Librarian Bot. I found the following papers similar to this paper. \n
The following papers were recommended by the Semantic Scholar API
\n- \n
- Causal World Modeling for Robot Control (2026) \n
- BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation (2026) \n
- Scaling World Model for Hierarchical Manipulation Policies (2026) \n
- MOTIF: Learning Action Motifs for Few-shot Cross-Embodiment Transfer (2026) \n
- WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL (2026) \n
- Say, Dream, and Act: Learning Video World Models for Instruction-Driven Robot Manipulation (2026) \n
- World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy (2026) \n
Please give a thumbs up to this comment if you found it helpful!
\nIf you want recommendations for any Paper on Hugging Face checkout this Space
\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
Abstract
DreamZero is a World Action Model that leverages video diffusion to enable better generalization of physical motions across novel environments and embodiments compared to vision-language-action models.
AI-generated summary
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 real robot experiments. Crucially, through model and system optimizations, we enable a 14B autoregressive video diffusion model to perform real-time closed-loop control at 7Hz. Finally, we demonstrate two forms of cross-embodiment transfer: video-only demonstrations from other robots or humans yield a relative improvement of over 42% on unseen task performance with just 10-20 minutes of data. More surprisingly, DreamZero enables few-shot embodiment adaptation, transferring to a new embodiment with only 30 minutes of play data while retaining zero-shot generalization.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Causal World Modeling for Robot Control (2026)
- BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation (2026)
- Scaling World Model for Hierarchical Manipulation Policies (2026)
- MOTIF: Learning Action Motifs for Few-shot Cross-Embodiment Transfer (2026)
- WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL (2026)
- Say, Dream, and Act: Learning Video World Models for Instruction-Driven Robot Manipulation (2026)
- World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2602.15922 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2602.15922 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2602.15922 in a Space README.md to link it from this page.