stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916033446543360 |
|---|---|
| author | Maes, Lucas Lidec, Quentin Le Facury, Luiz Massaudi, Nassim Chaurasia, Ayush Capuano, Francesco Gao, Richard Gillin, Taj Haramati, Dan Scieur, Damien LeCun, Yann Balestriero, Randall |
| author_facet | Maes, Lucas Lidec, Quentin Le Facury, Luiz Massaudi, Nassim Chaurasia, Ayush Capuano, Francesco Gao, Richard Gillin, Taj Haramati, Dan Scieur, Damien LeCun, Yann Balestriero, Randall |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_21800 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation Maes, Lucas Lidec, Quentin Le Facury, Luiz Massaudi, Nassim Chaurasia, Ayush Capuano, Francesco Gao, Richard Gillin, Taj Haramati, Dan Scieur, Damien LeCun, Yann Balestriero, Randall Machine Learning Robotics 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. |
| title | stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation |
| topic | Machine Learning Robotics |
| url | https://arxiv.org/abs/2605.21800 |