alphaXiv(@askalphaxiv):“OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining” World–Action Models inherit dynamics priors from video models, but it was unclear how to convert them into effective control. This paper shows the real gain comes from coupling world prediction with action generation, and that large-scale embodied pretraining mainly improves OOD generalization rather than in-domain fitting.

2026.09.14 01:22

“OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining” World–Action Models inherit dynamics priors from video models, but it was unclear how to convert them into effective control. This paper shows the real gain comes from coupling world prediction with action generation, and that large-scale embodied pretraining mainly improves OOD generalization rather than in-domain fitting.