AI视频生成终于有了长期记忆
现在的AI视频生成模型像金鱼——几秒后就开始忘记场景长什么样，物体消失、背景乱变。这篇论文让模型学会自己翻看之前的画面，用「查询令牌」主动找关键帧，而不是死板地每隔几帧取一张。在遮挡和物体移动的复杂场景下，生成的视频能保持场景一致，比如一个球滚到箱子后面再出来，还是同一个球。它不是你明天就能用的工具，但解决了视频世界模型走向实用的核心瓶颈。
📄 原文摘要(英文)
Video World Models are interactive video generation models that predict future world states based on user actions and history video frames. A critical challenge in video world models is the lack of memory, causing inconsistent generated scenes over extended durations. Previous methods explored rule-based context frame retrieval as memory, but they fail to generalize in scenarios with scene occlusions and dynamic objects. We propose MemLearner, a learning-based adaptive context query method using query tokens to bridge context and predicted tokens. By leveraging the video generation model itself for context querying, MemLearner exploits pre-trained visual priors without training additional modules from scratch, and incorporates efficient strategies for training and inference. We collect a dataset of long videos with scene occlusions and dynamic objects, paired with camera pose annotations, and propose a multi-dataset training strategy leveraging both annotated rendered and unannotated real-world videos. Extensive experiments demonstrate that MemLearner significantly outperforms prior video world models in terms of scene consistency and memory, particularly under challenging occlusion and dynamic scenarios.