Overview

World Action Models (WAMs) learn policies alongside predictions of future observations or task-relevant states, aiming to make control account for physical consequences. Approaches range from joint video-and-action diffusion and inverse-dynamics models to compact latent, geometric, object-centric, tactile, and motion representations, trained with robot demonstrations, human video, or synthetic data. On manipulation benchmarks such as LIBERO and RoboTwin and driving tests such as NAVSIM, many methods use future prediction as training supervision or compact guidance instead of generating full video at every step. A central challenge is ensuring imagined futures are causally aligned with actions and useful under distribution shifts, while keeping inference fast and light enough for closed-loop deployment.

Latest papers

CardsList

247 papers32 papers in the last four weeks, down 58% on the four weeks before. 0.2% of all new papers.

  1. WAMotor: Accelerating World Action Models via Speculative Inference under Dual Nonuniform Denoising Dynamics

    Nov 19, 2026Zexun Lin, Yuan Feng, Xike XieEfficient Inference for World Action ModelsWorld Action Models

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

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

  3. HINT-WAM: Hindsight-Informed Training for World Action Models

    Nov 18, 2026Phuong Tuan Dat, Qi Li, Xinchao WangWorld Action ModelsRobotic Manipulation

  4. EgoHandWAM: Probing the Role of Hand Motion in Egocentric World Action Modeling

    Nov 17, 2026Kailin Wang, Haoxiang Jie, Yaoyuan Yan +2World Action ModelsHuman Motion Prediction

  5. 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

  6. Joint World Action Models through Differentiable Trajectory Optimization

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

  7. Bind-WAM: Binding-Uncertainty-Guided Selective Future Imagination in World Action Models

    Nov 11, 2026Chenhao Qiu, Shuyi Chen, Songen Gu +6World Action ModelsWorld Models for VLAs

  8. From Video Frames to Robot Meta-Frames: A Unified Latent Interface for World Action Models

    Nov 10, 2026Guoqiang Liang, Yiqi Lin, Yanzhe Chen +2World Action ModelsWorld Models for VLAs

  9. LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning

    Nov 10, 2026Xuheng Zhang, Yiming Zhang, Jialin Gao +14World Models for RoboticsWorld Action Models

  10. SWAM: Scaling World Action Models with Cross-Modal Alignment

    Nov 9, 2026Yu Zhou, Xinyuan Xia, Xuankun Yang +8World Action ModelsVLA Training

  11. BAT-WAM: Bridging Action and Touch in World-Action Models for Dexterous Hands

    Nov 7, 2026Dong Fang, Feixuan Huang, Yuanxin Zhong +5Robotic ManipulationTactile World Models

  12. La-JEPA: Compact Robot Policies with Latent World Modeling

    Nov 5, 2026Mateo Clémente, George Z. Xue, Amin Abyaneh +5Robot Policy LearningWorld Action Models

  13. Reinforcing End-to-End Autonomous Driving Safety via Negative-Aware Planning in a Unified World-Action Model

    Nov 5, 2026Zihao Zhang, Xinyu Zhang, Bing Zeng +4End-to-End Autonomous DrivingWorld Action Models

  14. Spatial-UMI-Dream: Scaling World Action Models with Metric Geometry for UMI Manipulation

    Nov 4, 2026Weiduo Yuan, Ze Yuan, Sihan Liu +4World Models for RoboticsWorld Action Models

  15. HiLo-WAM: Decoupling Long-Horizon Task Evolution and Local Dynamics in World Action Models

    Nov 3, 2026Xingyu Wang, Yanjiang Guo, Zhijing Ding +7World Action ModelsWorld Models for Robotics

  16. Coordinating Humanoid Loco-Manipulation through Action-Conditioned Latent Foresight

    Nov 3, 2026Ju Dong, Xinyu Xiao, Yiming Zhou +12Robotic Loco-ManipulationWorld Action Models

  17. Cycle WAM: Coupling Action and Video through Cycle Consistency

    Nov 3, 2026Qinglin Yang, Jiepeng Wang, Yuxing Huang +5World Action ModelsAction-Conditioned Video Generation

  18. W2A: Distilling World Priors into Action Models for Real-Time Robotic Control

    Nov 2, 2026Xiaopeng Zhang, Yongjin Mu, Yueyang Weng +2World Action ModelsReal-Time Robot Control

  19. Gnomon4D: Learning Where and When to Focus for Geometric Motion-Grounded World-Action Modeling

    Nov 2, 2026Lingwei Dang, Yan Zhou, Juntong Li +10World Action ModelsRobot Learning from Video

  20. RoboSeed: Multidimensional Evaluation of Vision-Language-Action and World-Action Models: Capability, Resource Affordability, and Research Evidence

    Oct 29, 2026Xin Ma, Furong Chen, Xinlong Man +9Robot Foundation ModelsWorld Action Models

  21. Utility-WAM: Correcting Future-Induced Action Changes

    Oct 29, 2026Feihong Zhang, Xi Lin, Yulong Shi +7World Action ModelsWorld Models for VLAs

  22. Vision-Language-Action or World-Action? Just Action Models

    Oct 27, 2026Yonghao Yu, Lang Huang, Runyi Li +1VLA TrainingWorld Action Models

  23. TurboWAM: Learning What Matters for Fast World Action Models

    Oct 24, 2026Guile Wu, Shuangzhi Li, Xingxin Chen +5Efficient Inference for World Action ModelsWorld Action Models