Kairos: A Native World Model Stack for Physical AI

• URL: http://arxiv.org/abs/2606.16533v2
• Date: Tue, 16 Jun 2026 11:06:38 GMT
• Title: Kairos: A Native World Model Stack for Physical AI
• Abstract summary: We introduce Kairos, a native world model stack designed around these requirements.<n>Kairos learns the world by pioneering a Native Pre-training governed by a Cross-Embodiment Paradigm Data Curriculum.<n>Kairos maintains the world by unified world understanding, generation, and prediction within a Native Unified Architecture equipped with Hybrid Linear Temporal Attention.
• Score: 66.80630645291795
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 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.

Related papers

• Toward the Cognitive--Physical Limits of Embodied Intelligence through a World-Model-Centric Autonomous Racing Agent [41.433447721854144]
  We show that a world-model-centric autonomous racing agent provides a concrete step toward exploring coupled limits.<n>The framework learns predictive world models from near-limit successes and failures to capture interaction evolution, ego dynamics, and feasible-motion boundaries.<n>In full-scale simulated racing, the well trained world-model-centric agent achieves an 88.3% interaction success rate.
  arXiv  Detail & Related papers  (2026-08-11T08:01:35Z)
• CG-World: A Large-Scale World-State Dataset and Protocol for World Models [13.423809800311984]
  We introduce CG-World, a large-scale world-state dataset and protocol derived from industrial computer graphics production pipelines.<n> CG-World explicitly records intermediate states, including multimodal semantics, spatial structure, skeletal and controller states, motion curves, camera and lighting parameters, physics caches, contact events, and multi-pass renderings.
  arXiv  Detail & Related papers  (2026-07-29T04:06:28Z)
• GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving [56.50032398571235]
  GraphWorld is an E2E-AD framework that explicitly enhances long-horizon planning through latent world modeling.<n>We present a World-State-Conditioned Planning that learns ego-centric latent world representations by modeling interactions between an ego vehicle and surrounding agents.<n>This latent world state captures key interaction dynamics and safety-relevant semantics, and serves as a conditioning signal to guide long-horizon, safety-aware trajectory planning.
  arXiv  Detail & Related papers  (2026-06-15T06:26:46Z)
• AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization [79.26935895370191]
  AnchorWorld is a framework that advances egocentric simulation through enhanced interaction integrity.<n> auxiliary training supervision incorporates viewpoints decoupled from the agent's first-person sensorium.<n>We propose a simple yet effective mechanism for customizing self-evolving worlds.
  arXiv  Detail & Related papers  (2026-06-05T14:43:13Z)
• Xiaomi Auto World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving [51.90209659403234]
  This report presents a unified technical system addressing the two core capabilities of world models for autonomous driving.<n>For world representation, we propose WorldRec, a feed-forward reconstruction architecture driven by sparse scene queries.<n>For world generation, we propose WorldGen, a two-stage training framework of bidirectional pretraining followed by causal fine-tuning.
  arXiv  Detail & Related papers  (2026-05-18T09:46:16Z)
• CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving [4.4380564455353975]
  CoWorld-VLA is a multi-expert world reasoning framework for autonomous driving.<n>World representations serve as explicit conditions to guide action planning.<n>Experiments show that CoWorld-VLA achieves competitive results in both future scene generation and planning.
  arXiv  Detail & Related papers  (2026-05-11T12:01:13Z)
• Causal World Modeling for Robot Control [56.31803788587547]
  Video world models provide the ability to imagine the near future by understanding the causality between actions and visual dynamics.<n>We introduce LingBot-VA, an autoregressive diffusion framework that learns frame prediction and policy execution simultaneously.<n>We evaluate our model on both simulation benchmarks and real-world scenarios, where it shows significant promise in long-horizon manipulation, data efficiency in post-training, and strong generalizability to novel configurations.
  arXiv  Detail & Related papers  (2026-01-29T17:07:43Z)
• WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World [100.68103378427567]
  Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally.<n>We introduce WorldLens, a full-spectrum benchmark evaluating how well a model builds, understands, and behaves within its generated world.<n>We further construct WorldLens-26K, a large-scale dataset of human-annotated videos with numerical scores and textual rationales, and develop WorldLens-Agent.
  arXiv  Detail & Related papers  (2025-12-11T18:59:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.