Video Prediction Policy 2: Predict Better, Act Better
World action models (WAMs) have emerged as an important class of generalist robot policies, aiming to transfer video prediction priors to action learning. However, we find that existing WAMs frequently produce incorrect motion predictions in open-ended environment, leading to erroneous actions. We attribute this limitation to two factors: (1) base video models are not optimized for manipulation, and (2) naively incorporating action components into video models can substantially degrade their generalization capabilities. We introduce Video Prediction Policy 2 (VPP2), a WAM that enables strong zero-shot generalization in both video prediction and action generation. First, we curate a large-...
| Authors | Yanjiang Guo, Haodong Yan, Zhide Zhong et al. |
|---|---|
| Primary category | cs.CV |
| Published | 7 October 2026 |
| Last updated at source | 13 October 2026 |
Connected in the knowledge graph
- Haodong082399/VPP2Model · cited by
Models and datasets referencing this paper
- Haodong082399/VPP2Model
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 16 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.