arXiv cs.AI· Yequan Bie, Dengyang Jiang, Zhixuan Chen, Xiaozhuan Liang, Haoxuan Che, Quande Liu, Xi Chen, Hao Chen·· 11 小时前AI 评分40
EvoWorld：让生成式视频模型在视野之外推演世界演化
EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models
AI 导读
EvoWorld 提出“视野外因果演化”（Out-of-Sight Causal Evolution）新任务，要求模型渲染事件后推理其对世界状态的影响，并在视野之外呈现因果合理的结果。
正文 · 原文
Abstract:Generative video models are increasingly used as visual world simulators, yet their primary strength lies in rendering plausible pixels rather than reasoning about how a world should evolve. Coherent world evolution requires more than visual fidelity: when an event occurs, a model must infer its consequences for the entities in the world and then render the resulting state. For example, after a wild beast appears, the model should not only depict the wild beast, but also infer whether a nearby person should flee, take cover, or fight back based on the realized scene. Existing diffusion-based video models lack an explicit mechanism for maintaining world state and reasoning over such event-conditioned consequences, often producing visually plausible but behaviorally static or causally inconsistent outputs. To make this reasoning gap concrete and measurable, we propose a new problem, Out-of-Sight Causal Evolution, which requires a model to render an event, reason about its consequences for the evolving world state, and reveal a causally plausible outcome as the world continues to evolve, even out of sight. As a baseline reference solution, we introduce EvoWorld, a brain-renderer collaboration framework in which a vision-language model serves as the world brain: it observes generated segments, maintains an evolving account of the world, and reasons about plausible state transitions, while a segment-autoregressive video renderer realizes them visually. We further introduce EvoWorld-Data and EvoWorld-Bench for training and evaluating event realization, causal reactions, and revisit consistency. Experiments show that EvoWorld substantially improves event-conditioned causal evolution over recent models while preserving visual quality and consistency, establishing a reference point for reasoning-guided, autonomous world evolution beyond the current field of view.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.06748 [cs.CV] |
| (or arXiv:2611.06748v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06748 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yequan Bie [view email]
[v1]
Wed, 4 Nov 2026 16:26:45 UTC (4,928 KB)
来源：arXiv cs.AI · arxiv.org