VLA models
RT-2 (Robotic Transformer 2)
United States
The founding VLA: first to show that web-scale vision-language knowledge transfers directly to robot control by treating actions as text tokens. It spawned the RT-X / Open X-Embodiment cross-lab effort that underpins most later open VLAs. Research artifact, never released as weights or product.
OrganizationGoogle DeepMind
CountryUS
Release2023-07
Params (B)55
Open weightsno
ArchitectureVLA co-fine-tuned from web-scale VLMs (PaLI-X 55B and PaLM-E 12B variants); robot actions emitted as text tokens
Modalitiesvision, language, action
Embodimentsmanipulator, mobile
Training dataInternet-scale vision-language data co-fine-tuned with RT-1 robot demonstrations (collected with 13 robots over 17 months)
Sources : Google DeepMind (2023-07-28)arXiv (2023-07-28)InfoQ (2023-10-01)
← Back to comparator · VLA models