mlsanityData to 7 Oct 2026

From World Models to World Action Models: A Concise Tutorial for Robotics

arXiv 2607.00836 ↗First posted 1 Jul 2026cs.RO cs.AI cs.SYcited by 3

On the map: World models → World models for language agents

Abstract (arXiv)

Rather than providing an exhaustive survey, this paper presents a concise tutorial on world models and world action models for robotics. After reading the tutorial, readers should have a clear understanding of what constitutes a "world", how world models and world action models are defined, and what roles they play within robotic AI systems. The tutorial also develops a unified perspective for comparing representative approaches, such as World Labs' spatial intelligence models, Yann LeCun's JEPA framework, and NVIDIA's Cosmos platform, and clarifies how these models differ in their representations, predictive capabilities, and interaction mechanisms.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 50 of its 57 references that are in the map. First posted on arXiv 1 Jul 2026.

Builds on

50 of 57 references.

References · 50

  1. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  2. 2018World Modelscited by 1,444
  3. 2023Mastering Diverse Domains through World Modelscited by 1,193
  4. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 738
  5. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 482
  6. 2026World Action Models are Zero-shot Policiescited by 411
  7. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  8. 2022DayDreamer: World Models for Physical Robot Learningcited by 372
  9. 2024DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planningcited by 357
  10. 2026Fast-WAM: Do World Action Models Need Test-time Future Imagination?cited by 311
  11. 2024GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulationcited by 290
  12. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 279
38 more
  1. 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planningcited by 274
  2. 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Modelscited by 264
  3. 2026LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixelscited by 237
  4. 2025Motus: A Unified Latent Action World Modelcited by 231
  5. 2025Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasetscited by 218
  6. 2023Any-point Trajectory Modeling for Policy Learningcited by 207
  7. 2025Unified Video Action Modelcited by 195
  8. 2023Learning to Act from Actionless Videos through Dense Correspondencescited by 159
  9. 2025Ctrl-World: A Controllable Generative World Model for Robot Manipulationcited by 149
  10. 2025mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAscited by 133
  11. 2024Flow as the Cross-Domain Manipulation Interfacecited by 126
  12. 2026DreamDojo: A Generalist Robot World Model from Large-Scale Human Videoscited by 117
  13. 2025AdaWorld: Learning Adaptable World Models with Latent Actionscited by 108
  14. 2025Video Generators are Robot Policiescited by 86
  15. 2024Dreamitate: Real-World Visuomotor Policy Learning via Video Generationcited by 84
  16. 2025PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videoscited by 78
  17. 2026DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Controlcited by 71
  18. 2025Vidar: Embodied Video Diffusion Model for Generalist Manipulationcited by 58
  19. 2024Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulationcited by 51
  20. 2024VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planningcited by 37
  21. 20253DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Modelcited by 36
  22. 2025Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrationscited by 33
  23. 2025EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modelingcited by 29
  24. 2025ParticleFormer: A 3D Point Cloud World Model for Multi-Object, Multi-Material Robotic Manipulationcited by 26
  25. 2024Grounding Video Models to Actions through Goal Conditioned Explorationcited by 25
  26. 2025LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulationcited by 24
  27. 2025Inference-Time Enhancement of Generative Robot Policies via Predictive World Modelingcited by 22
  28. 2025PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulationcited by 22
  29. 2025SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulationcited by 21
  30. 2025FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulationcited by 17
  31. 2025Object-Centric World Model for Language-Guided Manipulationcited by 16
  32. 2025OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generationcited by 10
  33. 2025WoMAP: World Models For Embodied Open-Vocabulary Object Localizationcited by 8
  34. 2025ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planningcited by 8
  35. 2026ContactGaussian-WM: Learning Physics-Grounded World Model from Videoscited by 7
  36. 2026From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Datacited by 4
  37. 2025Generative Visual Foresight Meets Task-Agnostic Pose Estimation in Robotic Table-Top Manipulationcited by 2
  38. 2026SSI-Policy: Learning Structured Scene Interfaces for Vision-Language Robotic Manipulationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026PredVLA: Predictive Sensorimotor Modeling for Sub-Million-Parameter Robot Manipulationcited by 0
  2. 2026Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model Explorationcited by 0
  3. 2026DualWAM: Dual-System World Action Models for Asynchronous Global Planning and Local Refinementcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Step Toward World Models: A Survey on Robotic Manipulation
  2. 2026World-Action Models for Robot Learning and Control: A Survey
  3. 2026World Model for Robot Learning: A Comprehensive Survey
  4. 2026World Action Models: The Next Frontier in Embodied AI
  5. 2026What Matters in Designing World Action Models: An Empirical Study
  6. 2025A Comprehensive Survey on World Models for Embodied AI
  7. 2026A Tutorial on World Models and Physical AI
  8. 2026Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks