole

  • Scaling Instruction-Finetuned Language Models

    Unknown

  • Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates

    Shixiang Gu;Ethan Holly;Timothy Lillicrap;Sergey Levine

  • Continuous deep Q-learning with model-based acceleration

    Shixiang Gu;Timothy Lillicrap;Ilya Sutskever;Sergey Levine

  • Towards Deep Neural Network Architectures Robust to Adversarial Examples

    Shixiang Gu;Luca Rigazio

  • Data-Efficient Hierarchical Reinforcement Learning

    Ofir Nachum;Shixiang Gu;Honglak Lee;Sergey Levine

  • Large Language Models Can Self-Improve

    Unknown

  • Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog.

    Natasha Jaques;Asma Ghandeharioun;Judy Hanwen Shen;Craig Ferguson

  • Q-PrOP: Sample-efficient policy gradient with an off-policy critic

    Shixiang Gu;Timothy Lillicrap;Zoubin Ghahramani;Richard Eric Turner

  • Temporal Difference Models: Model-Free Deep RL for Model-Based Control

    Vitchyr Pong;Shixiang Gu;Murtaza Dalal;Sergey Levine

  • MuProp: Unbiased Backpropagation for Stochastic Neural Networks

    Shixiang Gu;Shixiang Gu;Sergey Levine;Ilya Sutskever;Andriy Mnih

  • Dynamics-Aware Unsupervised Discovery of Skills

    Archit Sharma;Shixiang Gu;Sergey Levine;Vikash Kumar

  • Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning

    Shixiang Gu;Timothy P. Lillicrap;Zoubin Ghahramani;Richard E. Turner

  • Sequence tutor: conservative fine-tuning of sequence generation models with KL-control

    Natasha Jaques;Shixiang Gu;Dzmitry Bahdanau;José Miguel Hernández-Lobato

  • A Divergence Minimization Perspective on Imitation Learning Methods

    Seyed Kamyar Seyed Ghasemipour;Richard S. Zemel;Shixiang Gu

  • Tuning Recurrent Neural Networks with Reinforcement Learning

    Natasha Jaques;Shixiang Gu;Richard E. Turner;Douglas Eck

  • Neural adaptive sequential Monte Carlo

    Shixiang Gu;Zoubin Ghahramani;Richard E. Turner

  • Near-Optimal Representation Learning for Hierarchical Reinforcement Learning

    Ofir Nachum;Shixiang Gu;Honglak Lee;Sergey Levine

  • Aligning Text-to-Image Models using Human Feedback

    Unknown

  • Language as an Abstraction for Hierarchical Deep Reinforcement Learning

    YiDing Jiang;Shixiang Gu;Kevin P. Murphy;Chelsea Finn

  • Categorical Reparametrization with Gumble-Softmax

    Eric Jang;Shixiang Gu;Ben Poole

  • The Mirage of Action-Dependent Baselines in Reinforcement Learning.

    George Tucker;Surya Bhupatiraju;Shixiang Gu;Richard E. Turner

  • Way Off-Policy Batch Deep Reinforcement Learning of Human Preferences in Dialog

    Natasha Jaques;Asma Ghandeharioun;Judy Hanwen Shen;Craig Ferguson

Frequent Co-Authors

Sergey Levine
Sergey Levine University of California, Berkeley
Richard E. Turner
Richard E. Turner University of Cambridge
Timothy P. Lillicrap
Timothy P. Lillicrap University College London
Zoubin Ghahramani
Zoubin Ghahramani University of Cambridge
Vikash Kumar
Vikash Kumar University of Washington
Honglak Lee
Honglak Lee University of Michigan–Ann Arbor
George Tucker
George Tucker Google (United States)
Yutaka Matsuo
Yutaka Matsuo University of Tokyo
Douglas Eck
Douglas Eck Google (United States)

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Studying Computer Science in the USA opens doors to a wide array of online degree options and exciting career opportunities. Many students today are looking for flexible and cost-effective pathways to advance their education while balancing other commitments.

For those aiming for leadership or research roles, there are affordable online doctoral programs available, offering advanced knowledge without breaking the bank. If you’re focused on educational leadership, consider the cheapest online doctorate in educational leadership to fast-track your qualifications and career prospects in academia or administration.

If you prefer to enter the tech workforce quickly, an accelerated online associates degree can be completed in as little as six months, helping you build foundational skills fast.

Additionally, expanding your expertise with business knowledge can be beneficial. Students interested in the business side of technology should explore a business administration degree online cost to find the best value programs. These diverse options can help you carve out a successful career in computer science or related fields.

Best Scientists Citing Shixiang Gu

Trending Scientists