This repository contains the reproducible Case 2 implementation for a bimanual ALOHA transfer-cube task. It includes the MuJoCo object and scene, the canonical Case 2 environment adapter, the R1/R2/R3 ...
Stage VLA V7 is an auditable, modular vision-language-action stack. The VLA core is independent of Isaac Lab; Isaac Lab is one optional Simulation backend. The refactor preserves the existing V7 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results