ValueFormer: Stage-Aware Value Labels for Online Failure Detection and VLA Post-Training
arXiv:2608.02958v2 Announce Type: replace-cross Abstract: Generalist vision-language-action (VLA) policies now transfer to new scenes with little task-specific training, but they still fail silently: from the action stream alone, a collapsing rollout looks much like one making clean progress, because imitation supplies no notion of progress. The cheap alternative, a terminal success / failure bit, is learnable in principle yet too sparse to say when a rollout went wrong. We argue that the per-f…