可寻址记忆用于视频世界模型

摘要

我们研究交互式视频世界模型中的视觉持久性问题。这类模型依赖键-值（KV）缓存作为不断增长的视觉记忆，以携带先前生成的帧。然而，我们发现一旦展开（rollout）超出训练时域，模型便无法可靠地寻址已存储的内容，因为此时时间旋转位置编码（RoPE）的偏移量超出了训练期间所见范围，模型难以通过注意力机制检索相关视觉信息。此外，在RoPE旋转空间中朴素地压缩缓存，会因对不兼容的位置相位取平均而破坏记忆。为解决这一问题，我们提出WorldTrace——一种无需训练的面向长时域视觉持久性的记忆框架。WorldTrace通过为每个摘要槽分配一个不同的、处于分布内的虚拟位置，使压缩记忆保持可寻址性。在此可寻址缓存中，我们研究了两种记忆压缩方法：WorldTrace-Field压缩历史以实现时间一致性，而WorldTrace-Landmark在检测到的场景转换处存储逐帧的原始场景痕迹，以实现情景回召。我们进一步引入LoopBench，这是一个评估压缩缓存能否在长段迂回后重建先前访问场景的基准。在LoopBench上，WorldTrace-Field将时间一致性提升+15.5%，WorldTrace-Landmark将情景回召提升+19.5%，无需重训练即可扩展视觉持久生成的能力。

English

We study visual persistence in interactive video world models. These models rely on a Key-Value (KV) cache as a growing visual memory to carry forward previously generated frames. However, we find that models can no longer reliably address stored content once rollouts extend beyond the training horizon, because temporal Rotary Positional Embeddings (RoPE) offsets then fall outside the range seen during training and the model struggles to retrieve the relevant visual information through attention. Moreover, naively compressing the cache in the RoPE-rotated space corrupts memory by averaging together incompatible positional phases. To address this, we propose WorldTrace, a training-free memory framework for long-horizon visual persistence. WorldTrace keeps compressed memory addressable by assigning each summary slot a distinct, in-distribution virtual position. Within this addressable cache, we study two memory compression approaches: WorldTrace-Field compresses history for temporal coherence, while WorldTrace-Landmark stores verbatim scene traces at detected transitions for episodic recall. We further introduce LoopBench, a benchmark evaluating whether a compressed cache can reconstruct a previously visited scene after a long detour. WorldTrace-Field improves temporal consistency by +15.5%, and WorldTrace-Landmark improves episodic recall by +19.5% on LoopBench, extending visually persistent generation without retraining.