stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation

Papers with Code Trending Papers
world-models reproducible-research reinforcement-learning robustness continual-learning framework open-source

Summary

Stable-Worldmodel (SWM) is a modular and standardized research framework for developing and evaluating world models, designed to improve reproducibility and support robustness and continual learning research.

World Models have emerged as a powerful paradigm for learning compact, predictive representations of environment dynamics, enabling agents to reason, plan, and generalize beyond direct experience. Despite recent interest in World Models, most available implementations remain publication-specific, severely limiting their reusability, increasing the risk of bugs, and reducing evaluation standardization. To mitigate these issues, we introduce stable-worldmodel (SWM), a modular, tested, and documented world-model research ecosystem that provides efficient data-collection tools, standardized environments, planning algorithms, and baseline implementations. In addition, each environment in SWM enables controllable factors of variation, including visual and physical properties, to support robustness and continual learning research. Finally, we demonstrate the utility of SWM by using it to study zero-shot robustness in DINO-WM.
Original Article
View Cached Full Text

Cached at: 05/29/26, 06:47 AM

Paper page - stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation

Source: https://huggingface.co/papers/2602.08968

Abstract

Stable-worldmodel provides a modular and standardized research framework for developing and evaluating world models with controllable environmental factors for robustness and continual learning applications.

World Modelshave emerged as a powerful paradigm for learning compact,predictive representationsofenvironment dynamics, enabling agents to reason, plan, and generalize beyond direct experience. Despite recent interest inWorld Models, most available implementations remain publication-specific, severely limiting their reusability, increasing the risk of bugs, and reducing evaluation standardization. To mitigate these issues, we introduce stable-worldmodel (SWM), a modular, tested, and documented world-model research ecosystem that provides efficientdata-collection tools,standardized environments,planning algorithms, andbaseline implementations. In addition, each environment in SWM enablescontrollable factors of variation, including visual and physical properties, to supportrobustnessandcontinual learningresearch. Finally, we demonstrate the utility of SWM by using it to studyzero-shot robustnessinDINO-WM.

View arXiv pageView PDFProject pageGitHub881Add to collection

Get this paper in your agent:

hf papers read 2602\.08968

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper2

#### zzsi/swm-dmc-cheetah #### zzsi/swm-dmc-expert-policies Reinforcement Learning• UpdatedFeb 26

Datasets citing this paper3

#### zzsi/swm-dmc-expert #### zzsi/swm-dmc-mixed-small #### zzsi/swm-dmc-mixed-large

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2602.08968 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

galilai-group/stable-worldmodel

GitHub Trending (daily)

stable-worldmodel is a unified platform for reproducible world model research, providing standardized environments, data collection, training, and evaluation interfaces.

Building Social World Models with Large Language Models

Hugging Face Daily Papers

The paper introduces the Social World Model (SWM) framework, which uses large language models to model the dynamics of social beliefs in response to events, without explicit annotations. It also presents a benchmark SWM-bench derived from prediction markets and shows state-of-the-art results.

World Model for Robot Learning: A Comprehensive Survey

Hugging Face Daily Papers

This comprehensive survey reviews the literature on world models for robot learning, covering their roles in policy learning, planning, and simulation. It highlights key paradigms, benchmarks, and future directions for predictive modeling in embodied agents.