AI Daybook
AI Daybook
Today's issue
PaperResearch

EvoWorld improves causal reasoning in generative video models through world state evolution

Original titleEvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models

Outlet
Hugging Face
Published
Importance
2/5
Trending
11

Summary

The authors address how generative video models can reason about world state changes when events occur, not just render plausible pixels. They introduce EvoWorld, a framework where a vision-language model acts as a world brain to observe segments, maintain an evolving world account, and reason about state transitions, while a video renderer realizes them visually. They also propose the Out-of-Sight Causal Evolution task and introduce EvoWorld-Data and EvoWorld-Bench for training and evaluation.

Original excerpt

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.

#reasoning#world model#video generation
Read the original
See all →