Sotabase

Career

· Research Intern, Physical Intelligence2025–2025
· Research Intern, Google DeepMind2024–2024
· AI PhD Student, Stanford University2021–
· Intern, Citadel Global Quantitative Strategies2019–2019
· Intern, AI Products Group, Intel Corporation2018–2018
· Research Assistant, ROMPS Group, UC Berkeley2018–2018
· Android Developer, Mobile Developers of Berkeley2017–2019
· B.S. in Electrical Engineering and Computer Science, University of California, Berkeley2017–2021
· Research Assistant, Stanford University2016–2016
· Captain, FRC Team 114, Eagle Strike - FIRST Robotics Competition2015–2017

Publications (43)

Octo: An Open-Source Generalist Robot Policy
Robotics: Science and Systems · 2024
928
cited
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Robotics: Science and Systems · 2024
512
cited
Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration
IEEE International Conference on Robotics and Automation · 2024
282
cited
From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function
2024
230
cited
Few-Shot Preference Learning for Human-in-the-Loop RL
Conference on Robot Learning · 2022
126
cited
Extreme Q-Learning: MaxEnt RL without Entropy
International Conference on Learning Representations · 2023
108
cited
Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
Neural Information Processing Systems · 2024
102
cited
Inverse Preference Learning: Preference-based RL without a Reward Function
Neural Information Processing Systems · 2023
75
cited
Contrastive Preference Learning: Learning from Human Feedback without RL
arXiv.org · 2023
74
cited
PERSONA: A Reproducible Testbed for Pluralistic Alignment
International Conference on Computational Linguistics · 2024
50
cited
Vision Language Models are In-Context Value Learners
International Conference on Learning Representations · 2024
46
cited
Aligning Language Models with Demonstrated Feedback
International Conference on Learning Representations · 2024
42
cited
Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning
Conference on Robot Learning · 2024
41
cited
Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning
International Conference on Learning Representations · 2024
33
cited
Distance Weighted Supervised Learning for Offline Interaction Data
International Conference on Machine Learning · 2023
18
cited
Robot Data Curation with Mutual Information Estimators
Robotics · 2025
17
cited
Improving Long-Horizon Imitation Through Instruction Prediction
AAAI Conference on Artificial Intelligence · 2023
12
cited
So You Think You Can Scale Up Autonomous Robot Data Collection?
Conference on Robot Learning · 2024
12
cited
Show, Don't Tell: Aligning Language Models with Demonstrated Feedback
arXiv.org · 2024
11
cited
Scaffolding Dexterous Manipulation with Vision-Language Models
arXiv.org · 2025
6
cited
Sotabase