@inproceedings{wang2025co-evolving,
author = {Wang, Yucen and Zhang, Feng and Zhan, De-Chuan and Zhao, Li and Wang, Kaixin and Bian, Jiang},
title = {Co-Evolving Latent Action World Models},
booktitle = {ICML 2026},
year = {2025},
month = {October},
abstract = {Adapting pretrained video generation models into controllable world models via latent actions is a promising step towards creating generalist world models. The dominant paradigm adopts a two-stage approach that trains latent action model (LAM) and the world model separately, resulting in redundant training and limiting their potential for co-adaptation. A conceptually simple and appealing idea is to directly replace the forward dynamic model in LAM with a powerful world model and training them jointly, but it is non-trivial and prone to representational collapse. In this work, we propose CoLA-World, which for the first time successfully realizes this synergistic paradigm, resolving the core challenge in joint learning through a critical warm-up phase that effectively aligns the representations of the from-scratch LAM with the pretrained world model. This unlocks a co-evolution cycle: the world model acts as a knowledgeable tutor, providing gradients to shape a high-quality LAM, while the LAM offers a more precise and adaptable control interface to the world model. Empirically, CoLA-World matches or outperforms prior two-stage methods in both video simulation quality and downstream visual planning, establishing a robust and efficient new paradigm for the field.},
url = {http://approjects.co.za/?big=en-us/research/publication/co-evolving-latent-action-world-models/},
}