Atlasof World Models
Start

The map room

Library

The primary sources behind the atlas. The essays that framed the field, the tutorials that teach it and the systems that show it working. Every link opens the original.

Essays & Perspectives

The pieces that framed what a world model is and why it matters.

  1. World Models Ha & Schmidhuber, 2018 Cited in T-01
  2. A Path Towards Autonomous Machine Intelligence Yann LeCun Cited in T-19
  3. From Words to Worlds Fei-Fei Li Cited in T-02T-13
  4. A Functional Taxonomy of World Models World Labs Cited in T-14
  5. Agents That Imagine and Plan Google DeepMind Cited in T-18
  6. The Quest for a Common Model of the Intelligent Decision Maker Richard Sutton Cited in T-01T-21

Tutorials & Collections

Structured ways in, from survey tutorials to maintained paper lists.

  1. From Video Generation to World Model CVPR 2025 tutorial Cited in T-11
  2. World Modeling Workshop Mila 2026 Cited in T-12
  3. Awesome World Models Dong et al. Cited in T-21
  4. From World Models to World Action Models Zhang et al. Cited in T-17
  5. World Models (lecture slides) CMU 10-423 Generative AI
  6. The World of World Modeling (lecture slides) Stanford CS234 Cited in T-18
  7. CIS 6280: World Models University of Pennsylvania, Fall 2026

Talks & Seminars

The field in its builders' own words.

  1. Fireside Chat with Ilya Sutskever and Jensen Huang NVIDIA GTC 2023
  2. The Sensorimotor Road to Artificial Intelligence Jitendra Malik, UC Berkeley 2023
  3. With Spatial Intelligence, AI Will Understand the Real World Fei-Fei Li, TED 2024
  4. Fireside Chat with Yann LeCun RAISE 2026
  5. A Path Towards Autonomous Machine Intelligence Yann LeCun, AFOSR 2024
  6. A Path Towards Autonomous Machine Intelligence Yann LeCun, IHES 2023

Systems & Demos

World models you can see working.

  1. DreamerV3 Hafner et al. Cited in T-03T-09
  2. V-JEPA 2 Meta AI Cited in T-05
  3. Genie Google DeepMind Cited in T-12
  4. Marble World Labs Cited in T-14
  5. GAIA-4 Wayve Cited in T-11
  6. AIDO Cell Simulator GenBio AI Cited in T-15
  7. DayDreamer: World Models for Physical Robot Learning Wu et al. Cited in T-16
  8. DINO-WM: World Models on Pre-trained Visual Features Zhou et al., ICML 2025 Cited in T-16

Key Papers

Papers cited across the territories, each checked against its arXiv record.

  1. Learning Latent Dynamics for Planning from Pixels (PlaNet) Hafner et al., 2018 Cited in T-08
  2. Dream to Control: Learning Behaviors by Latent Imagination Hafner et al., 2019 Cited in T-10
  3. Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model (MuZero) Schrittwieser et al., 2019 Cited in T-10
  4. Denoising Diffusion Probabilistic Models Ho et al., 2020 Cited in T-06T-07
  5. Flow Matching for Generative Modeling Lipman et al., 2022 Cited in T-07
  6. Genie: Generative Interactive Environments Bruce et al., 2024 Cited in T-12
  7. NeRF: Representing Scenes as Neural Radiance Fields Mildenhall et al., 2020 Cited in T-13
  8. 3D Gaussian Splatting for Real-Time Radiance Field Rendering Kerbl et al., 2023 Cited in T-13
  9. Learning to Simulate Complex Physics with Graph Networks Sanchez-Gonzalez et al., 2020 Cited in T-15
  10. RT-2: Vision-Language-Action Models Brohan et al., 2023 Cited in T-17
  11. Emergent World Representations (Othello-GPT) Li et al., 2022 Cited in T-18
  12. OSWorld: Benchmarking Multimodal Agents Xie et al., 2024 Cited in T-20

By territory

Every territory's further reading, 112 entries in reading order.

T-01 World Models: An Overview 4
  1. World Models David Ha, Jürgen Schmidhuber, 2018
  2. Dyna, an Integrated Architecture for Learning, Planning, and Reacting Richard S. Sutton, 1991
  3. The Quest for a Common Model of the Intelligent Decision Maker Richard S. Sutton, 2022
  4. A Path Towards Autonomous Machine Intelligence Yann LeCun, 2022
T-02 History, Foundations & Probabilistic Formulation 4
  1. A New Approach to Linear Filtering and Prediction Problems R. E. Kalman, 1960
  2. Planning and Acting in Partially Observable Stochastic Domains Leslie Pack Kaelbling, Michael L. Littman, Anthony R. Cassandra, 1998
  3. Learning Latent Dynamics for Planning from Pixels Danijar Hafner, Timothy Lillicrap, Ian Fischer, Ruben Villegas, David Ha, Honglak Lee, James Davidson, 2019
  4. From Words to Worlds: Spatial Intelligence is AI's Next Frontier Fei-Fei Li, 2025
T-03 Environments, Simulators & Rollouts 5
  1. OpenAI Gym Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, Wojciech Zaremba, 2016
  2. Gymnasium: A Standard Interface for Reinforcement Learning Environments Mark Towers, Ariel Kwiatkowski, Jordan Terry, John U. Balis and others, 2024
  3. Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks Samy Bengio, Oriol Vinyals, Navdeep Jaitly, Noam Shazeer, 2015
  4. When to Trust Your Model: Model-Based Policy Optimization Michael Janner, Justin Fu, Marvin Zhang, Sergey Levine, 2019
  5. Mastering diverse control tasks through world models (DreamerV3) Danijar Hafner, Jurgis Pasukonis, Jimmy Ba, Timothy Lillicrap, 2025
T-04 State-Space Models 5
  1. A New Approach to Linear Filtering and Prediction Problems R. E. Kalman, 1960
  2. Maximum Likelihood Estimates of Linear Dynamic Systems H. E. Rauch, F. Tung, C. T. Striebel, 1965
  3. Efficiently Modeling Long Sequences with Structured State Spaces Albert Gu, Karan Goel, Christopher Ré, 2022
  4. Mamba: Linear-Time Sequence Modeling with Selective State Spaces Albert Gu, Tri Dao, 2023
  5. Kalman Filter Tracking Dynamax
T-05 Representation Learning 6
  1. Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture Mahmoud Assran, Quentin Duval, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael Rabbat, Yann LeCun, Nicolas Ballas, 2023
  2. V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning Mido Assran, Adrien Bardes, David Fan, Quentin Garrido and others, 2025
  3. A Simple Framework for Contrastive Learning of Visual Representations Ting Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey Hinton, 2020
  4. Masked Autoencoders Are Scalable Vision Learners Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross Girshick, 2021
  5. LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics Randall Balestriero, Yann LeCun, 2025
  6. Contrastive Representation Learning Lilian Weng, 2021
T-06 Generative Foundations: Latent Variables, Diffusion & Flow 5
  1. Auto-Encoding Variational Bayes Diederik P. Kingma, Max Welling, 2013
  2. Generative Adversarial Networks Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio, 2014
  3. Generating Sentences from a Continuous Space Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, Andrew M. Dai, Rafal Jozefowicz, Samy Bengio, 2016
  4. Denoising Diffusion Probabilistic Models Jonathan Ho, Ajay Jain, Pieter Abbeel, 2020
  5. From Autoencoder to Beta-VAE Lilian Weng, 2018
T-07 Diffusion & Flow Matching 6
  1. Denoising Diffusion Probabilistic Models Jonathan Ho, Ajay Jain, Pieter Abbeel, 2020
  2. Flow Matching for Generative Modeling Yaron Lipman, Ricky T. Q. Chen, Heli Ben-Hamu, Maximilian Nickel, Matt Le, 2022
  3. High-Resolution Image Synthesis with Latent Diffusion Models Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Björn Ommer, 2022
  4. Classifier-Free Diffusion Guidance Jonathan Ho, Tim Salimans, 2022
  5. Diffusion for World Modeling: Visual Details Matter in Atari Eloi Alonso, Adam Jelley, Vincent Micheli, Anssi Kanervisto, Amos Storkey, Tim Pearce, François Fleuret, 2024
  6. Diffusion Models Are Real-Time Game Engines Dani Valevski, Yaniv Leviathan, Moab Arar, Shlomi Fruchter, 2024
T-08 Latent World Models 5
  1. Learning Latent Dynamics for Planning from Pixels (PlaNet) Danijar Hafner, Timothy Lillicrap, Ian Fischer, Ruben Villegas, David Ha, Honglak Lee, James Davidson, 2018
  2. Mastering Atari with Discrete World Models (DreamerV2) Danijar Hafner, Timothy Lillicrap, Mohammad Norouzi, Jimmy Ba, 2020
  3. Mastering Diverse Domains through World Models (DreamerV3) Danijar Hafner, Jurgis Pasukonis, Jimmy Ba, Timothy Lillicrap, 2023
  4. Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture (I-JEPA) Mahmoud Assran et al., 2023
  5. Deep Dive into Yann LeCun's JEPA Rohit Bandaru, 2024
T-09 Model-Based Reinforcement Learning, Planning & Control 6
  1. DreamerV3 Danijar Hafner, 2023
  2. Model Predictive Control: Theory, Computation, and Design (2nd edition) James B. Rawlings, David Q. Mayne, Moritz M. Diehl, 2017
  3. Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models (PETS) Kurtland Chua, Roberto Calandra, Rowan McAllister, Sergey Levine, 2018
  4. When to Trust Your Model: Model-Based Policy Optimization (MBPO) Michael Janner, Justin Fu, Marvin Zhang, Sergey Levine, 2019
  5. TD-MPC2: Scalable, Robust World Models for Continuous Control Nicklas Hansen, Hao Su, Xiaolong Wang, 2023
  6. V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning Mido Assran et al., 2025
T-10 Learning in Imagination: Policy & Value 4
  1. Dream to Control: Learning Behaviors by Latent Imagination Danijar Hafner, Timothy Lillicrap, Jimmy Ba, Mohammad Norouzi, 2019
  2. Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model (MuZero) Julian Schrittwieser et al., 2019
  3. World Models David Ha, Jurgen Schmidhuber, 2018
  4. World Models · MBRL History Loqman Samani
T-11 Video World Models I: Generation & Rollout 5
  1. Learning Interactive Real-World Simulators (UniSim) Sherry Yang et al., 2023
  2. GAIA-1: A Generative World Model for Autonomous Driving Anthony Hu et al., 2023
  3. GAIA-4 Wayve, 2026
  4. Cosmos World Foundation Model Platform for Physical AI NVIDIA, 2025
  5. From Video Generation to World Model CVPR 2025 tutorial, 2025
T-12 Video World Models II: Interaction, Memory & Efficiency 6
  1. Genie: Generative Interactive Environments Jake Bruce et al., 2024
  2. Diffusion Models Are Real-Time Game Engines (GameNGen) Dani Valevski, Yaniv Leviathan, Moab Arar, Shlomi Fruchter, 2024
  3. Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion Boyuan Chen et al., 2024
  4. Genie Google DeepMind
  5. Genie 3: A new frontier for world models Google DeepMind, 2025
  6. World Modeling Workshop Mila, 2026
T-13 Spatial World Models I: Geometry & 3D Representations 4
  1. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis Ben Mildenhall et al., 2020
  2. 3D Gaussian Splatting for Real-Time Radiance Field Rendering Bernhard Kerbl, Georgios Kopanas, Thomas Leimkuhler, George Drettakis, 2023
  3. DUSt3R: Geometric 3D Vision Made Easy Shuzhe Wang et al., 2023
  4. From Words to Worlds: Spatial Intelligence Fei-Fei Li, 2025
T-14 Spatial World Models II: 4D Dynamics & Interaction 6
  1. D-NeRF: Neural Radiance Fields for Dynamic Scenes Albert Pumarola, Enric Corona, Gerard Pons-Moll, Francesc Moreno-Noguer, 2020
  2. Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis Jonathon Luiten, Georgios Kopanas, Bastian Leibe, Deva Ramanan, 2023
  3. 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering Guanjun Wu et al., 2023
  4. OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving Wenzhao Zheng et al., 2023
  5. A Functional Taxonomy of World Models World Labs, 2026
  6. Marble World Labs, 2025
T-15 Neural Physics & Learned Dynamics 6
  1. Learning to Simulate Complex Physics with Graph Networks Alvaro Sanchez-Gonzalez et al., 2020
  2. Learning Mesh-Based Simulation with Graph Networks (MeshGraphNets) Tobias Pfaff, Meire Fortunato, Alvaro Sanchez-Gonzalez, Peter W. Battaglia, 2020
  3. Fourier Neural Operator for Parametric Partial Differential Equations Zongyi Li et al., 2020
  4. Hamiltonian Neural Networks Sam Greydanus, Misko Dzamba, Jason Yosinski, 2019
  5. GraphCast: Learning skillful medium-range global weather forecasting Remi Lam et al., 2022
  6. AIDO Cell Simulator GenBio AI
T-16 World Models for Robots I: Simulation, Control & Sim-to-Real 4
  1. Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World Tobin, Fong, Ray, Schneider, Zaremba, Abbeel, 2017
  2. Sim-to-Real Transfer of Robotic Control with Dynamics Randomization Peng, Andrychowicz, Zaremba, Abbeel, 2017
  3. DayDreamer: World Models for Physical Robot Learning Wu, Escontrela, Hafner, Goldberg, Abbeel, 2022
  4. DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning Zhou, Pan, LeCun, Pinto, 2024
T-17 World Models for Robots II: Vision-Language-Action & World-Action Models 5
  1. RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control Brohan et al., 2023
  2. OpenVLA: An Open-Source Vision-Language-Action Model Kim et al., 2024
  3. π0: A Vision-Language-Action Flow Model for General Robot Control Black et al. (Physical Intelligence), 2024
  4. Learning Universal Policies via Text-Guided Video Generation Du et al., 2023
  5. From World Models to World Action Models: A Concise Tutorial for Robotics Zhang, Zeng, Zhang, 2026
T-18 LLMs as World Models: Simulation, State Tracking & Grounding 6
  1. Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task Li, Hopkins, Bau, Viégas, Pfister, Wattenberg, 2023
  2. Can Language Models Serve as Text-Based World Simulators? Wang, Todd, Xiao, Yuan, Côté, Clark, Jansen, 2024
  3. Evaluating the World Model Implicit in a Generative Model Vafa, Chen, Rambachan, Kleinberg, Mullainathan, 2024
  4. World Modeling in Transformers Beckmann, Queloz, Freitas, 2026
  5. Agents That Imagine and Plan Google DeepMind, 2017
  6. The World of World Modeling (Stanford CS234 lecture slides) Stanford CS234, 2026
T-19 Reasoning Models: Deliberation, Recurrence & Test-Time Compute 8
  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models Wei, Wang, Schuurmans, Bosma, Ichter, Xia, Chi, Le, Zhou, 2022
  2. Self-Consistency Improves Chain of Thought Reasoning in Language Models Wang et al., 2022
  3. Tree of Thoughts: Deliberate Problem Solving with Large Language Models Yao et al., 2023
  4. Let's Verify Step by Step Lightman et al., 2023
  5. Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters Snell, Lee, Xu, Kumar, 2024
  6. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning DeepSeek-AI, 2025
  7. Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Geiping et al., 2025
  8. A Path Towards Autonomous Machine Intelligence Yann LeCun, 2022
T-20 World Models for Digital Agents 5
  1. WebArena: A Realistic Web Environment for Building Autonomous Agents Zhou et al., 2023
  2. OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Xie et al., 2024
  3. Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation Chae et al., 2024
  4. Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents Gu et al., 2024
  5. τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains Yao, Shinn, Razavi, Narasimhan, 2024
T-21 Evaluating World Models: Utility, Robustness & Open Problems 7
  1. Objective Mismatch in Model-based Reinforcement Learning Lambert, Amos, Yadan, Calandra, 2020
  2. Do generative video models understand physical principles? Motamed, Culp, Swersky, Jaini, Geirhos, 2025
  3. Evaluating the World Model Implicit in a Generative Model Vafa, Chen, Rambachan, Kleinberg, Mullainathan, 2024
  4. Towards Accurate Generative Models of Video: A New Metric & Challenges Unterthiner, van Steenkiste, Kurach, Marinier, Michalski, Gelly, 2018
  5. A Survey of Algorithms for Black-Box Safety Validation of Cyber-Physical Systems Corso, Moss, Koren, Lee, Kochenderfer, 2021
  6. The Quest for a Common Model of the Intelligent Decision Maker Richard Sutton, 2022
  7. Awesome World Models (Dong et al.) Dong et al., 2026

Search the atlas