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. JailWAM: Jailbreaking World Action Models in Robot Control

    Apr 7, 2026Hanqing Liu, Songping Wang, Jiahuan Long +9Jailbreak AttacksRobot Safety

  2. Enhancing Policy Learning with World-Action Model

    Mar 30, 2026Yuci Han, Alper YilmazRobot Policy LearningWorld Action Models

  3. Do World Action Models Generalize Better than VLAs? A Robustness Study

    Mar 23, 2026Zhanguang Zhang, Zhiyuan Li, Behnam Rahmati +11World Action ModelsRobustness of VLAs

  4. Fast-WAM: Do World Action Models Need Test-time Future Imagination?

    Mar 17, 2026Tianyuan Yuan, Zibin Dong, Yicheng Liu +1World Action ModelsEfficient Inference for World Action Models

  5. World Action Models are Zero-shot Policies

    Feb 17, 2026Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng +33World Action ModelsZero-Shot Robotic Manipulation