Overview

Causal world models aim to represent not only what a scene looks like, but how entities and environments change under actions, so agents can plan and answer what-if questions. Methods range from structural causal graphs and object-centric latent dynamics to video-prediction models trained with paired interventions, counterfactual rollouts, or physical constraints. They are tested in simulated physics and manipulation, driving and navigation, and video benchmarks that compare factual futures with altered-action outcomes. Models increasingly improve action control and intervention prediction, but plausible video is not necessarily causally correct: learning effects from limited interventions while retaining factual accuracy and generalizing across settings remains difficult.

Latest papers

CardsList

51 papers5 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.

  1. Counterfactual World Models: JEPAs That Reason About "What If"

    Nov 18, 2026Randall Balestriero, Yann LeCun, Kerda VarakuCounterfactual PredictionCausal World Models

  2. A research world model of power engineering learns its dynamics and reveals what-ifs

    Nov 3, 2026Fanping Sui, Ying Zhang, Liwei LinCausal World Models

  3. Causal world models under physical parameter shifts

    Oct 21, 2026Chu Lin, Yi SunCausal World ModelsWorld Models for Robotics

  4. CaMeWM: A Causal Medical World Model for Generative Tumor Evolution and Treatment Planning

    Oct 17, 2026Huanlong Gao, Xuelei He, Fengjun Zhao +1Causal World ModelsCausal Counterfactual Generation

  5. A Plausible Future Is Not a Causal Future: Can Video Models Generate How the World Unfolds?

    Oct 11, 2026Jialiang Li, Zhengning Xu, Zongyang Ma +1Causal Video GenerationVideo Generation

  6. CAG-WAM: Causal Action-Gain World Action Models for Robot Manipulation

    Oct 10, 2026Peizheng Guo, Cheng Zhang, Xingyu Zhang +2Action-Conditioned World ModelsRobotic Manipulation

  7. CausalDreamer: Learning Predictive World Models with Latent Disentanglement

    Oct 8, 2026Prince Jha, Nils Lukas, Kun Zhang +1World Model LearningCausal World Models

  8. Same Predictions, Different Harms: Causal Auditing of Patient World Models

    Oct 4, 2026Yicheng Qi, Xiyi XiongStructural Causal ModelsCausal World Models

  9. Do-JEPA: From Masking to Intervention in Latent World Models

    Sep 29, 2026Hossein Resani, Javen Qinfeng ShiCausal Effect EstimationCausal World Models

  10. World Agent: Can Language Models Keep a World Running?

    Sep 26, 2026Weixing Chen, Weipeng Zhang, Nan An +2World Model EvaluationWorld Models

  11. Stable and Counterfactually Robust Physical World Models from Imposed Structure and Learned Physics

    Sep 24, 2026Yufeng Wang, Parivesh Priye, Lu Wei +1World Model LearningPhysics-Informed ML

  12. What Matters in Designing World Action Models: An Empirical Study

    Sep 21, 2026Chao Tang, Haoqing Wang, Zilang Cen +9World Model LearningCausal World Models

  13. OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling

    Sep 20, 2026Yikun Miao, Fangqi Zhu, Quanxin Shou +6World Model LearningCausal World Models

  14. CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model

    Sep 19, 2026Ziming Xu, Shuang Liang, Ruobing Han +10Causal World ModelsAction-Conditioned World Models

  15. Compact but Moving: Intervention-Relevant Geometry in Recurrent World Models

    Sep 18, 2026Yuming Chen, Yang LiuWorld ModelsWorld Model Learning

  16. Converting Sequenced Fuzzy Cognitive Maps to Causal Virtual Worlds with Large Video Generators

    Sep 14, 2026Akash Kumar Panda, Olaoluwa Adigun, Bart KoskoCausal World ModelsFuzzy Cognitive Maps

  17. InfluenceField: A Differentiable Field with Interventionally Identifiable Causal Structure for Multimodal World Modeling

    Sep 7, 2026Zihao Yang, Zijia Wang, Zhiqiu HuangCausal Representation LearningCausal World Models

  18. CST-WM: A Causally Structured World Model for Embodied Visual Tracking

    Sep 5, 2026Junyi Hu, Shuaihang Yuan, Jiazhao Liang +1Causal World ModelsVisual Object Tracking

  19. CAER: Causal Action Effect Reweighting for World Model Training

    Aug 31, 2026Jianjie Fang, Xvyuan Liu, Ziyou Wang +9Action-Conditioned Video GenerationWorld Model Learning

  20. A Unifying Perspective on Causal World Models: From Observations to Representations to Structure

    Aug 13, 2026Avinash Kori, Fabrizio RussoCausal Representation LearningWorld Model Learning

  21. FACT: Failure-Aware Causal Training for World-Action Models

    Aug 10, 2026Quanquan Peng, Yutong Liang, Rui Yan +2Causal World ModelsAction-Conditioned World Models

  22. Compiling VGDL into Causal Models

    Aug 10, 2026Mohit Jiwatode, Bodo Rosenhahn, Alexander DockhornCausal World ModelsStructural Causal Models

  23. CausalNav: Reliability-Certified Causal World Models for Control under Physical-Parameter Shift

    Aug 7, 2026Yiyao Zhang, Diksha Goel, Hussain AhmadCausal World ModelsWorld Models

  24. Learning Implicit Causal World Models from Multi-Agent Demonstrations

    Jul 28, 2026Jasorsi GhoshCausal Representation LearningCausal World Models