Shixiang Gu
The University of Tokyo(JP)
Publications by Year
Research Areas
Reinforcement Learning in Robotics, Adversarial Robustness in Machine Learning, Robot Manipulation and Learning, Topic Modeling, Multimodal Machine Learning Applications
Most-Cited Works
- → Categorical Reparameterization with Gumbel-Softmax(2016)3,222 cited
- → Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates(2017)1,439 cited
- → Scaling Instruction-Finetuned Language Models(2022)1,181 cited
- → Large Language Models are Zero-Shot Reasoners(2022)1,100 cited
- → Towards Deep Neural Network Architectures Robust to Adversarial Examples(2014)632 cited
- → Continuous Deep Q-Learning with Model-based Acceleration(2016)336 cited
- → Data-Efficient Hierarchical Reinforcement Learning(2018)265 cited
- → Large Language Models Can Self-Improve(2023)175 cited
- → A Minimalist Approach to Offline Reinforcement Learning(2021)164 cited