XPENG Releases World Model Technical Report Backing VLA 2.0 Autonomous Driving

Traditional simulation testing techniques based on 3D Gaussian Splatting can reproduce real-world scenes but fail when the autonomous driving model deviates from original trajectories, such as sharp lane changes. This has forced the industry to rely on expensive real-world road testing with limited scenario coverage. XPENG's X-World, a generative world model built on video diffusion technology, addresses this by generating future multi-camera video streams from historical video and driving actions, enabling controllable, real-time simulation.

X-World supports XPENG's VLA 2.0 in closed-loop evaluation, online reinforcement learning, and large-scale data generation. It enables evaluating safety metrics like collision rate and ride comfort in a virtual environment, and can generate missing long-tail scenario data for corner cases.