היכן פיקוח מנבא מעצב את מדיניות VLA

תקציר מקורי באנגליתarXiv:2609.36645v2 Announce Type: replace-cross Abstract: Future prediction is increasingly used to improve vision-language-action (VLA) policies, based on the premise that anticipating scene evolution encourages representations useful for control. However, forecast quality alone does not establish that a policy has learned a better representation for action. This distinction matters under distribution shift, where successful control depends on preserving spatial state and likely scene change beyond familiar configurations. We study what determines whether predictive supervision improves the visual representation used by a VLA policy. Through controlled comparisons with matched target constructions, prediction horizons, and training conditions, we find that different prediction interfaces