Visual world models drift over long rollouts: JointGV adds a parallel graph rollout and cuts joint-position error by 11–28%
Recursive visual world models drift in entity pose and spatial relations, which limits long-horizon robot planning. JointGV rolls out a task-conditioned scene graph alongside the existing visual model, couples their action-induced changes, and applies a bounded residual correction whose gradients never enter the original model. On DMC Cheetah Run, Walker Walk and Finger Turn Hard, 32-step joint-position error falls by 11–28%.