מדיניות סקלה: חישוב זרימה למודלי פעולה-עולם עם קובצי פעולה גדולים

תקציר מקורי באנגליתarXiv:2609.36471v1 Announce Type: cross Abstract: World-Action Models (WAMs) improve robotic manipulation by conditioning action generation on predicted future observations, but future prediction adds further inference overhead to already expensive iterative action generation. Action chunking can amortize this cost over multiple actions, yet performance degrades over long execution horizons because later actions remain conditioned on stale observations. We introduce STAIRCASE POLICY, a streaming inference and training framework that turns a flow-matching VLA into a JEPA-style WAM and partitions a large action chunk into sub-chunks at staggered denoising stages. Near-term actions are executed as soon as they become available, while later actions continue to be refined. At each sub-chunk bou