Awesome World Model Hub Papers · Datasets · Projects
← Back to papers

When do Neural Networks Learn World Models?

arXiv 25.2 2025 48.8 theory

TLDR

The paper provides theoretical results showing that neural networks with low-degree bias can recover latent world model variables in multi-task settings.

Reasoning

Strengths include novel theoretical analysis using Fourier-Walsh transforms and connections to self-supervised learning. Weaknesses are the lack of empirical validation and reliance on restrictive Boolean model assumptions.

Read-first score

Read-first score 48.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 16.

Methodology quality 25%
90

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

Recency 8%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Reproducibility 25%
38

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

Topical relevance 42%
22.9

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

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 518.

Keyword Scores

world model
9
generative world model
2
world simulator
1
interactive world model
1
video world model
1
world dynamics prediction
1
model-based reinforcement learning world model
1

Deep Analysis

Innovations

  • First theoretical results for when neural networks learn world models in a multi-task setting
  • Demonstrating that models with low-degree bias provably recover latent data-generating variables under mild assumptions, even with complex non-linear proxy tasks
  • New techniques for analyzing invertible Boolean transforms via the Fourier-Walsh transform

Methodology

The paper presents a theoretical analysis using Boolean models of task solutions and the Fourier-Walsh transform. It introduces new techniques for analyzing invertible Boolean transforms to prove that neural networks with low-degree bias can recover latent variables in a multi-task setting, assuming mild conditions on the data generation process.

Key Results

The theoretical results show that under mild assumptions, neural networks with low-degree bias can provably recover latent data-generating variables, but this recovery is sensitive to model architecture.

Limitations

  • Recovery of latent variables is sensitive to model architecture, limiting general applicability
  • The analysis relies on Boolean models and specific assumptions that may not hold in all real-world scenarios
  • The results are theoretical and lack empirical validation on practical datasets or tasks

Tags