AI RESEARCH
Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generation
arXiv CS.CV
•
ArXi:2605.20476v1 Announce Type: new Long-horizon video generation suffers from two intertwined issues. First, there is drift, where video quality degrades over time. Second, there are continuity issues which manifest as object permanence issues, or improperly rendering transient content (e.g., an object that appears in non-consecutive frames changing color/style). Recent work has focused on autoregressive distillation techniques that attack both problems simultaneously. We instead choose to focus on drift directly and.