Computational usability asks what to compute, how far to simulate, where to run it, and what value it adds.
Action-oriented data help models prioritize the states that matter for decisions and safety.
Risk-adaptive rollouts and device-edge-cloud computing may make world models more deployable.
Action gain per computational cost measures improvements in decision-making relative to computing and resource costs.
| [1] | Ha D. and Schmidhuber J. (2018). Recurrent world models facilitate policy evolution. Adv. Neural Inf. Process. Syst. 31:2451−2463. DOI:10.48550/arXiv.1809.01999 |
| [2] | Hafner D., Lillicrap T., Fischer I., et al. (2019). Learning latent dynamics for planning from pixels. Proc. Mach. Learn. Res. 97:2555−2565. DOI:10.48550/arXiv.1811.04551 |
| [3] | Hafner D., Lillicrap T., Ba J., et al. (2020). Dream to control: Learning behaviors by latent imagination. International Conference on Learning Representations. DOI: 10.48550/arXiv.1912.01603 |
| [4] | Hafner D., Pasukonis J., Ba J., et al. (2025). Mastering diverse control tasks through world models. Nature 640:647−653. DOI:10.1038/s41586-025-08744-2 |
| [5] | Brooks T., Peebles B., Holmes C., et al. (2024). Video generation models as world simulators. OpenAI Technical Report |
| [6] | Assran M., Bardes A., Fan D., et al. (2025). V-JEPA 2: Self-supervised video models enable understanding, prediction and planning. Preprint at arXiv:2506.09985. DOI: 10.48550/arXiv.2506.09985 |
| [7] | World Labs. (2025). Marble: A multimodal world model. World Labs Research Release |
| [8] | World Labs. (2025). RTFM: A real-time frame model. Research preview |
| [9] | Parker-Holder J., Ball P., Bruce J., et al. (2024). Genie 2: A large-scale foundation world model. Google DeepMind Research Report |
| [10] | Parker-Holder J. and Fruchter S. (2025). Genie 3: A new frontier for world models. Google DeepMind Research Report |
| [11] | NVIDIA. (2025). Cosmos world foundation model platform for physical AI. NVIDIA Technical Report DOI: 10.48550/arXiv.2501.03575 |
| [12] | Bordes F., Garrido Q., Kao J.T., et al. (2025). IntPhys 2: Benchmarking intuitive physics understanding in complex synthetic environments. Preprint at arXiv:2506.09849. DOI: 10.48550/arXiv.2506.09849 |
| [13] | Jiang F., Chen Y., Xu K., et al. (2026). RoboWM-Bench: A benchmark for evaluating world models in robotic manipulation. Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recogn Workshops: 4455–4460. DOI: 10.48550/arXiv.2604.19092 |
| [14] | Unterthiner T., van Steenkiste S., Kurach K., et al. (2019). Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:1812.01717. DOI: 10.48550/arXiv.1812.01717 |
| [15] | Assran M., Duval Q., Misra I., et al. (2023). Self-supervised learning from images with a joint-embedding predictive architecture. Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recogn.: 15619–15629. DOI: 10.1109/CVPR52729.2023.01499 |
| [16] | Bardes A., Garrido Q., Ponce J., et al. (2024). Revisiting feature prediction for learning visual representations from video. Trans. Mach. Learn. Res. DOI: 10.48550/arXiv.2404.08471 |
| [17] | Zhang Z., Wang J., Lin C., et al. (2026). TWM: Multimodal data generation engine via traffic world model. Communications in Transportation Research 6(3):9640045. DOI:10.26599/COMMTR.2026.9640045 |
| [18] | Tian S., Zheng Y., Zheng Y., et al. (2026). VT-WAM: Visual-tactile world action model for contact-rich manipulation. Preprint at arXiv:2607.02503. DOI: 10.48550/arXiv.2607.02503 |
| [19] | Higuera C., Arnaud S., Boots B., et al. (2026). Visuo-tactile world models. Preprint at arXiv:2602.06001. DOI: 10.48550/arXiv.2602.06001 |
| [20] | Zheng Y., Gu S., Li W., et al. (2026). OmniVTA: Visuo-tactile world modeling for contact-rich robotic manipulation. Preprint at arXiv:2603.19201. DOI: 10.48550/arXiv.2603.19201 |
| [21] | Zhang Z., Zhou P., Zhang K., et al. (2026). ContactWorld: What matters in vision-tactile world models for contact-rich manipulation. Preprint at arXiv:2606.13877. DOI: 10.48550/arXiv.2606.13877 |
| [22] | Wang S., Shi J., Fu Z., et al. (2026). World action models: The next frontier in embodied AI. Preprint at arXiv:2605.12090. DOI: 10.48550/arXiv.2605.12090 |
| [23] | Cen J., Yu C., Yuan H., et al. (2025). WorldVLA: Towards autoregressive action world model. Adv. Neural Inf. Process. Syst (NeurIPS) 2026 DOI: 10.48550/arXiv.2506.21539 |
| [24] | Yang Y., Liu Z., Kou S., et al. (2026). World-language-action model for unified world modeling, language reasoning, and action synthesis. Conference on Robot Learning (CoRL) 2026 DOI: 10.48550/arXiv.2606.05979 |
| [25] | Russell L., Hu A., Bertoni L., et al. (2025). GAIA-2: A controllable multi-view generative world model for autonomous driving. Preprint at arXiv:2503.20523. DOI: 10.48550/arXiv.2503.20523 |
| [26] | Ren X., Lu Y., Cao T., et al. (2025). Cosmos-Drive-Dreams: Scalable synthetic driving data generation with world foundation models. Preprint at arXiv:2506.09042. DOI: 10.48550/arXiv.2506.09042 |
| [27] | NVIDIA. (2026). NVIDIA OmniDreams: Real-time generative world model for closed-loop autonomous vehicle simulation. Preprint at arXiv:2606.03159. DOI: 10.48550/arXiv.2606.03159 |
| [28] | Zhao P., Lin J., Rupprecht T., et al. (2026). PhyWorld: Physics-faithful world model for video generation. Preprint at arXiv:2605.19242. DOI: 10.48550/arXiv.2605.19242 |
| [29] | Oh Y. and Yun S. (2026). Reference-free assessment of physical consistency in world model-based video generation. Preprint at arXiv:2606.22363. DOI: 10.48550/arXiv.2606.22363 |
| [30] | NVIDIA. (2025). Cosmos-Transfer1: Conditional world generation with adaptive multimodal control. Preprint at arXiv:2503.14492. DOI: 10.48550/arXiv.2503.14492 |
| [31] | Kim M.J., Pertsch K., Karamcheti S., et al. (2025). OpenVLA: An open-source vision-language-action model. Proc. Mach. Learn. Res. 270:2679−2713. DOI:10.48550/arXiv.2406.09246 |
| [32] | Yue Y., Wang Y., Kang B., et al. (2024). DeeR-VLA: Dynamic inference of multimodal large language models for efficient robot execution. Adv. Neural Inf. Process. Syst (NeurIPS). 37:56619−56643. DOI:10.52202/079017-1803 |
| [33] | Kim M.J., Finn C. and Liang P. (2025). Fine-tuning vision-language-action models: Optimizing speed and success. Proc. Robot. Sci. Syst. DOI: 10.15607/RSS.2025.XXI.017 |
| [34] | Liu B., Poe W.Y., Di J., et al. (2026). ComVLA: Communication-aware split inference for VLA models in 6G-connected robotics. Preprint at arXiv:2609.07838. DOI: 10.48550/arXiv.2609.07838 |
| [35] | Yang T., Shen Z., Mi Z., et al. (2026). MiraBench: Evaluating action-conditioned reliability in robotic world models. Preprint at arXiv:2605.29360. DOI: 10.48550/arXiv.2605.29360 |
| [36] | Li J., Guo T., Ye Y., et al. (2026). Efficient-WAM: A 1B-parameter world-action model with low-cost future imagination. Preprint at arXiv:2606.10040. DOI: 10.48550/arXiv.2606.10040 |
| [37] | Bi H., Tan H., Xie S., et al. (2026). Motus: A unified latent action world model. Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR): 35101–35113. DOI: 10.48550/arXiv.2512.13030. |
| Song Y., Wang J., Liu H., et al. (2026). World models: Toward computationally usable embodied AI. The Innovation Insights 1:100018. https://doi.org/10.59717/j.tiis.2026.100018 |
To request copyright permission to republish or share portions of our works, please visit Copyright Clearance Center's (CCC) Marketplace website at marketplace.copyright.com.
Architectural taxonomy, evolution, and computational-usability dimensions of world models for embodied intelligence.
Action-oriented data pyramid for computationally usable world models.