English

MWM: Mobile World Models for Action-Conditioned Consistent Prediction

Computer Vision and Pattern Recognition 2026-03-10 v1 Robotics

Abstract

World models enable planning in imagined future predicted space, offering a promising framework for embodied navigation. However, existing navigation world models often lack action-conditioned consistency, so visually plausible predictions can still drift under multi-step rollout and degrade planning. Moreover, efficient deployment requires few-step diffusion inference, but existing distillation methods do not explicitly preserve rollout consistency, creating a training-inference mismatch. To address these challenges, we propose MWM, a mobile world model for planning-based image-goal navigation. Specifically, we introduce a two-stage training framework that combines structure pretraining with Action-Conditioned Consistency (ACC) post-training to improve action-conditioned rollout consistency. We further introduce Inference-Consistent State Distillation (ICSD) for few-step diffusion distillation with improved rollout consistency. Our experiments on benchmark and real-world tasks demonstrate consistent gains in visual fidelity, trajectory accuracy, planning success, and inference efficiency. Code: https://github.com/AIGeeksGroup/MWM. Website: https://aigeeksgroup.github.io/MWM.

Keywords

Cite

@article{arxiv.2603.07799,
  title  = {MWM: Mobile World Models for Action-Conditioned Consistent Prediction},
  author = {Han Yan and Zishang Xiang and Zeyu Zhang and Hao Tang},
  journal= {arXiv preprint arXiv:2603.07799},
  year   = {2026}
}
R2 v1 2026-07-01T11:09:24.965Z