Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond

arXiv 24.5 2024 72.8 survey

TLDR

A comprehensive survey of general world models, focusing on Sora's simulation capabilities, generative video, autonomous driving, and autonomous agents.

Reasoning

The paper provides a broad overview of world models across multiple domains, which is a strength for a survey. However, it lacks original experiments or real-world validation, limiting its novelty and empirical contribution.

Read-first score

Read-first score 72.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 56.

Topical relevance 42%

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

Recency 8%

75.1

Uses a gentle age decay so recent papers surface without erasing older foundations. 2024

Reproducibility 25%

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

Methodology quality 25%

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

Field roles

Reproducibility anchor

Rank sensitivity

Stability: volatile; rank range: 79.

Keyword Scores

world model

world simulator

generative world model

video world model

interactive world model

world dynamics prediction

model-based reinforcement learning world model

Deep Analysis

Innovations

Sora model's simulation capabilities demonstrating incipient comprehension of physical laws
Comprehensive survey linking video generation, autonomous driving, and autonomous agents under the umbrella of world models

Methodology

This survey conducts a comprehensive literature review of recent advancements in world models, analyzing generative methodologies in video generation, autonomous-driving world models, and world models in autonomous agents. It examines challenges and limitations and discusses future directions.

Key Results

The survey finds that Sora exhibits remarkable simulation capabilities with an incipient comprehension of physical laws, and that world models are pivotal for synthesizing realistic visual content, reshaping transportation, and enabling intelligent interactions in dynamic environments.

Limitations

Challenges and limitations of world models are discussed but not detailed in the abstract.

Resources

Paper Code