Sotabase

Career

· Postdoc, University of Washington2025–
· Research Intern, NVIDIA2024–2025
· Applied Scientist Intern, Amazon Web Services (AWS)2023–2023
· AI Research Scientist Intern, NAVER Corp2021–2021
· General AI Lab Research Intern, Horizon Robotics2020–2020
· Graduate Student Instructor Researcher, University of Southern California2020–2023
· Undergraduate Researcher, Berkeley Artificial Intelligence Research2019–2020
· Undergraduate Course TA, UC Berkeley College of Engineering2019–2019
· Course Reader, UC Berkeley Electrical Engineering & Computer Sciences (EECS)2019–2019
· Undergraduate Research Assistant, Berkeley RISE Lab2018–2019
· Undergraduate Research Assistant, Berkeley RISE Lab2017–2019

Publications (23)

RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback
International Conference on Machine Learning · 2024
118
cited
RoboCLIP: One Demonstration is Enough to Learn Robot Policies
Neural Information Processing Systems · 2023
116
cited
COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning
arXiv.org · 2020
110
cited
Hierarchical Reinforcement Learning By Discovering Intrinsic Options
International Conference on Learning Representations · 2021
95
cited
Learning to Synthesize Programs as Interpretable and Generalizable Policies
Neural Information Processing Systems · 2021
87
cited
Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance
Conference on Robot Learning · 2023
86
cited
Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
International Conference on Machine Learning · 2020
62
cited
REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning
arXiv.org · 2019
40
cited
SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling
IEEE International Conference on Robotics and Automation · 2023
22
cited
ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations
arXiv.org · 2025
19
cited
REPLAB: A Reproducible Low-Cost Arm Benchmark for Robotic Learning
IEEE International Conference on Robotics and Automation · 2019
15
cited
EXTRACT: Efficient Policy Learning by Extracting Transferrable Robot Skills from Offline Data
Conference on Robot Learning · 2024
14
cited
LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers
arXiv.org · 2023
12
cited
Hierarchical Neural Program Synthesis
arXiv.org · 2023
9
cited
HAND Me the Data: Fast Robot Adaptation via Hand Path Retrieval
arXiv.org · 2025
5
cited
SPRINT: Scalable Semantic Policy Pre-Training via Language Instruction Relabeling
2022
3
cited
Chaining Behaviors from Data with Model-Free Reinforcement Learning
Conference on Robot Learning · 2020
2
cited
PEEK: Guiding and Minimal Image Representations for Zero-Shot Generalization of Robot Manipulation Policies
arXiv.org · 2025
2
cited
Hope For The Best But Prepare For The Worst: Cautious Adaptation In RL Agents
2019
Unsupervised Projection Networks for Generative Adversarial Networks
arXiv.org · 2019
Sotabase
Jesse Zhang | Researcher Profile | Sotabase | Sotabase