cs.CVNov 19, 2026

ScaleWorld: High-Resolution World Generation through Shared Prediction and Refinement

Authors: Yansong Qu, Wesker Zheng, Quanjian Song, Zhiyuan Zhang, Xiao Cao, Shengchuan Zhang, Liujuan Cao

Organizations: Xiamen University · Southeast University · City University of Hong Kong · National University of Singapore

Abstract

High-resolution generation enables video world models to render fine-grained scene structures and textures, but directly generating high-resolution video incurs substantial computational and memory costs. We present ScaleWorld, a causal video model that unifies low-resolution world prediction and high-resolution refinement within a single shared backbone. By refining its own predictions, ScaleWorld produces high-resolution world videos without requiring a separate refinement model. For each video chunk, the shared backbone first completes a low-resolution prediction and then performs one-step high-resolution refinement conditioned on that prediction. To support efficient streaming generation, we maintain separate causal states with a long low-resolution history for prediction and a short high-resolution history for refinement. To address task interference during distillation, we separate specialist optimization from capability consolidation and introduce task-asymmetric on-policy distillation (TA-OPD). This procedure transfers prediction and refinement behaviors from specialized teachers into a shared student through local velocity matching under their respective sampling and history policies. {Extensive experiments demonstrate that ScaleWorld achieves high-quality world generation with improved computational and memory efficiency.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. DreamWorld: Unified World Modeling in Video Generation

    Feb 28, 2026Boming Tan, Xiangdong Zhang, Ning Liao +73D-Aware Video GenerationVideo World Models

  2. Next Forcing: World Action Modeling with Multi-Chunk Prediction

    Jun 9, 2026Gangwei Xu, Qihang Zhang, Jiaming Zhou +4Causal World ModelsAutoregressive Video Generation