arXiv cs.AI· Dahyun Chung, Siyoon Jin, Hyunwook Choi, Honggyu An, Junyoung Seo, Hyunsung Kim, Seung Wook Kim, Seungryong Kim·· 9 天前AI 评分22
ME-World：细粒度具身交互的多智能体自我中心世界模型
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction
AI 导读
研究者提出多智能体自我中心世界模型 ME-World，将多智能体自我中心世界建模定义为多个智能体通过细粒度动作在共享世界中交互的同步自我流生成。该方法在共享 token 序列中联合去噪多条自我流，以所有智能体的目标视角位姿为条件，并用共享环境记忆约束生成，同时提出环境、更新与身份一致性指标。实验显示 ME-World 在共享世界一致性、动作控制、身份保持和视频质量上优于现有方法。
正文 · 原文
Abstract:Egocentric world models predict first-person observations conditioned on an agent's actions, but most focus on a single agent. Real embodied settings often involve multiple agents that act and interact within a shared environment. Existing multi-agent world models rely on coarse actions like locomotion, camera control, or discrete commands, leaving fine-grained embodied interactions underexplored. We formulate multi-agent egocentric world modeling as synchronized ego-stream generation for multiple agents interacting through fine-grained actions in a shared world. This requires cross-view action consistency, shared-environment consistency, and consistent propagation of interaction-induced state updates. We propose Multi-agent Egocentric World Model (ME-World), which jointly denoises multiple ego streams in a shared token sequence, conditions each stream on all agents' target-view poses, and grounds generation with shared environment memory. We train and evaluate on real and synthetic multi-agent data and introduce shared-world consistency metrics for environment, update, and identity consistency. Experiments show ME-World improves shared-world consistency, action control, identity preservation, and video quality over existing methods.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.12299 [cs.CV] |
| (or arXiv:2610.12299v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12299 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dahyun Chung [view email]
[v1]
Thu, 8 Oct 2026 16:50:04 UTC (12,706 KB)
来源：arXiv cs.AI · arxiv.org