OpenVLA
Stanford UniversityUniversity of California (UC) BerkeleyToyota Research InstituteGoogle DeepMindMassachusetts Institute of Technology (MIT)Physical IntelligenceRobotic manipulationOpen weights
Developed by Stanford University,University of California (UC) Berkeley,Toyota Research Institute,Google DeepMind,Massachusetts Institute of Technology (MIT),Physical Intelligence in 2024, OpenVLA is a robotic manipulation model with 7188100000.0 parameters with openly available weights.
About OpenVLA
Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can fine-tune such vis
Details
- Provider
- Stanford University,University of California (UC) Berkeley,Toyota Research Institute,Google DeepMind,Massachusetts Institute of Technology (MIT),Physical Intelligence
- Task
- Robotic manipulation
- Parameters
- 7188100000.0
- Released
- 2024-06-13
- Open weights
- Yes