mlsanityData to 14 Oct 2026

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

arXiv 2605.21800 ↗First posted 20 May 2026cs.LG cs.ROcited by 20

On the map: World models → Video-generation world models and simulators

Abstract (arXiv)

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, textttswm dramatically reduces research overhead and accelerates trustworthy progress toward reliable world models.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Placed in Video-generation world models and simulators, one of 11 directions in World models. Builds on 50 of its 68 references that are in the map. First posted on arXiv 20 May 2026.

Builds on

50 of 68 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026WorldMark: A Unified Benchmark Suite for Interactive Video World Models23 Apr
  2. 2024Genie: Generative Interactive Environments23 Feb
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale22 Oct

Other references · 47

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  5. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  6. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  7. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  8. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  9. 2018World Modelscited by 1,513
  10. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,427
  11. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  12. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,293
35 more
  1. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  2. 2023Mastering Diverse Domains through World Modelscited by 1,253
  3. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,057
  4. 2020Mastering Atari with Discrete World Modelscited by 1,007
  5. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 809
  6. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
  7. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 512
  8. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 511
  9. 2022Temporal Difference Learning for Model Predictive Controlcited by 397
  10. 2024DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planningcited by 386
  11. 2024Diffusion for World Modeling: Visual Details Matter in Ataricited by 300
  12. 2026LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixelscited by 273
  13. 2024Navigation World Modelscited by 272
  14. 2025LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristicscited by 254
  15. 2024OGBench: Benchmarking Offline Goal-Conditioned RLcited by 238
  16. 2025Training Agents Inside of Scalable World Modelscited by 136
  17. 2021Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentationcited by 105
  18. 2021The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixelscited by 100
  19. 2020Sample-efficient Cross-Entropy Method for Real-time Planningcited by 95
  20. 2017Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Controlcited by 93
  21. 2025Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Modelscited by 89
  22. 2024Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learningcited by 88
  23. 2019A Step Toward Quantifying Independently Reproducible Machine Learning Researchcited by 77
  24. 2026LeRobot: An Open-Source Library for End-to-End Robot Learningcited by 73
  25. 2024Learning and Leveraging World Models in Visual Representation Learningcited by 72
  26. 2022Predictive Sampling: Real-time Behaviour Synthesis with MuJoCocited by 47
  27. 2021MBRL-Lib: A Modular Library for Model-based Reinforcement Learningcited by 42
  28. 2023RoboHive: A Unified Framework for Robot Learningcited by 42
  29. 2018Natural Environment Benchmarks for Reinforcement Learningcited by 32
  30. 2025Assessing Adaptive World Models in Machines with Novel Gamescited by 20
  31. 2026A Lightweight Library for Energy-Based Joint-Embedding Predictive Architecturescited by 14
  32. 2026Parallel Stochastic Gradient-Based Planning for World Modelscited by 7
  33. 2026From Kepler to Newton: Inductive Biases Guide Learned World Models in Transformerscited by 7
  34. 2025Lance: Efficient Random Access in Columnar Storage through Adaptive Structural Encodingscited by 6
  35. 2024DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractorscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 20.

20 papers.

Sort:

By area:

  1. 2026World Model Control by Trajectory Reachability Metricscited by 8
  2. 2026LpWM: A Case for Sparse Representations in World Modelscited by 8
  3. 2026FF-JEPA: Long-Horizon Planning in World Models with Latent Plannerscited by 6
  4. 2026PhyLatent: Learning Dynamics-Relevant Representations for JEPA World Modelscited by 6
  5. 2026IMWM: Intuition Models Complement World Models for Latent Planningcited by 4
  6. 2026Action from Adjacent Set in Physical Space Outperforms the Best Prediction in World Modelscited by 2
  7. 2026Reinforced Planning with Latent World Modelscited by 2
  8. 2026Mind the Gap: Promises and Pitfalls of Hierarchical Planning in LeWorldModelcited by 1
  9. 2026Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learnerscited by 0
  10. 2026Beyond Task Success: Stage-Wise Reliability of World Model Planning under Sensing Degradationcited by 0
  11. 2026ATLAS: Aligned Transport of Latent Structure for Reliable World Model Planningcited by 0
  12. 2026Do-JEPA: From Masking to Intervention in Latent World Modelscited by 0
8 more
  1. 2026CF-JEPA: Improving Robustness of JEPA World Models via Controllability Factorizationcited by 0
  2. 2026Learning Commute-Time-Preserving World Models for Planningcited by 0
  3. 2026Keeping JEPA World Models Plannable When Little of the Frame Movescited by 0
  4. 2026What Should World Models Forget? Stratified Retention for Continual Adaptationcited by 0
  5. 2026Flow Policies as Actions of Skill-Level World Models: Learned and Symbolic Abstractions for Long-Horizon Planningcited by 0
  6. 2026How Long, Not How Close: A Learned Temporal Metric for Planning in Latent World Modelscited by 0
  7. 2026LeWAM: End-to-End World and Action Modeling with JEPAscited by 0
  8. 2026LeHami: Symplectic Latent Dynamics for World Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation
  2. 2026PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
  3. 2026A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models
  4. 2025Toward Stable World Models: Measuring and Addressing World Instability in Generative Environments
  5. 2026Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models
  6. 2026PAWBench: How Far Are We from Probabilistically Aligned World Modeling?
  7. 2025World-in-World: World Models in a Closed-Loop World
  8. 2025SmallWorlds: Assessing Dynamics Understanding of World Models in Isolated Environments