cs.CVNov 17, 2026

Code World Model 2.0: Towards Infinite Controllable Video Generation

Authors: Ruoyu Wang, Hao Zhong, Yanming Yang, Jiahao Tian, Lin Liu, Biao Gong, Guoshan Lu, Yiding Tian, 

Organizations: Westlake University · AGI Research Center, Inclusion AI · Zhejiang University

Abstract

Visual proxies decouple explicit world-state simulation from photorealistic video synthesis, offering a controllable interface for both offline clip creation and real-time interactive streaming. Yet a practical renderer must address two challenges. Upstream proxies vary from coarse layouts to fine articulated geometry depending on the interaction, and streaming inference must operate in a few causal steps without accumulating drift across self-generated history. We present Invoker-Render, pairing a bidirectional creation model with a causal four-step streaming model under a shared conditioning interface over structural proxies, an appearance reference, and language. Trained on an aligned approximately 200-hour multi-granularity corpus, Invoker-Render honors fine geometric constraints when supplied while synthesizing plausible local motion under coarse proxies, enabling runtime selection of input detail. To bridge bidirectional creation and real-time streaming without compounding step compression and rollout drift, we introduce Progressive Forcing (ProForcing). ProForcing first trains a causal predictor and distills it into a four-step renderer using histories derived from training videos. Training then shifts to continuous self-generated rollouts. A pipelined serving stack supports efficient streaming inference. Experiments show versatile control across proxy families, granularities, and camera paths, consistent gains over recent streaming baselines, and stable 30-minute racing rollouts that preserve scene and subject appearance.

Figures & tables

Explore similar work

CardsList
  1. Streaming Video Generation with Streaming Force Control

    Jun 5, 2026Hanhui Wang, Yiming Xie, Haiwen Feng +3Streaming Video GenerationAutoregressive Video Generation

  2. Astronex-World 1.0: Real-Time Interactive World Model Foundation

    Sep 17, 2026Xin Zhou, Cong MiaoVideo World ModelsVideo Diffusion Models

  3. RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control

    May 7, 2026Youcan Xu, Jiaxin Shi, Zhen Wang +5Camera-Controlled Video GenerationReal-Time Interactive Video Generation