Menu

View

JournalDigital

Theme

LightDarkSystem

Text size

AAA

The paper in your inbox every morning

Straight from the source · Glossary

The Tech Gazette

World model

A model that learns how an environment behaves so it can predict what happens next, used in robotics, games and video generation.

Read more at en.wikipedia.org →

In the news

1. arXiv cs.ROOct 15, 2026Research
   T2-z: Test-Time Optimization of Environment Latents for Robotic World Models
2. arXiv cs.CVOct 15, 2026Research
   GeoState: Learning View-Decoupled Geometry States for 3D World Modeling
3. arXiv (vision, retrieval & HCI) cs.CVOct 15, 2026Research
   Velox: Spatial Memory Makes World Models Efficient
4. arXiv (vision, retrieval & HCI) cs.ROOct 13, 2026Research
   WorldOracle: Benchmarking Action-Conditioned World Models against Real-World Executions
5. arXiv cs.ROOct 13, 2026Research
   UniW(A)M: A Unified Mixture-of-Experts Framework for World and World-Action Models
6. arXiv cs.ROOct 13, 2026Research
   Grid or Nodes? Probing Object Memory in World Models Under Partial Observability
7. arXiv cs.CLOct 9, 2026Research
   RSI-Anything: Unlocking Recursive Self-Improvement with World Models
8. arXiv cs.ROOct 9, 2026Research
   Dream to Remember: Continual Steering of Generalist Robot Policies with World Models
9. arXiv (vision, retrieval & HCI) cs.CVOct 9, 2026Research
   GLIMPSE: Global-Local Indexing with Multi-Precision Spectral Encoding for Explorable Video World Models
10. arXiv (systems & security) cs.CROct 9, 2026Research
    Towards Safe World Models: Risks, Defenses, and Evaluation
11. arXiv (vision, retrieval & HCI) cs.ROOct 8, 2026Research
    DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training
12. arXiv (vision, retrieval & HCI) cs.CVOct 8, 2026Research
    What 30,000 Hours of Ego-centric Video Does Not Teach
13. arXiv (vision, retrieval & HCI) cs.CVOct 8, 2026Research
    OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs
14. arXiv (vision, retrieval & HCI) cs.CVOct 8, 2026Research
    WorldGuide: Goal-Directed Video World Model for Procedural Task Execution
15. arXiv (vision, retrieval & HCI) cs.CVOct 8, 2026Research
    WorldCast: Distributed Multiplayer World Models
16. arXiv cs.CVOct 8, 2026Research
    RiCo: Neural Simulation of Rigid-Body Interactions via Local Contact Reasoning
17. arXiv cs.CVOct 8, 2026Research
    Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction
18. arXiv cs.CLOct 8, 2026Research
    Language Models as AI Research World Models
19. arXiv cs.AIOct 7, 2026Research
    RoboJEPA: Scaling Robotic Latent World Models
20. arXiv (vision, retrieval & HCI) cs.CVOct 7, 2026Research
    UltraWorld: Learning Interactive Ultrasound World Models from Untracked Clinical Videos with Acoustic Sampling Map