Alaya-EVOKE: From Linear-Scaling Supervision to Endless World

Interactive video world model that externalizes persistent world state into a camera-indexed bank and uses a linear-scaling teacher (sparse chunk attention + linear-attention global state). On a single H200 at 384x640 each 1.5s chunk is generated in 2.11s, and the model achieves state-of-the-art on WBench while remaining competitive on VBench-Long and VBench-2.0.