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

Chenhao Qiu, Shuyi Chen, Songen Gu, Shufeng Nan, Tianyu Wang, Siyu Lin, Yifan Li, Bingwen Zhu, Yanwei FuarXiv 2026 · arXiv

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.
BibTeX
@misc{qiu2026bind,
  author = {Chenhao Qiu and Shuyi Chen and Songen Gu and Shufeng Nan and Tianyu Wang and Siyu Lin and Yifan Li and Bingwen Zhu and Yanwei Fu},
  title = {{Bind-WAM: Binding-Uncertainty-Guided Selective Future Imagination in World Action Models}},
  year = {2026},
  eprint = {2611.15368},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.15368},
}

Loading related content...

Figure