OpenVLA
Summary
OpenVLA is an open 7B VLA model that maps image observations and language instructions to discretized robot action tokens.
Role In The Wiki
OpenVLA anchors the open action-token VLA branch and serves as a baseline against diffusion/flow action experts.
Evidence
Official Artifacts
Relation To Foundation TSFM Agenda
Use the source-level agenda mapping in openvla-2024 rather than duplicating verdict rows here.
At the entity level, OpenVLA anchors the open action-token VLA branch and serves as a baseline against diffusion/flow action experts. This page should stay as the object card; source pages carry slot-level verdicts, evidence, and missing pieces.