צינור: למידה של זיכרון קצר-מידה על-פי דיסטילציה-מדריך לצינורי וידאו ארוכים

תקציר מקורי באנגליתarXiv:2609.36364v1 Announce Type: cross Abstract: Standard video generators do not natively compact historical context into reusable memory tokens. As generation continues, the growing history makes it increasingly difficult to retain information from earlier frames due to long-context degradation. Key-frame-based approaches address this challenge by retaining selected past frames, but can discard information needed for future generation. Rather than relying on frame selection alone, we study whether a frozen video generator can supply the supervision needed to learn a compact representation of the history. We propose Prediction-Aligned Context Compaction (PACC), which uses a learned compressor to aggregate information across past frames into compact memory tokens. We train the compressor