视频AI的“失忆症”有解了：一个让AI记住几分钟前画面的新方法
现在的AI生成视频，几秒钟还行，一拉长就“失忆”:物体消失再出现，长相就变了，前后对不上。这篇论文给了一个叫 Ring Forcing 的训练框架，核心是逼着模型在生成每一帧时，必须回头去“翻”很久以前的画面，而不是只看眼前几帧。配合历史压缩和稀疏位置编码，它能把有效记忆拉长到几分钟，物体再次出现时还能保持原样。这不是你明天就能用的工具，但它指向了视频AI从“短视频片段”走向“长叙事”的关键一步——如果AI连几分钟内的物体都记不住，更别提让它讲一个完整的故事了。
📄 原文摘要(英文)
Scaling video generation to long durations reveals a critical bottleneck: current models lack robust long-term memory. This deficiency can be studied along two critical aspects: object permanence, the ability to precisely reproduce the appearance of objects upon re-entry; and memory capacity, the ability to process ultra-long context and use information from distant history. Robust long-term memory requires both: object permanence without sufficient context handling limits the temporal scope, while long context length without permanence fails to maintain identity. To address this, we present Ring Forcing, an autoregressive video diffusion framework designed to robustly construct and precisely utilize long-term memory. Our ring-structured training strategy enforces retrieval from distant history, effectively reconciling the trade-off between strict historical adherence and generative diversity. To expand memory capacity, we introduce a compression and timestep composition strategy. Under fixed sequence length constraints, this method extends the effective historical span to minutes-long durations and achieves a comprehensive receptive field over the entire history. Furthermore, we present a sparse RoPE mechanism to enable flexible, scalable memory adaptation while fully exploiting pre-trained priors. Extensive experiments demonstrate that Ring Forcing achieves superior minutes-long coherence and object permanence, significantly outperforming state-of-the-art methods.