mlsanityData to 7 Oct 2026

A Definition and Roadmap for World Models

arXiv 2607.06401 ↗First posted 7 Jul 2026cs.AIcited by 3

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

Abstract (arXiv)

World models -- internal simulators that learn the structure and dynamics of an environment -- have become one of the most actively debated concepts in AI. From model-based reinforcement learning and video generation to embodied robotics and ultimately, physical AI, researchers across AI subfields are building systems that they call "world models", yet there is no consensus on what a world model fundamentally is, what it should predict, or how it should be built. This perspective article provides a scientific definition of world models, discussions of their key technical aspects, and a staged roadmap for developing effective world models.

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 139 of its 253 references that are in the map. First posted on arXiv 7 Jul 2026.

Builds on

139 of 253 references.

Closest ancestors · 9

Same direction, newest first

  1. 2026The Trinity of Consistency as a Defining Principle for General World Models26 Feb
  2. 2025Emu3.5: Native Multimodal Models are World Learners30 Oct
  3. 2025Social World Models30 Aug
  4. 2025General Agentic Planning Through Simulative Reasoning with World Models31 Jul
  5. 2025Critique of World Model7 Jul
  6. 2025Cosmos World Foundation Model Platform for Physical AI7 Jan
  7. 2024Understanding World or Predicting Future? A Comprehensive Survey of World Models21 Nov
  8. 2024WorldGPT: Empowering LLM as Multimodal World Model28 Apr
  9. 2024MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control18 Mar

Other references · 130

  1. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  2. 2020Scaling Laws for Neural Language Modelscited by 6,411
  3. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  4. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  5. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  6. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  7. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  8. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  9. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  10. 2018World Modelscited by 1,444
  11. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  12. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,305
38 more
  1. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  2. 2023Mastering Diverse Domains through World Modelscited by 1,193
  3. 2020Mastering Atari with Discrete World Modelscited by 990
  4. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 982
  5. 2018DeepMind Control Suitecited by 935
  6. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 904
  7. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 867
  8. 2020Learning Mesh-Based Simulation with Graph Networkscited by 840
  9. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 787
  10. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 763
  11. 2024Emu3: Next-Token Prediction is All You Needcited by 761
  12. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 738
  13. 2024Genie: Generative Interactive Environmentscited by 706
  14. 2025Qwen2.5-Omni Technical Reportcited by 704
  15. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
  16. 2023GAIA-1: A Generative World Model for Autonomous Drivingcited by 618
  17. 2024Movie Gen: A Cast of Media Foundation Modelscited by 614
  18. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 569
  19. 2024Revisiting Feature Prediction for Learning Visual Representations from Videocited by 490
  20. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 482
  21. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 479
  22. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 447
  23. 2026World Action Models are Zero-shot Policiescited by 411
  24. 2020Lagrangian Neural Networkscited by 388
  25. 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 375
  26. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  27. 2026Fast-WAM: Do World Action Models Need Test-time Future Imagination?cited by 311
  28. 2023Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Drivingcited by 309
  29. 2025VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulnesscited by 289
  30. 2026Causal World Modeling for Robot Controlcited by 289
  31. 2024Diffusion for World Modeling: Visual Details Matter in Ataricited by 285
  32. 2024Diffusion Models Are Real-Time Game Enginescited by 282
  33. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 279
  34. 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planningcited by 274
  35. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
  36. 2023DriveDreamer: Towards Real-world-driven World Models for Autonomous Drivingcited by 258
  37. 2016Unsupervised Learning for Physical Interaction through Video Predictioncited by 256
  38. 2020ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulationcited by 249

50 most cited of 130 All 130 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Datacited by 1
  2. 2026Persistent Computational State: A Session-Centric Runtime for Generative World Modelscited by 0
  3. 2026InternW0: A Foundational Physical World Model for Efficient Real-World Interactionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications
  2. 2026Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks
  3. 2026From World Models to World Action Models: A Concise Tutorial for Robotics
  4. 2026A Tutorial on World Models and Physical AI
  5. 2026Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling
  6. 2026Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
  7. 2025A Comprehensive Survey on World Models for Embodied AI
  8. 2026World Model for Robot Learning: A Comprehensive Survey