# Infrastructure-Centric World Models: Bridging Temporal Depth and Spatial Breadth for Roadside Perception

arXiv: https://arxiv.org/abs/2604.17651 · HTML: https://mlsanity.com/paper/2604.17651/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in World models for autonomous driving, one of 11 directions in World models.
- Builds on 13 of its 54 references that are in the map.
- First posted on arXiv 19 Apr 2026.

## Placed in

- World models / [World models for autonomous driving](https://mlsanity.com/wm/world-models-for-autonomous-driving/)

## Builds on (most cited first, 13 of 13)

- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [Advancing Open-source World Models](https://mlsanity.com/paper/2601.20540/) (2026)
- [DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving](https://mlsanity.com/paper/2510.12796/) (2025)
- [World Models for Autonomous Driving: An Initial Survey](https://mlsanity.com/paper/2403.02622/) (2024)
- [A Survey of World Models for Autonomous Driving](https://mlsanity.com/paper/2501.11260/) (2025)
- [LidarDM: Generative LiDAR Simulation in a Generated World](https://mlsanity.com/paper/2404.02903/) (2024)
- [The Role of World Models in Shaping Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2502.10498/) (2025)
- [UrbanWorld: An Urban World Model for 3D City Generation](https://mlsanity.com/paper/2407.11965/) (2024)
- [Vehicle-to-Everything Cooperative Perception for Autonomous Driving](https://mlsanity.com/paper/2310.03525/) (2023)
- [ResWorld: Temporal Residual World Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2602.10884/) (2026)
- [CarDreamer: Open-Source Learning Platform for World Model based Autonomous Driving](https://mlsanity.com/paper/2405.09111/) (2024)

## Built on by (most cited first, 1 of 1)

- [Bridging Local Observation and Global Simulation in Closed-Loop Traffic Modeling](https://mlsanity.com/paper/2606.31844/) (2026)

## Abstract (arXiv)

World models, generative AI systems that simulate how environments evolve, are transforming autonomous driving, yet all existing approaches adopt an ego-vehicle perspective, leaving the infrastructure viewpoint unexplored. We argue that infrastructure-centric world models offer a fundamentally complementary capability: the bird's-eye, multi-sensor, persistent viewpoint that roadside systems uniquely possess. Central to our thesis is a spatio-temporal complementarity: fixed roadside sensors excel at temporal depth, accumulating long-term behavioral distributions including rare safety-critical events, while vehicle-borne sensors excel at spatial breadth, sampling diverse scenes across large road networks. This paper presents a vision for Infrastructure-centric World Models (I-WM) in three phases: (I) generative scene understanding with quality-aware uncertainty propagation, (II) physics-informed predictive dynamics with multi-agent counterfactual reasoning, and (III) collaborative world models for V2X communication via latent space alignment. We propose a dual-layer architecture, annotation-free perception as a multi-modal data engine feeding end-to-end generative world models, with a phased sensor strategy from LiDAR through 4D radar and signal phase data to event cameras. We establish a taxonomy of driving world model paradigms, position I-WM relative to LeCun's JEPA, Li Fei-Fei's spatial intelligence, and VLA architectures, and introduce Infrastructure VLA (I-VLA) as a novel unification of roadside perception, language commands, and traffic control actions. Our vision builds upon existing multi-LiDAR pipelines and identifies open-source foundations for each phase, providing a path toward infrastructure that understands and anticipates traffic.