Sotabase

Career

· Assistant Professor, Tsinghua University2022–
· Postdoctoral Researcher, Stanford University2021–
· PhD Student, University of California, Berkeley2016–

Publications (56)

End-to-End Learning of Driving Models from Large-Scale Video Datasets
Computer Vision and Pattern Recognition · 2016
858
cited
Natural Language Object Retrieval
Computer Vision and Pattern Recognition · 2015
570
cited
Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees
International Conference on Learning Representations · 2018
242
cited
Multi-Task Reinforcement Learning with Soft Modularization
Neural Information Processing Systems · 2020
221
cited
Reinforcement Learning from Imperfect Demonstrations
International Conference on Learning Representations · 2018
210
cited
Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes
Computer Vision and Pattern Recognition · 2020
168
cited
RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools
Conference on Robot Learning · 2023
96
cited
Multi-Person 3D Motion Prediction with Multi-Range Transformers
Neural Information Processing Systems · 2021
93
cited
Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning
Neural Information Processing Systems · 2022
93
cited
See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation
Conference on Robot Learning · 2022
92
cited
Disentangling Propagation and Generation for Video Prediction
IEEE International Conference on Computer Vision · 2018
90
cited
NovelD: A Simple yet Effective Exploration Criterion
Neural Information Processing Systems · 2021
89
cited
On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
International Conference on Machine Learning · 2022
75
cited
RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks
Robotics: Science and Systems · 2022
73
cited
Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification
International Conference on Machine Learning · 2021
71
cited
TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
Neural Information Processing Systems · 2023
63
cited
Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization
International Conference on Learning Representations · 2021
61
cited
Modular Architecture for StarCraft II with Deep Reinforcement Learning
Artificial Intelligence and Interactive Digital Entertainment Conference · 2018
58
cited
Multi-Agent Collaboration via Reward Attribution Decomposition
arXiv.org · 2020
46
cited
BeBold: Exploration Beyond the Boundary of Explored Regions
arXiv.org · 2020
43
cited
Sotabase
Huazhe Xu | Researcher Profile | Sotabase | Sotabase