Overview

World models learn or encode how states, objects, and events evolve, often predicting what will happen under different actions or observations. These predictions can help agents plan ahead, learn with fewer real-world trials, test decisions safely, and reason about situations they cannot currently observe. Approaches range from latent-state predictors and action-conditioned video generators to object- or graph-based models, executable programs, and physics-informed dynamics. A central challenge is making predictions useful and reliable over long horizons: visual plausibility and one-step accuracy do not guarantee correct causal dynamics, persistent memory, or better decisions.

Latest papers

CardsList

402 papers38 papers in the last four weeks, down 51% on the four weeks before. 0.3% of all new papers.

  1. From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery

    Jul 14, 2026Ingmar Posner, Anson Lei, Bernhard SchölkopfAI for ScienceWorld Models

  2. PanoWorld: Real-World Panoramic Generation

    Jul 10, 2026Haoyuan Li, Dizhe Zhang, Yuemei Zhou +7World Model LearningWorld Models

  3. Causally Debiased Latent Action Model for Embodied Action Conditioned World Models

    Jul 10, 2026Yufan Wei, Kun Zhou, Lingjun Mao +9Latent Action LearningCausal Representation Learning

  4. WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving

    Jul 9, 2026Xuerun Yan, Zhexi Lian, Nuoheng Zhang +5End-to-End Autonomous DrivingWorld Models

  5. TouchWorld: A Predictive and Reactive Tactile Foundation Model for Dexterous Manipulation

    Jul 8, 2026Jianyi Zhou, Feiyang Hong, Yunhao Li +9Dexterous ManipulationLong-Horizon Robotic Manipulation

  6. RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

    Jul 7, 2026Haoyu Zhao, Xingyue Zhao, Siteng Huang +3Language-Conditioned Robot ManipulationBimanual Robotic Manipulation

  7. A Definition and Roadmap for World Models

    Jul 7, 2026Xinyuan Chen, Haoyu Guo, Shi Guo +10World Model LearningWorld Models

  8. Imagined Rollouts are Kinematic, Not Dynamic: A Diagnosis of Long-Horizon World-Model Failure

    Jul 7, 2026Finn Rasmus Schäfer, Korbinian Moller, Yuan Gao +3World ModelsWorld Model Evaluation

  9. Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models

    Jul 6, 2026Hongyu Li, Wanjia Fu, Xiaoyan Cong +11World ModelsDeformable Object Manipulation

  10. Object-Centric Environment Modeling for Agentic Tasks

    Jul 3, 2026Yiyang Li, Tianyi Ma, Zehong Wang +2Continual Learning for LLM AgentsWorld Models

  11. PWM-ArtGen: Part World Model for Articulated Object Generation

    Jul 2, 2026Wentao Zheng, Ancong WuPart-Level 3D Generation3D Asset Generation

  12. PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation

    Jul 2, 2026Peng Yun, Shouwang Huang, Hao Li +3World Models for RoboticsWorld Models

  13. OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3

    Jul 1, 2026David Courtis, Wenhao Li, Scott SannerWorld Model LearningWorld Models

  14. Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments

    Jul 1, 2026Jinwoo Jang, Daniel J. Rho, Sihyung Yoon +2World Model LearningWorld Models

  15. Delta-JEPA: Learning Action-Sensitive World Models via Latent Difference Decoding

    Jun 30, 2026Zhenghao Zhang, Yuanxiang Wang, Zhenyu Guan +11World ModelsWorld Model-Based Planning

  16. ForgeDrive: Bidirectional Cross-Conditioning for Unified Visual-Action Generation in Autonomous Driving

    Jun 30, 2026Xuchang Zhong, He Zheng, Chenxu Zhao +8Diffusion-Based PlanningWorld Models

  17. Self-Evolving World Models for LLM Agent Planning

    Jun 29, 2026Xuan Zhang, Wenxuan Zhang, See-Kiong Ng +1Test-Time AdaptationWorld Model Learning

  18. Situation Perception: A Necessary Primitive to Artificial Superintelligence

    Jun 29, 2026Ziqin Yuan, Jaymari ChuaWorld ModelsArtificial General Intelligence

  19. OWMDrive: Causality-Aware End-to-End Autonomous Driving via 4D Occupancy World Model

    Jun 29, 2026Junjie Cheng, Ruiqi Song, Ye Wu +3Causal World ModelsEnd-to-End Autonomous Driving

  20. FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation

    Jun 29, 2026Lingfeng Zhang, Zeying Gong, Xiaoshuai Hao +7World ModelsVision-Language Navigation

  21. J-LAW: Joint Localization and Action-Conditioned World Modeling via Coupled Latent Factor Graphs

    Jun 27, 2026Guanqun Cao, Liang ChenSimultaneous Localization and MappingFactor Graph Optimization

  22. Agentic vs. Parametric World Models: Hybrid Planning for Reliable Language Agents

    Jun 26, 2026Xinyuan Song, Zekun CaiWorld ModelsWorld Model-Based Planning