Live
GESTAMPGestamp opens fifth India plant in Gujarat with €47.4 million investmentFERRARI N.V.Ferrari takes third and fourth in Spanish Grand Prix opening practice at new Madring circuitASHOK LEYLANDAshok Leyland opens 12th Karnataka LCV dealership in Raichur with SB MotorsYUTONG BUS CO., LTD.Yutong Opens First European Service Center in Norway to Support Electric Bus FleetsASHOK LEYLANDSB Motors opens Raichur LCV site as Karnataka network reaches 12KIAKia India takes pre-bookings for Carnival hybrid and its first factory-fitted CNG modelsTATA MOTORSTata Cars, IndianOil and ToneTag put UPI fuel payments inside the carLI AUTOLi Auto sets Li 6 name and Paris debut for European entryBYDFinDreams takes BYD’s Blade battery into industrial railTESLAChina gets Tesla’s 369,000-yuan Model Y Performance flagshipCHINA PASSENGER CAR ASSOCIATIONNEVs reached 71.5% of China’s early-September passenger-car retailCHINA ASSOCIATION OF AUTOMOBILE MANUFACTURERSChina’s 2030 NEV target puts electric sales and autonomy on the same timetableGESTAMPGestamp opens fifth India plant in Gujarat with €47.4 million investmentFERRARI N.V.Ferrari takes third and fourth in Spanish Grand Prix opening practice at new Madring circuitASHOK LEYLANDAshok Leyland opens 12th Karnataka LCV dealership in Raichur with SB MotorsYUTONG BUS CO., LTD.Yutong Opens First European Service Center in Norway to Support Electric Bus FleetsASHOK LEYLANDSB Motors opens Raichur LCV site as Karnataka network reaches 12KIAKia India takes pre-bookings for Carnival hybrid and its first factory-fitted CNG modelsTATA MOTORSTata Cars, IndianOil and ToneTag put UPI fuel payments inside the carLI AUTOLi Auto sets Li 6 name and Paris debut for European entryBYDFinDreams takes BYD’s Blade battery into industrial railTESLAChina gets Tesla’s 369,000-yuan Model Y Performance flagshipCHINA PASSENGER CAR ASSOCIATIONNEVs reached 71.5% of China’s early-September passenger-car retailCHINA ASSOCIATION OF AUTOMOBILE MANUFACTURERSChina’s 2030 NEV target puts electric sales and autonomy on the same timetable
MotorClaw.news
Search releases, companies, topics...
Live2026-09-12 04:58 UTC+0 todayUpdated

XPENG Releases World Model Technical Report Backing VLA 2.0 Autonomous Driving

XPENG has released a technical report for X-World, a generative world model that creates real-time multi-view simulations for autonomous driving, now integrated into VLA 2.0 development and validation.

Daily simulated test mileage
30 million kilometers
Autonomous driving simulation scenarios
Over 500,000

What Happened

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.

Autonomous Driving Simulation Scenarios

500,000+scenarios

up from 30,000 a year ago; daily simulated test mileage equivalent to 30 million km

Core Strengths of X-World
  • Strong cross-view consistency across seven surround-view cameras
  • Strict action following: generated scenes match specified ego-vehicle behavior
  • Long-horizon video simulation for stable predictions over extended time spans

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.

Why this matters

X-World reduces the need for expensive real-world testing by generating realistic driving simulations, helping XPENG develop safer autonomous driving more efficiently.

Terms in This Story

World model
A generative AI model that can simulate and predict future states of a driving environment.
VLA
Vision-Language-Action model, an AI system for autonomous driving that processes visual data, language instructions, and driving actions.
DiT
Diffusion Transformer, a neural network architecture used for generating high-quality video sequences.
Read Original: Xpeng

Summarised from the linked release; details can be imperfect — always verify against the original source.