AI RESEARCH
X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference
arXiv CS.CV
•
ArXi:2604.20289v1 Announce Type: new Real-time world simulation is becoming a key infrastructure for scalable evaluation and online reinforcement learning of autonomous driving systems. Recent driving world models built on autoregressive video diffusion achieve high-fidelity, controllable multi-camera generation, but their inference cost remains a bottleneck for interactive deployment. However, existing diffusion caching methods are designed for offline video generation with multiple denoising steps, and do not transfer to this scenario.