| title | AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization |
|---|---|
| authors | Yu Li, Menghan Xia, Gongye Liu, Xintao Wang, Conglang Zhang, Lei Ke, Yuxuan Lin, Ruihang Chu, Pengfei Wan, Kun Gai, Yujiu Yang |
| date | 2026-06-05 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.07326 |
| affiliation | KlingAI Research |
| upvotes | 30 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Despite being a pivotal frontier, interactive world modeling remains underexplored in terms of the versatile controllability required by practical scenarios. To bridge this gap, we present AnchorWorld, a framework that advances egocentric simulation through enhanced interaction integrity and a flexible mechanism for world customization. First, we utilize 3D human motion as the primary interaction modality. To complement the out-of-view or truncated body parts in egocentric views, we introduce an auxiliary training supervision that incorporates exogenous viewpoints decoupled from the agent's first-person sensorium. It allows the model to observe the agent's full-body positioning relative to the environment, facilitating a more robust spatial grounding of human-world interactions. Furthermore, we propose a simple yet effective mechanism for customizing self-evolving worlds. This is achieved by defining anchor views within a unified world coordinate system, coupled with textual descriptions dictating the dynamic evolution of local scenes. Experimental results show that AnchorWorld significantly outperforms state-of-the-art baselines, while ablation studies validate the effectiveness of our key designs. Notably, our customization scheme exhibits promising spatio-temporal geometric consistency and adheres strictly to the prescribed evolutionary dynamics. |
cite
@misc{li2026anchorworld,
title={AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization},
author={Yu Li and Menghan Xia and Gongye Liu and Xintao Wang and Conglang Zhang and Lei Ke and Yuxuan Lin and Ruihang Chu and Pengfei Wan and Kun Gai and Yujiu Yang},
year={2026},
eprint={2606.07326},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.07326}
}