让AI世界随你动：从第一人称到上帝视角
你玩VR游戏时，只能看到自己的手，身体在哪全靠猜。这篇论文让AI模拟的世界不再有这种盲区：它用3D人体动作作为交互方式，同时引入一个“上帝视角”的辅助训练，让模型能看到你全身的位置和动作，从而更准确地理解人与环境的互动。更酷的是，你可以在一个统一的世界坐标系里定义“锚点视角”，配合文字描述，让局部场景按你的想法动态演变——比如指定“这面墙会随时间裂开”。实验证明，这种定制方案能保持时空几何一致性，严格遵循你设定的演化规则。虽然它不是你明天就能用的产品，但为未来更沉浸、更可控的虚拟世界（如VR游戏、数字孪生）铺平了道路。
📄 原文摘要(英文)
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.