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. Render the Robot, Generate the World: One Video World Model Across Embodiments

    Nov 18, 2026Yash Jangir, Karan Mirakhor, Renos Zabounidis +4World Models for RoboticsWorld Models

  2. WM^MLLM: Turning MLLMs into World Models

    Nov 18, 2026Baiang Li, Enze Xie, Jincheng Yu +5World ModelsInteractive World Models

  3. Embodied Graph: A Relational World Model for Long-Horizon Tasks

    Nov 18, 2026Zongyuan Wu, Xin Wang, Tongtong Feng +4World Model LearningWorld Models

  4. MitoWorld: A Stochastic World Model of the Single-Cell Cycle under Genetic Perturbation

    Nov 18, 2026Ting Long, Xiaojing Sun, Cheng Han +5Single-Cell Perturbation ModelingWorld Models

  5. Evolve in Panorama, Render in View: Panoramic World State Evolution for Video World Models

    Nov 17, 2026Longtao Jiang, Mingfei Han, Jianmin Bao +7World ModelsVideo World Models

  6. JointGV: Structure-Aware Correction of Visual World Models with Parallel Graph Dynamics for Long-Horizon Modeling

    Nov 17, 2026Tian Lyu, Yichen Jiang, Ziyuan Cheng +7World Models for RoboticsWorld Models

  7. WM-Quant: Rollout-Aware Post-Training Quantization for JEPA-Style World Models

    Nov 16, 2026William Hammer, Andrew Heuer, Nikhil Krishna +2Post-Training QuantizationWorld Models

  8. Recovered or Memorized? Investigating Dynamical Consistency and Faithfulness in World Model Latents

    Nov 13, 2026Jerome Francisco, Kyle Deng, George Flint +1World ModelsLatent World Models

  9. Dynamics-Informed Action Learning for Goal-Conditioned Latent Planning

    Nov 7, 2026Yinuo Jiang, Guangzhi Wang, Yiran Wang +5Latent-Space PlanningGoal-Conditioned Planning

  10. The World Model Planning Accelerator (WMPA): Hardware-Algorithm Co-Design for Embedded AI in Robotics

    Nov 6, 2026Prerana Ramkumar, Suhas Suresh Bharadwaj, Fazal HameedWorld Model-Based PlanningWorld Models

  11. Learning a patient world model for health system simulation in intensive care

    Nov 5, 2026Yingtai Li, Ruoyan Wang, Yu Li +1World ModelsWorld Model Learning

  12. GPWM: Modeling the World as 3D Particle Motion

    Nov 5, 2026Robert Ren, Matthew Bronars, He Zhu +5World Model LearningWorld Models

  13. PlayGen2: Learning Real-Time Playable Worlds with Explicit 3D State

    Nov 5, 2026Jihai Zhang, Yuhan Zhou, Junyou Li +3Game World ModelsVideo Games

  14. Detecting Silent Action-Interface Mismatch with Calibrated Relational World Models

    Nov 4, 2026Rui Zhu, Xurui Li, Haixu TangRobotic Anomaly DetectionWorld Models

  15. MKD2World: A Typed Spatial MarkDown World Model For Web Agents

    Nov 4, 2026Zhihao Nan, Sifan Zhou, Yiming Cheng +5World Model LearningWorld Models

  16. Compression Forcing: Hierarchical History Tokenization Enables Flexible World Models

    Nov 2, 2026Siqiao Huang, Partha Kaushik, Michael Chen +5World Model LearningWorld Models

  17. Toward Uncertainty-Aware, Physics-Grounded Human World Models

    Nov 2, 2026Yufei Zhang, Zijun CuiWorld ModelsHuman Motion Prediction

  18. Predictive Safety Guardrails Do Not Always Make LLM Agents Safer

    Nov 2, 2026Weixiang Zhao, Zhihao Liu, Guancheng Li +3LLM Agent SafetySafety Filtering

  19. Human-Oriented World Model

    Nov 2, 2026Saihui Hou, Zengyun Mou, Chunshui Cao +1World ModelsHuman Behavior Modeling

  20. OpenNWM: A Generalist Navigation World Model with Latent Action Pretraining

    Nov 1, 2026Dujun Nie, Ruiqi Song, Zixuan Wang +6World Model LearningRobot Navigation

  21. Why Koopman Structure Does Not Help Differentiable World Models for Humanoid Whole-Body Tracking

    Oct 31, 2026Haizhou Ge, Mengshuo Wang, Yufei Jia +4World Models for RoboticsWorld Models

  22. Roz: A Taste Test for World Model Latents

    Oct 31, 2026Kenneth Ge, Dhruv Sheth, Kunvar ThamanWorld Model EvaluationWorld Models

  23. SPT-Flow: One Integration, Many Futures in Continuous-Time World Models

    Oct 30, 2026Mingyang Lyu, Yinqian Sun, Gongce Cao +5World Model LearningWorld Models

  24. world2vec: Mechanistic world models through latent dynamics learning

    Oct 29, 2026Tobias Schmidt, Rodrigo Gonzalez Laiz, Krisztián Szuppinger +1World Model LearningWorld Models

  25. Fight World Model: Customizable Combat through Visual Interaction Proxies

    Oct 29, 2026Jiahua Li, Zixu John, Tom Zhong +5Game World ModelsInteractive World Models