LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models

arXiv 26.3 2026 72.4 method

TLDR

LiveWorld extends video world models to simulate persistent out-of-sight dynamics using a global state and monitor-based mechanism, evaluated on LiveBench.

Reasoning

The paper identifies a novel limitation (out-of-sight dynamics) in video world models and proposes a framework with persistent global state and monitor-based simulation. Strengths include a clear problem formalization and a dedicated benchmark, but the abstract lacks details on real-world data and the benchmark's composition.

Read-first score

Read-first score 72.4, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 58.

Recency 8%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Topical relevance 42%

82.9

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Methodology quality 25%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=baseline,benchmark,evaluation,experiment

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=github

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 84.

Keyword Scores

world model

generative world model

video world model

interactive world model

world dynamics prediction

world simulator

model-based reinforcement learning world model

Deep Analysis

Innovations

Formalizing the out-of-sight dynamics problem in generative video world models
Proposing LiveWorld framework with a persistent global state composed of static 3D background and dynamic entities
Monitor-based mechanism for autonomously simulating temporal progression of active entities and synchronizing evolved states upon revisiting
Introducing LiveBench, a dedicated benchmark for evaluating out-of-sight dynamics

Methodology

LiveWorld models a persistent global state consisting of a static 3D background and dynamic entities that continue evolving even when unobserved. It employs a monitor-based mechanism to autonomously simulate the temporal progression of active entities and synchronizes their evolved states upon revisiting, ensuring spatially coherent rendering. The framework extends existing video world models to support persistent world evolution.

Key Results

LiveWorld enables persistent event evolution and long-term scene consistency, bridging the gap between existing 2D observation-based memory and true 4D dynamic world simulation.

Resources

Paper