X-World 1 6 provides controllable virtual cities for driving tests

X-World 1.6: Building Controllable Virtual Cities with World Models

Artificial Intelligence

Summary

Simulating virtual driving environments is hard because the scenarios must be realistic and controllable over time. The authors improved their X-World simulator to better control traffic elements like lights and road markings and to keep scenes consistent from multiple camera views. Their system can create new city layouts from simple inputs and generate future driving videos, helping test driving policies. They also made the simulator's output more stable and aligned with human preferences over longer simulations. A new evaluation suite helps check and improve the simulator’s performance systematically.

What this means in practice

  • For autonomous vehicle developers: Simulate detailed and controllable traffic scenarios with multi-view videos to test and train self-driving car policies more effectively.
  • For video game designers: Create realistic virtual city environments that maintain consistency across multiple viewpoints and over time for driving or open-world games.

Authors

XPeng, :, Boyang Wang, Boyi Sun, Chaoda Zheng, Dongbin Zhang, Guangfeng Jiang, Hanlong Chen, Hongbin Lin, Jianlei Zheng, Jinhao Deng, Kai Yang, Kangjie Chen, Linkun Xu, Minqi Wang, Puyi Wang, Rongliang Cheng, Ruixin Liu, Shijia Chen, Shuang Deng, Sijia Chen, Sin Wai Choo, Tianyuan Xie, Xiangyu Li, Xianming Liu, Xingjie Liu, Xinlong Zheng, Xuejie Lv, Xuezhi Yang, Yi Guo, Yixiao Zeng, Yu Zhang, Yuecheng Ma, Yuhao Wang, Yuqi Zhang, Yuxin Peng

Abstract

Deploying generative world models for end-to-end closed-loop evaluation and policy learning requires precise scenario control, consistent observations, and sustained generation quality during extended interactions. This report presents \emph{X-World~1.6}, advancing X-World~1.0 toward a more reliable and versatile driving simulator. The upgraded base model offers finer-grained control over traffic semantics, including traffic lights and road markings, together with improved spatial consistency across cameras. Virtual City capabilities broaden scenario construction through a family of models conditioned on diverse 2D and 3D references, including support for generating multi-camera future videos from a single image. An enhanced post-training framework enables efficient causal, few-step generation with stronger temporal coherence, better quality retention over longer rollouts, and improved alignment with human preferences. We also introduce a dedicated evaluation suite to support systematic assessment and guide model iteration. Together, these upgrades expand the scenarios X-World can simulate and improve the efficiency and reliability of its generated observations, supporting broader use in autonomous-driving development.