π0.5: a Vision-Language-Action Model with Open-World Generalization
A vision-language-action system studies generalization across environments and tasks using varied sources of supervision.
THE RESEARCH ATLAS
Physical Intelligence Papers & Recent Research
Institution base · Physical Intelligence 🇺🇸 United StatesVision-language-action · Manipulation. Papers, reports and open-source projects are identified separately.
π0: A Vision-Language-Action Flow Model for General Robot Control
A pretrained vision-language backbone is combined with flow-based action generation for diverse robot tasks.
What this index holds from Physical Intelligence
This index currently holds 2 records attributed to Physical Intelligence (2024–2025). Each entry links to the primary source; product announcements and news posts are not counted as papers.
- π0: A Vision-Language-Action Flow Model for General Robot Control 2024-10 · Research paper
- π0.5: a Vision-Language-Action Model with Open-World Generalization 2025-04 · Research paper
Related work on the same topics
These records come from other institutions but address the same topics, so the lab can be read in context.
- UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videos 2026-03 · Research paper
- Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation 2026-06-15 · Technical report
- UnifoLM-WLA-1.0: One Model Driven, Whole-Body Coordination 2026-09-28 · Official open-source project
- What work can robots do? 2026-09-30 · Official research article
- FACT: A Multimodal Force-Action-Track Foundation Model for Human-to-Robot Dexterity 2026-10 · Research paper
- PointWalker: Mapless Quadruped Locomotion Directly From Raw LiDAR Point Clouds 2026-10-11 · Research paper