CtrlCache: Accelerating Interactive Video World Models with Control-Aware Caching

Interactive video world models need to generate each video chunk efficiently while responding faithfully to user controls. Many systems use chunk-wise autoregressive generation with few-step denoising, but each chunk still requires several costly denoising iterations. Training-free caching can reduce this cost, yet existing policies make reuse decisions primarily from model-internal denoising dynamics and do not explicitly account for control transitions. Interactive generation exposes a signal they do not use: the controls for a chunk arrive before it is denoised, so a schedule derived from them costs no forward pass.

We analyze adjacent chunks under different control regimes and find that structural similarity drops around action changes, while low-frequency structure remains more persistent than high-frequency detail. Motivated by these observations, we propose CtrlCache, a training-free control-aware caching framework. Its action-aware scheduling and refresh policy labels each chunk as initial, transition, turning, or steady; at one selected interior denoising step, initial and transition chunks retain full computation, while turning and steady chunks reuse the transformer residual. A frequency-mixed history prior guidance further transfers complementary information from the preceding clean latent without an additional DiT forward pass. On Matrix-Game 2.0 and LingBot-World v1/v2, CtrlCache achieves 1.21×–1.41× DiT-backbone speedups while improving WBench Overall on all three models.