Kairos：用於物理 AI 的原生世界模型堆疊

摘要

世界模型正从被动的视觉生成器，转变为物理人工智能的基础性、可运行基础设施：它们必须原生地从异构经验中获取世界知识，在长时间跨度内维持持久状态，并在真实部署约束下高效执行。我们提出 Kairos，一个围绕这些需求设计的原生世界模型栈。(1) Kairos 通过开创一种由跨具身数据课程引导的原生预训练范式来学习世界，该范式将开放世界视频、人类行为数据和机器人交互组织成一个渐进式的发展路径。(2) Kairos 通过一个配备混合线性时间注意力的原生统一架构来维护世界，该架构集成了统一的世界理解、生成和预测功能，其中滑动窗口注意力捕捉局部动态，扩张滑动窗口捕捉中程依赖，门控线性注意力维持持久的全局记忆。我们建立了形式化理论边界，证明这种时间分解严格限制了误差累积，从而在数学上保证了跨扩展时间跨度的状态传播。(3) Kairos 通过融入部署感知的系统协同设计来运行世界，以支持在服务器和消费级硬件上进行低延迟的 rollouts 生成，用于真实的观察-行动-反馈循环。在具身世界模型、长时域和行动策略基准上的实验表明，Kairos 实现了顶尖性能，同时在效率与能力之间取得了良好的平衡。这些结果共同将 Kairos 定位为未来自进化物理智能的一个统一运行基础。

English

World models are transitioning from passive visual generators to foundational, operational infrastructure for Physical AI: they must natively acquire world knowledge from heterogeneous experience, maintain persistent states over long horizons, and execute efficiently within real deployment constraints. We introduce Kairos, a native world model stack designed around these requirements. (1) Kairos learns the world by pioneering a Native Pre-training Paradigm governed by a Cross-Embodiment Data Curriculum, which organizes open-world videos, human behavioral data, and robot interactions into a progressive developmental pathway. (2) Kairos maintains the world by unified world understanding, generation, and prediction within a Native Unified Architecture equipped with Hybrid Linear Temporal Attention, where sliding-window attention captures local dynamics, dilated sliding windows capture mid-range dependencies, and gated linear attention maintains persistent global memory. We establish formal theoretical bounds demonstrating that this temporal factorization strictly limits error accumulation, mathematically guaranteeing state propagation across extended horizons. (3) Kairos runs the world by incorporating a Deployment-Aware System Co-Design to support low-latency rollout generation on server and consumer-grade hardware for real-world observation-action-feedback loops. Experiments on embodied world-model, long-horizon, and action-policy benchmarks show that Kairos achieves top level performance while offering a strong efficiency-capability trade-off. Together, these results position Kairos as a cohesive operational foundation for future self-evolving physical intelligence.