Anticipating diverse future states is a central challenge in video world modeling. Discriminative world models produce a deterministic prediction that implicitly averages over possible futures, while existing generative world models remain computationally expensive. Recent work demonstrates that predicting the future in the feature space of a vision foundation model (VFM), rather than a latent space optimized for pixel reconstruction, requires significantly fewer world model parameters. However, most such approaches remain discriminative. In this work, we introduce DeltaTok, a tokenizer that encodes the VFM feature difference between consecutive frames into a single continuous "delta" token, and DeltaWorld, a generative world model operating on these tokens to efficiently generate diverse plausible futures. Delta tokens reduce video from a three-dimensional spatio-temporal representation to a one-dimensional temporal sequence, for example yielding a 1,024x token reduction with 512x512 frames. This compact representation enables tractable multi-hypothesis training, where many futures are generated in parallel and only the best is supervised. At inference, this leads to diverse predictions in a single forward pass. Experiments on dense forecasting tasks demonstrate that DeltaWorld forecasts futures that more closely align with real-world outcomes, while having over 35x fewer parameters and using 2,000x fewer FLOPs than existing generative world models. Code and weights: https://deltatok.github.io.

翻译：预测多种未来状态是视频世界建模的核心挑战。判别式世界模型通过隐式平均可能的未来状态产生确定性预测，而现有生成式世界模型计算成本高昂。近期研究表明，在视觉基础模型（VFM）的特征空间中预测未来——而非针对像素重建优化的隐空间——所需的模型参数显著更少。然而，这类方法大多仍属于判别式模型。本文提出DeltaTok分词器，将连续帧之间的VFM特征差异编码为单个连续"增量"标记；同时提出DeltaWorld生成式世界模型，基于此类标记高效生成多样化的合理未来状态。增量标记将视频从三维时空表示压缩为一维时序序列，例如对512×512像素帧可实现1024倍标记压缩。这种紧凑表示支持可行的多假设训练策略——并行生成多个未来状态，仅对最优结果进行监督训练。推理时，该模型通过单次前向传播即可生成多样化预测。在密集预测任务上的实验表明，DeltaWorld预测的未来状态更贴近真实世界结果，同时参数量比现有生成式世界模型减少超过35倍，计算量降低2000倍。代码与权重：https://deltatok.github.io。