Krista Reymann
Papers
7
Total Citations
622
H-Index
4
About
Krista Reymann is a leading researcher at the intersection of robotics, computer vision, and embodied AI, whose work is fundamentally reshaping how robots perceive, learn, and interact with the physical world. She is perhaps best known for spearheading the creation of **Google Scanned Objects**, a high-quality, open-source dataset of over 1,000 photorealistic 3D household items. This resource, which has garnered over 315 citations, has become a cornerstone for training robots in simulated environments, dramatically accelerating progress in deep learning for manipulation tasks. Reymann’s impact extends to the frontier of vision-language-action models; her work on **RT-2** (267 citations) demonstrated how web-scale knowledge can be directly transferred to robotic control, enabling emergent semantic reasoning and unprecedented generalization. In a stunning display of real-world performance, she led the development of the first learned robot agent to achieve **amateur human-level performance in competitive table tennis**, a landmark achievement in high-speed, dynamic control. Most recently, her contributions to the **Gemini Robotics** family of models are pioneering the translation of large multimodal AI into physical agents, bringing us closer to a future where generalist robots operate seamlessly in our homes and workplaces.
Research Focus
Key Achievements
Top Papers
- 1Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items315 citations · 2022
- 2RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control267 citations · 2023
- 3Robotic Table Tennis: A Case Study into a High Speed Learning System17 citations · 2023
- 4Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items13 citations · 2022
- 5Gemini Robotics: Bringing AI into the Physical World4 citations · 2025
- 6Achieving Human Level Competitive Robot Table Tennis3 citations · 2025
- 7Achieving Human Level Competitive Robot Table Tennis3 citations · 2024