Sotabase

Career

· Research Intern, Microsoft Research2025–2025
· Research Intern, Toyota Research Institute (TRI)2024–2024
· Research Intern, Google DeepMind Robotics2023–2024
· PhD in Computer Science, Stanford University2023–
· AI Resident, X, the moonshot factory2022–2023
· B.A. in Computer Science (Highest Distinction), University of California, Berkeley2019–2023

Publications (40)

RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
Conference on Robot Learning · 2023
2,268
cited
Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration0
IEEE International Conference on Robotics and Automation · 2023
785
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
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
Neural Information Processing Systems · 2023
195
cited
Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
International Conference on Machine Learning · 2024
176
cited
When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?
arXiv.org · 2022
98
cited
A Workflow for Offline Model-Free Robotic Reinforcement Learning
Conference on Robot Learning · 2021
91
cited
Pre-Training for Robots: Offline RL Enables Learning New Tasks in a Handful of Trials
Robotics: Science and Systems · 2022
86
cited
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought
arXiv.org · 2025
85
cited
Should I Run Offline Reinforcement Learning or Behavioral Cloning?
International Conference on Learning Representations · 2022
80
cited
Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models
arXiv.org · 2025
56
cited
Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation
arXiv.org · 2024
50
cited
From Agile Ground to Aerial Navigation: Learning from Learned Hallucination
IEEE/RJS International Conference on Intelligent RObots and Systems · 2021
44
cited
Robotic Offline RL from Internet Videos via Value-Function Pre-Training
arXiv.org · 2023
29
cited
Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials
arXiv.org · 2022
19
cited
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
16
cited
FSPO: Few-Shot Preference Optimization of Synthetic Preference Data in LLMs Elicits Effective Personalization to Real Users
arXiv.org · 2025
16
cited
Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints
arXiv.org · 2022
15
cited
Personalized Preference Fine-tuning of Diffusion Models
Computer Vision and Pattern Recognition · 2025
15
cited
D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning
RLJ · 2024
11
cited
Sotabase
Anikait Singh | Researcher Profile | Sotabase | Sotabase