Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets

By toyota research institute.

This is a first look thinking about how we unify world models and VLAs.

Citation

(Zhu et al., 2025)

Zhu, C., Yu, R., Feng, S., Burchfiel, B., Shah, P., & Gupta, A. (2025). Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets. https://arxiv.org/abs/2504.02792