EditWorld moves video world models from navigation to streaming editing, scoring 73.8 overall and 80.0 on editing in WBench-Editing
EditWorld is a video world model that accepts streaming editing instructions and reference images during autoregressive generation through Gated Causal Attention, a Sparse Context mechanism, joint autoregressive and bidirectional training, and a dedicated data synthesis and annotation pipeline, and it introduces WBench-Editing with roughly 150 cases of 240–480 frames each, achieving the best overall score of 73.8 and an editing score of 80.0 on that benchmark.