Ury Zhilinsky
Papers
3
Total Citations
137
H-Index
2
About
Ury Zhilinsky is at the forefront of robot learning, pioneering the development of vision-language-action (VLA) models that bridge the gap between AI and real-world robotic control. His most influential work, the π₀ (pi-zero) family of models, introduces a novel vision-language-action flow architecture designed for general robot control, achieving 127 citations in 2025 alone. This research addresses one of the field’s deepest challenges: enabling robots to perform flexible, dexterous tasks outside the lab with open-world generalization. Zhilinsky’s π₀.5 model further extends this capability, demonstrating that VLA systems can handle practically relevant, real-world scenarios beyond controlled environments. His contributions are reshaping how robots interpret visual and linguistic commands to execute complex actions, with implications for manufacturing, healthcare, and domestic assistance. By tackling the core question of how far end-to-end robot learning can generalize, Zhilinsky is not only advancing robotic autonomy but also pushing the boundaries of artificial intelligence itself. His work stands as a cornerstone for a new generation of general-purpose robots.
Research Focus
Key Achievements
Top Papers
- 1π₀: A Vision-Language-Action Flow Model for General Robot Control127 citations · 2025
- 2$π_0$: A Vision-Language-Action Flow Model for General Robot Control8 citations · 2024
- 3$π_{0.5}$: a Vision-Language-Action Model with Open-World Generalization2 citations · 2025