Sotabase

Career

· Research Intern, Google2022–2022
· PhD in Computer Science, University of California, Berkeley2018–2023
· Research Assistant, University of California, Berkeley2018–2023
· Google AI Resident, Google2017–2018
· Intern, Google2015–2015
· Research Assistant, University of California, Berkeley2015–2017
· Intern, IBM2014–2014
· Bachelor of Arts in Computer Science and Statistics, University of California, Berkeley2013–2017
· Research Scientist, Google DeepMind

Publications (39)

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
arXiv.org · 2025
1,636
cited
Real-time user-guided image colorization with learned deep priors
ACM Transactions on Graphics · 2017
618
cited
Automatic Goal Generation for Reinforcement Learning Agents
International Conference on Machine Learning · 2017
555
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
The False Promise of Imitating Proprietary LLMs
arXiv.org · 2023
256
cited
Sequential Modeling Enables Scalable Learning for Large Vision Models
Computer Vision and Pattern Recognition · 2023
233
cited
Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
International Conference on Learning Representations · 2024
167
cited
Multimodal Masked Autoencoders Learn Transferable Representations
arXiv.org · 2022
135
cited
Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization
International Conference on Machine Learning · 2022
116
cited
Conservative Objective Models for Effective Offline Model-Based Optimization
International Conference on Machine Learning · 2021
112
cited
Deep reinforcement learning for tensegrity robot locomotion
IEEE International Conference on Robotics and Automation · 2016
102
cited
RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
Neural Information Processing Systems · 2024
99
cited
Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery
International Conference on Learning Representations · 2019
93
cited
Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement
Neural Information Processing Systems · 2020
93
cited
Multistage Cable Routing Through Hierarchical Imitation Learning
IEEE Transactions on robotics · 2023
89
cited
Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes
International Conference on Learning Representations · 2022
69
cited
Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling
arXiv.org · 2020
40
cited
Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning
Conference on Robot Learning · 2023
36
cited
The False Promise of Imitating Proprietary Language Models
International Conference on Learning Representations · 2024
25
cited
Dynamical Distance Learning for Unsupervised and Semi-Supervised Skill Discovery
arXiv.org · 2019
14
cited
Sotabase
Xinyang Geng | Researcher Profile | Sotabase | Sotabase