Diffusion-based world models have shown strong potential for unified world simulation, but the iterative denoising remains too costly for interactive use and long-horizon rollouts. While feature caching can accelerate inference without training, we find that policies designed for single-modal diffusion transfer poorly to world models due to two world-model-specific obstacles: \emph{token heterogeneity} from multi-modal coupling and spatial variation, and \emph{non-uniform temporal dynamics} where a small set of hard tokens drives error growth, making uniform skipping either unstable or overly conservative. We propose \textbf{WorldCache}, a caching framework tailored to diffusion world models. We introduce \textit{Curvature-guided Heterogeneous Token Prediction}, which uses a physics-grounded curvature score to estimate token predictability and applies a Hermite-guided damped predictor for chaotic tokens with abrupt direction changes. We also design \textit{Chaotic-prioritized Adaptive Skipping}, which accumulates a curvature-normalized, dimensionless drift signal and recomputes only when bottleneck tokens begin to drift. Experiments on diffusion world models show that WorldCache delivers up to \textbf{3.7×} end-to-end speedups while maintaining \textbf{98\%} rollout quality, demonstrating the vast advantages and practicality of WorldCache in resource-constrained scenarios. Our code is released in https://github.com/FofGofx/WorldCache.
@article{arxiv.2603.06331,
title = {WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching},
author = {Weilun Feng and Guoxin Fan and Haotong Qin and Chuanguang Yang and Mingqiang Wu and Yuqi Li and Xiangqi Li and Zhulin An and Libo Huang and Dingrui Wang and Longlong Liao and Michele Magno and Yongjun Xu},
journal= {arXiv preprint arXiv:2603.06331},
year = {2026}
}