World Action Models are Zero-shot Policies
State-of-the-art Vision-Language-Action (VLA) models excel at semantic generalization but struggle to generalize to unseen physical motions in novel environments. We introduce DreamZero, a World Action Model (WAM) built upon a pretrained video diffusion backbone. Unlike VLAs, WAMs learn physical dynamics by predicting future world states and actions, using video as a dense representation of how the world evolves. By jointly modeling video and action, DreamZero learns diverse skills effectively from heterogeneous robot data without relying on repetitive demonstrations. This results in over 2x improvement in generalization to new tasks and environments compared to state-of-the-art VLAs in r...
| Authors | Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng et al. |
|---|---|
| Primary category | cs.RO |
| Published | 17 February 2026 |
| Last updated at source | 17 February 2026 |
Connected in the knowledge graph
- GEAR-Dreams/DreamZero-DROIDModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.