Paper Detail
Kairos Team, Fei Wang, Shan You, Qiming Zhang, Tao Huang, Zuoyi Fu, Zhisheng Zheng, Yunlong Xi, Feng Lv, Xiaoming Wu, Zeyu Liu, Cong Wan, Pu Li, Ruiqing Yang, Xiaoou Li, Wei Wang, Kangkang Zhu, Yuwei Zhang, Shi Fu, Zheng Zhang, Xiaoning Wu, Xuzeng Fan, Dacheng Tao, Xiaogang Wang
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{team2026kairos,
title = {Kairos: A Native World Model Stack for Physical AI},
author = {Kairos Team and Fei Wang and Shan You and Qiming Zhang and Tao Huang and Zuoyi Fu and Zhisheng Zheng and Yunlong Xi and Feng Lv and Xiaoming Wu and Zeyu Liu and Cong Wan and Pu Li and Ruiqing Yang and Xiaoou Li and Wei Wang and Kangkang Zhu and Yuwei Zhang and Shi Fu and Zheng Zhang and Xiaoning Wu and Xuzeng Fan and Dacheng Tao and Xiaogang Wang},
year = {2026},
abstract = {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 Cur},
url = {https://huggingface.co/papers/2606.16533},
keywords = {world models, native pre-training paradigm, cross-embodiment data curriculum, native unified architecture, hybrid linear temporal attention, sliding-window attention, dilated sliding windows, gated linear attention, temporal factorization, error accumulation, deployment-aware system co-design, embodied world-model, long-horizon benchmarks, action-policy benchmarks, code available, huggingface daily},
eprint = {2606.16533},
archiveprefix = {arXiv},
}
{}