Sotabase

Career

· Graduate Student Instructor, CS188: Artificial Intelligence, UC Berkeley2017–
· Intern, Google Research2016–
· PhD Student, UC Berkeley2016–
· PhD Student, Computer Science, UC Berkeley2016–2021
· Teaching Assistant, CS 4780/5780: Machine Learning, Cornell University2015–
· Intern, Facebook2014–
· Intern, Moody's Analytics2013–
· Cofounder and CTO, saund2013–2014
· B.S. Computer Science, Electrical & Computer Engineering, Cornell University2012–2016
· Research Scientist, OpenAI

Publications (38)

GPT-4 Technical Report
2023
21,596
cited
Visual Reinforcement Learning with Imagined Goals
Neural Information Processing Systems · 2018
580
cited
Uncertainty-Aware Reinforcement Learning for Collision Avoidance
arXiv.org · 2017
328
cited
Skew-Fit: State-Covering Self-Supervised Reinforcement Learning
International Conference on Machine Learning · 2019
298
cited
Temporal Difference Models: Model-Free Deep RL for Model-Based Control
International Conference on Learning Representations · 2018
255
cited
Composable Deep Reinforcement Learning for Robotic Manipulation
IEEE International Conference on Robotics and Automation · 2018
244
cited
Planning with Goal-Conditioned Policies
Neural Information Processing Systems · 2019
236
cited
Offline Meta-Reinforcement Learning with Online Self-Supervision
International Conference on Machine Learning · 2021
77
cited
Contextual Imagined Goals for Self-Supervised Robotic Learning
Conference on Robot Learning · 2019
74
cited
Reactive high-level behavior synthesis for an Atlas humanoid robot
IEEE International Conference on Robotics and Automation · 2016
48
cited
OpenAI GPT-5 System Card
2025
46
cited
REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning
arXiv.org · 2019
40
cited
MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning
International Conference on Machine Learning · 2021
35
cited
Outcome-Driven Reinforcement Learning via Variational Inference
Neural Information Processing Systems · 2021
22
cited
DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies
IEEE International Conference on Robotics and Automation · 2021
15
cited
Losing Visual Needles in Image Haystacks: Vision Language Models are Easily Distracted in Short and Long Contexts
Conference on Empirical Methods in Natural Language Processing · 2024
9
cited
FinMind-Y-Me at the Regulations Challenge Task: Financial Mind Your Meaning based on THaLLE
COLING Workshops · 2025
4
cited
Towards Artwork Explanation in Large-scale Vision Language Models
Annual Meeting of the Association for Computational Linguistics · 2024
3
cited
Dunamu ML at the Financial Misinformation Detection Challenge Task: Improving Supervised Fine-Tuning with LLM-based Data Augmentation
COLING Workshops · 2025
2
cited
From KMMLU-Redux to Pro: A Professional Korean Benchmark Suite for LLM Evaluation
Conference on Empirical Methods in Natural Language Processing · 2025
2
cited
Sotabase
Vitchyr H. Pong | Researcher Profile | Sotabase | Sotabase