cs.RONov 11, 2026

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

Authors: Chenhao Qiu, Shuyi Chen, Songen Gu, Shufeng Nan, Tianyu Wang, Siyu Lin, Yifan Li, Bingwen Zhu, 

Organizations: Fudan University · ROBOTOPIA · Tongji University · Shanghai Innovation Institute

Abstract

World Action Models (WAMs) can improve robot learning by jointly predicting future visual states and actions, but generating a visual future at every replanning step is expensive and sometimes unnecessary. This raises a critical question: when should a robot policy imagine the future? In this paper, we propose Bind-WAM, a binding-uncertainty-guided WAM for selective future imagination. Bind-WAM introduces language-object binding uncertainty, selectively invoking joint future-action generation when the current observation does not support stable task-relevant action generation. An offline labeling pipeline uses complete demonstrations and action context to identify task-relevant objects and detect reference mismatch, invisibility, and identity drift. The resulting pseudo-labels supervise a lightweight router that predicts binding uncertainty from the current observation and language instruction. At inference, a shared WAM policy invokes selective future imagination according to the predicted uncertainty and its change between consecutive replanning steps. Simulation and real-world experiments demonstrate that Bind-WAM can establish binding uncertainty as a strong, interpretable signal for selective future imagination.

Figures & tables

Explore similar work

CardsList
  1. World-Action Models for Robot Learning and Control: A Survey

    Sep 13, 2026Zuxing Lu, Hongjia Zhai, Guanzhi Wang +13World Action ModelsAction-Conditioned World Models

  2. Latent Action as Intention Enables Efficient Future Imagination for World Action Models

    Aug 25, 2026Xiang Li, Yupeng Zheng, Songen Gu +11Latent Action LearningWorld Models for Robotics

  3. When to Trust Imagination: Adaptive Action Execution for World Action Models

    May 7, 2026Rui Wang, Yue Zhang, Canyang Chen +3Long-Horizon Robotic ManipulationWorld Models for Robotics