Overview

World models learn to predict what will happen when a robot acts, giving it a way to plan ahead, learn from imagined experience, and reduce costly or risky real-world trials. Approaches range from latent-dynamics models such as JEPA and Dreamer, often paired with model-predictive control or reinforcement learning, to video-based world-action models that predict future observations alongside executable actions. Researchers also add structure—3D geometry, object-centric states, physics, memory, and tactile or force signals—to handle contact, navigation, and long-horizon tasks. A central challenge is that visually convincing predictions may not follow actions faithfully or support reliable control; balancing physical consistency, robustness, evaluation quality, and inference speed remains open.

Latest papers

CardsList

426 papers51 papers in the last four weeks, down 46% on the four weeks before. 0.4% of all new papers.

  1. Schrödinger's Navigator: Imagining an Ensemble of Futures for Zero-Shot Object Navigation

    Dec 24, 2025Yu He, Da Huang, Zhenyang Liu +53D Scene PredictionRobot Navigation

  2. Action-Guided Reachability for Deterministic World Models of Vision-Based Systems

    Dec 8, 2025Yuang Geng, Zhongzheng Zhang, Chengzhen Jiang +4Reachability AnalysisFormal Verification

  3. From Discrete Plans to Real-World Execution: A World-Model-Driven Framework for Execution-Aware Multi-Agent Path Finding

    Nov 26, 2025Jingtian Yan, Shuai Zhou, He Jiang +2Multi-Robot Motion PlanningWorld Models for Robotics

  4. Semantic World Models

    Oct 22, 2025Jacob Berg, Chuning Zhu, Yanda Bao +2World Models for RoboticsWorld Model-Based Planning

  5. A Comprehensive Survey on World Models for Embodied AI

    Oct 19, 2025Xinqing Li, Xin He, Le Zhang +3World Model LearningWorld Models for Robotics

  6. RoDyn: Taming Interactive Robot-Dynamic 2.5D World Model for Robotic Manipulation

    Oct 10, 2025Chuanrui Zhang, Zhengxian Wu, Guanxing Lu +2World Models for RoboticsWorld Models