עתיד נבחר: עדיין ניתן לכתוב אותו מחדש: כתיבתיות סיבתית בדגמי וידאו

תקציר מקורי באנגליתarXiv:2609.15980v1 Announce Type: new Abstract: When a video model generates physically incorrect motion, did it fail to learn the correct motion, or did it learn it but fail to use it? We show the latter: the correct motion remains available inside the model and can still be made to control the generated video. We train on videos where red masses oscillate slowly and blue masses oscillate quickly, then test a red mass with fast observed motion. Even when the model generates slow motion in this conflicting case, a low-dimensional edit predicted from simple physical variables restores the correct fast motion. We call this ability causal writability. At fixed strength, we find a sharp depth boundary: the same edit changes the video before the boundary but not after it. This closure marks com