stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation

TL;DR

The paper introduces stable-worldmodel (swm), an open-source platform that standardizes and streamlines research and evaluation of world models, addressing reproducibility and comparison challenges.

Contribution

It provides a high-performance data layer, implementations of modern baselines, and a suite of environments for systematic evaluation, unifying the research pipeline.

Findings

Reduces research overhead and accelerates progress in world modeling.

Supports diverse datasets and environments for comprehensive evaluation.

Enhances reproducibility and fair comparison across studies.

Abstract

World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is currently fragmented, with disparate codebases, data pipelines, and evaluation protocols hindering reproducibility and fair comparison. Current practice is further limited by three key bottlenecks: fragile one-off codebases, slow video data loading, and the lack of standardized generalization benchmarks. We present stable-worldmodel (swm), an open-source platform for standardized and reproducible world modeling research and evaluation. It delivers (1) a high-performance Lance-based data layer with native support and conversion tools for MP4, HDF5, and LeRobot datasets, (2) clean, well-tested implementations of modern world model baselines and planning solvers, and (3) a broad suite of environments and tasks extended with controllable visual, geometric, and physical factors of variation for systematic in-silico evaluation of dynamics understanding, control performance, representation quality, and out-of-distribution generalization. By unifying the full pipeline under a single, scalable framework, \texttt{swm} dramatically reduces research overhead and accelerates trustworthy progress toward reliable world models.