titleMulti-Agent Egocentric World Model with Fine-Grained Embodied Interaction
authorsDahyun Chung, Siyoon Jin, Hyunwook Choi, Honggyu An, Junyoung Seo, Hyunsung Kim, Seung Wook Kim, Seungryong Kim
date2026-10-08
venuearXiv (preprint, not peer reviewed)
idarXiv:2610.12299
affiliationKAIST AI
upvotes61 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf code
primerWorld models
abstractEgocentric 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.

cite

@misc{chung2026multi,
  title={Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction},
  author={Dahyun Chung and Siyoon Jin and Hyunwook Choi and Honggyu An and Junyoung Seo and Hyunsung Kim and Seung Wook Kim and Seungryong Kim},
  year={2026},
  eprint={2610.12299},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2610.12299}
}