MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data
MetaWorld proposes a novel framework to scale multi-agent video world models from single-view videos, addressing data scarcity and world state alignment. It uses Monocular World-State Unrolling (MWSU) to decompose camera ego-motion and subject trajectory, a Subject-Aware World Generator for appearance-driven simulation, and World-State Alignment (WSA) via cross-attention to ensure cross-view consistency. Experiments show superior cross-view consistency and identity fidelity.
[2606.02753] MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data
[Submitted on 1 Jun 2026]
Title:MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data
View a PDF of the paper titled MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data, by Teng Hu and 8 other authors
View PDF HTML (experimental)
Abstract:Video world models are a foundational generative technology for embodied AI and the Metaverse, yet existing approaches are inherently limited to a single agent observing from a single perspective. Extending these models to multi-agent settings introduces two critical challenges: data scarcity (coordinated multi-view recordings are prohibitively expensive to collect for general open-domain scenarios) and world state alignment (independently generated video streams cannot ensure that shared physical environments and events evolve consistently across views). To address these challenges, we propose MetaWorld, a novel framework that scales multi-agent video world models to open-domain environments directly from single-view videos. First, we introduce Monocular World-State Unrolling (MWSU) to explicitly decompose monocular footage into the camera operator's ego-motion and the visible subject's spatial trajectory. This camera-trajectory decomposition naturally extracts synchronized multi-agent motion data within a shared 3D space, completely bypassing the need for multi-camera setups. Second, for precise visual control, we develop the Subject-Aware World Generator to enable appearance-driven simulation conditioned on per-agent identity images. Finally, to ensure both views are grounded in the identical physical reality, we propose World-State Alignment, a per-frame inter-branch cross-attention mechanism inserted at every transformer layer of the video DiT. By jointly synchronizing the denoising process, WSA enforces both static geometric consistency and dynamic motion consistency, encouraging that the shared 3D environment and physical events remain well-aligned across both egocentric views. Extensive experiments demonstrate that MetaWorld achieves superior cross-view consistency and identity fidelity, establishing a highly scalable, physics-driven paradigm for multi-agent video world modeling.
Subjects:
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.02753 [cs.CV]
(or arXiv:2606.02753v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2606.02753
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Teng Hu [view email] [v1] Mon, 1 Jun 2026 18:20:20 UTC (20,651 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data, by Teng Hu and 8 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-06
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)