ActionSplice: עריכת פעולות בעת סריקת עולם תלת־ממד

תקציר מקורי באנגליתarXiv:2609.08230v1 Announce Type: cross Abstract: Chunk-autoregressive video world models typically condition each generated chunk on one action. An action received during sampling must therefore wait for the next chunk, condition future solver evaluations on a state produced under the previous action, or trigger rollback that repeats completed evaluations. We introduce ActionSplice, an inference framework that formulates this problem as Counterfactual State Transport (CST). A lightweight corrector transports the interrupted backbone-native representation toward the matched state induced by the revised action at the same solver step. The world model and sampler remain frozen, and sampling resumes without replaying completed evaluations. The retargeting variant $\mathrm{CST}*{R}$ updates th