Sotabase

Career

· Research Scientist, Google DeepMind2024–
· Research Intern, Toyota Research Institute2023–2023
· PhD in Computer Science, Stanford University2021–
· PhD Student, Stanford University2021–
· AI Resident, Google Brain2018–2020
· Research Assistant, IIT Kanpur2017–2018
· Research Intern, Mila - Quebec Artificial Intelligence Institute2017–2017
· B.Tech in Electrical Engineering, IIT Kanpur2014–2018
· Research Scientist, Googe DeepMind

Publications (58)

Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Neural Information Processing Systems · 2023
7,064
cited
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
arXiv.org · 2025
1,636
cited
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
Conference on Empirical Methods in Natural Language Processing · 2023
547
cited
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Robotics: Science and Systems · 2024
512
cited
Dynamics-Aware Unsupervised Discovery of Skills
International Conference on Learning Representations · 2019
460
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
Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
International Conference on Machine Learning · 2024
176
cited
Yell At Your Robot: Improving On-the-Fly from Language Corrections
Robotics: Science and Systems · 2024
119
cited
Stream of Search (SoS): Learning to Search in Language
arXiv.org · 2024
117
cited
SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
IEEE International Conference on Robotics and Automation · 2024
100
cited
Waypoint-Based Imitation Learning for Robotic Manipulation
Conference on Robot Learning · 2023
82
cited
An Emulator for Fine-Tuning Large Language Models using Small Language Models
International Conference on Learning Representations · 2023
66
cited
Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning
Robotics: Science and Systems · 2020
54
cited
Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning
IEEE International Conference on Robotics and Automation · 2023
45
cited
Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone
arXiv.org · 2024
43
cited
A Critical Evaluation of AI Feedback for Aligning Large Language Models
Neural Information Processing Systems · 2024
39
cited
Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning
International Conference on Machine Learning · 2021
39
cited
Autonomous Reinforcement Learning: Formalism and Benchmarking
International Conference on Learning Representations · 2021
35
cited
Autonomous Reinforcement Learning via Subgoal Curricula
Neural Information Processing Systems · 2021
32
cited
You Only Live Once: Single-Life Reinforcement Learning
Neural Information Processing Systems · 2022
29
cited
Sotabase
Archit Sharma | Researcher Profile | Sotabase | Sotabase