Alaya-EVOKE: From Linear-Scaling Supervision to Endless World
An interactive video world model that combines a camera-indexed external world-state bank with a sparse-attention teacher that scales linearly in memory and compute, distilled into a three-step student via a 30-second distribution-matching objective. Sets SOTA on WBench and is competitive on VBench-Long and VBench-2.0 while generating each 1.5s chunk in 2.11s on a single H200 at 384x640.
Why it matters
HF Daily +105 upvotes; only paper today above the 100-upvote notable-upvote bar, and a practical step toward long-horizon interactive world models that fit on a single GPU.
Importance: 4/5
HF Daily +105 upvotes; top HF Daily paper (default base 2)
Sources
official
arXiv 2608.13546