Overview

World model learning studies how agents can represent a changing environment and predict what may happen next, especially after an action. Common approaches include latent-state models such as RSSMs and JEPAs, video diffusion models, and structured representations based on objects, graphs, geometry, physics, or executable rules. These models are used for imagined rollouts and planning in settings such as robot manipulation, autonomous driving, games, and web or GUI agents, as well as for scientific forecasting and simulation. A central challenge is that strong one-step or visual predictions do not guarantee useful decisions: long-horizon consistency, action accuracy, uncertainty, and transfer to unfamiliar settings remain difficult to balance with computational cost.

Latest papers

CardsList

463 papers56 papers in the last four weeks, down 40% on the four weeks before. 0.4% of all new papers.

  1. World Models Favor Learned Priors over Visual Evidence

    Nov 19, 2026Han Xiao, Zhiyong Bao, Xiaotong Liu +2World Model LearningVideo World Models

  2. Identity World Model: Recognizing People in an Imagined Latent World

    Nov 18, 2026Dingqiang Ye, Kartik Narayan, Vishal M. PatelPerson Re-IdentificationWorld Model Learning

  3. Phoenix: Learning Scene Structure Representations for Generalizable World-Action Models

    Nov 18, 2026Yupeng Zheng, Chaoyue Li, Linbo Wang +15World Model LearningWorld Action Models

  4. PsyWorld: Profile-Conditioned World Modeling for Human Behavior Prediction

    Nov 18, 2026Ziyuan Qin, Yang Qiao, Summer B. Frandsen +2Human Behavior ModelingHuman Behavior Prediction

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

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

  6. Distilling World Action Models for Efficient Bimanual Manipulation via Anchored Path Matching

    Nov 17, 2026Jialong Liu, Junjie He, Yandu Chen +5Diffusion Model DistillationEfficient Inference for World Action Models

  7. 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

  8. Towards Data-Efficient, Real-Time World Models

    Nov 17, 2026Raluca Stevenson, David Bignell, Jennifer C. White +9World Model LearningGame World Models

  9. DiffWAM: Learning World Action Model from Consecutive Visual Difference

    Nov 15, 2026Xinheng Zhang, Haoyu Xiong, Chao Jing +4World Model LearningWorld Models for VLAs

  10. The Flip Test: Video World Models Fail to Learn the World State

    Nov 15, 2026Mi Luo, Lijun Yu, Adams Wei Yu +10Video World ModelsWorld Model Learning

  11. ResWAM: Learning What Changes, Not What Stays, for World-Action Models

    Nov 14, 2026Chongyu Fan, Gaowen Liu, Ramana Rao Kompella +2World Action ModelsWorld Models for VLAs

  12. WeatherDreamer: Learning a World Model from Multimodal Earth Observations

    Nov 13, 2026Kate Duffy, Elise Penn, Tristan Ballard +2Weather ForecastingWorld Model Learning

  13. Joint World Action Models through Differentiable Trajectory Optimization

    Nov 13, 2026Mintae Kim, Koushil SreenathWorld Action ModelsTrajectory Optimization

  14. TyphoonWorld: A Residual Token World Model for Probabilistic Forecasting of Typhoon Imagery

    Nov 11, 2026Xiaoyu Chen, Tianyi Li, Xuanyi ZhangProbabilistic ForecastingWeather Forecasting

  15. Few-Shot Residual Adaptation of Pretrained Latent World Models

    Nov 10, 2026Jakub Suliga, Pankhuri Vanjani, Nisarga Nilavadi +2Latent World ModelsWorld Models for Robotics

  16. Building World Models from Intrinsic Motivation

    Nov 9, 2026Reece Keller, Declan Kutscher, Xaq Pitkow +1Intrinsic MotivationWorld Model Learning

  17. ΣΣ-LeWM: Learning World Models via S-Information for Robot Control

    Nov 9, 2026Xinrui Zu, Michael Przystupa, Zhao Yang +2World Model LearningLatent World Models

  18. How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test Time

    Nov 9, 2026Ku Onoda, Haruto Kawano, Shota Takashiro +1Game World ModelsWorld Model Learning

  19. An Evaluation of Tabular Foundation Models as Training-Free World Models

    Nov 9, 2026Xian Yeow Lee, Ryoichi Takase, Ahmed FarahatWorld Model LearningWorld Models for Robotics

  20. How Many Candidates Does a One-Step World Model Need? A Random-Codebook Account of Nearest-of-m Training on Frozen DINO Tokens

    Nov 9, 2026Yong Hwi Song, Keon Myung LeeWorld Model LearningOne-Step Generative Modeling

  21. K-PWM: Control-Oriented Structured Bilinear World Models under Partial Observation

    Nov 8, 2026Santosh Mohan Rajkumar, Sriram Narayanan, Samuel E. Otto +1World Model LearningPartially Observable Markov Decision Processes

  22. Breaking survivorship bias in driving world models

    Nov 8, 2026Zihao Sheng, Zilin Huang, Yuhao Luo +5World Model LearningWorld Models for Autonomous Driving

  23. SurgWorld: Learning Surgical Representations Beyond Observation via Latent Prediction

    Nov 8, 2026Jingkun Yue, Pengxiang Wang, Siqi Zhang +7Surgical Video UnderstandingVideo Representation Learning

  24. ObjectWorld: Scaling Object-Centric World Models with A Large-Scale 3D Full-Object Flow Dataset

    Nov 8, 2026Haonan Chen, Sicheng Isabella Lu, Haitian Li +9World Models for RoboticsWorld Model Learning

  25. Tiresias: Towards Language-Conditioned World Models

    Nov 7, 2026Fengyi Wu, Yifei Dong, Yetong Sha +6World Model-Based PlanningWorld Model Learning

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

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

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

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