{"id":"61c27e6d-6315-44b9-9ebf-128b8c6a68de","slug":"xpeng-vla-2","name":"XPENG VLA 2.0","description":"XPENG's mass-produced billion-parameter-scale foundation model for physical AI. Uses a novel 'Vision-Implicit Token-Action' path that eliminates the language translation step, achieving end-to-end direct generation from visual signals to action commands. First in industry to deploy billion-parameter model on-vehicle (2250 TOPS via Turing AI chip). Cross-domain: simultaneously drives AI cars, IRON humanoid robot, and flying cars. Trained on ~100M real driving video clips without annotation. Rolled out to XPENG Ultra models Q1 2026.","brainType":"foundation-model","isOpen":false,"maturityStage":"production","architecture":"Vision-Implicit Token-Action (V-I-A), 72B cloud base + billion-parameter on-vehicle, Turing AI chip 2250 TOPS","reviewStatus":"reviewed","sources":[{"url":"https://www.xpeng.com/pressroom/news/019a56f54fe99a2a0a8d8a0282e402b7","date":"2025-11-05","title":"XPENG Shares Achievements in Physical AI Emergence: Unveils XPENG VLA 2.0, Robotaxi, Next-Gen IRON, and Flying Car","sourceName":"XPENG"},{"url":"https://www.xpeng.com/news/019a56f54fe99a2a0a8d8a0282e402b7","title":"XPENG Shares Achievements in Physical AI Emergence","sourceName":"XPENG"},{"url":"https://www.xpeng.com/pressroom/news/019cae5e67b99c0960ee8a028129016a","title":"XPENG Accelerates Global Deployment of VLA 2.0","sourceName":"XPENG"},{"url":"https://www.xpeng.com/pressroom/news/019e95aed2899e8226228a028d650112","title":"XPENG Showcases Physical AI and World Model at CVPR 2026","sourceName":"XPENG"},{"url":"https://www.xpeng.com/pressroom/news/019f12539bff9f1220b48a028223000e","title":"XPENG Unveils X-Mind: A Future-Foresight Brain for Autonomous Driving","sourceName":"XPENG"}],"keyFacts":[{"label":"VLA 2.0 architecture and on-vehicle scale (primary XPENG)","value":"XPENG's Nov 5 2025 AI Day release introduces VLA 2.0 with a Vision-Implicit Token-Action path that removes a language translation step for end-to-end vision-to-action generation. It cites a 72 billion parameter cloud base model iterating about every five days on a 30,000-card cluster, and says a billions-of-parameters VLA 2.0 build was installed on Ultra models with 2250 TOPS via Turing AI chip software-stack work. Treat scale and architecture claims as company-stated (XPENG)"},{"label":"Rollout and Volkswagen (primary XPENG)","value":"The same release says pioneer users would experience VLA 2.0 by end of December 2025 with a full Ultra-model rollout in Q1 2026, that VLA 2.0 would be open-sourced to business partners, and that Volkswagen is the launch customer for VLA 2.0 while the Turing AI chip secured a Volkswagen nomination. Treat partner and schedule claims as company-stated (XPENG)"},{"label":"VLA 2.0 Physical AI unveil (primary XPENG)","value":"XPENG's pressroom piece titled on Physical AI Emergence unveils XPENG VLA 2.0 alongside Robotaxi, next-gen IRON, and flying systems, describing VLA 2.0 as a core Physical AI application for vehicle control. Treat product framing as company-stated (XPENG)"},{"label":"End-to-end physical AI model","value":"XPENG describes VLA 2.0 as an end-to-end physical AI model that maps visual signals to action commands for AI-defined vehicles, humanoid robots, and flying vehicles (XPENG VLA 2.0)."},{"label":"Autonomous-driving deployment","value":"XPENG says VLA 2.0 supports full-scenario driving functions and is being advanced through public-road testing and a planned delivery programme (XPENG VLA 2.0 deployment)."},{"label":"Physical AI world model","value":"XPENG's CVPR 2026 pressroom release presents its Physical AI and world-model work as part of the company's autonomous-driving technology roadmap (XPENG at CVPR 2026)."},{"label":"X-Mind future forecasting","value":"XPENG describes X-Mind as a future-foresight brain that uses visual chain-of-thought and predictive world-model reasoning to forecast future traffic states before driving decisions; treat the architecture framing as company-stated (XPENG X-Mind)."},{"label":"Vision-language-action driving model","value":"XPENG describes VLA 2.0 as a physical AI model that translates visual signals into action commands and supports assisted and autonomous driving systems (XPENG VLA 2.0)."},{"label":"Global deployment plan","value":"XPENG says it is expanding public-road testing of VLA 2.0 and plans global vehicle delivery using the model in 2027 (XPENG deployment plan)."}],"aliases":[],"collisionRisk":"low","reviewNote":null,"builtOnBrainId":null,"createdAt":"2026-08-09T14:41:02.609Z","updatedAt":"2026-10-09T22:00:55.693Z","jsonLd":{"@context":"https://schema.org","@type":"SoftwareApplication","@id":"https://registry.deploy.report/brains/xpeng-vla-2","url":"https://registry.deploy.report/brains/xpeng-vla-2","name":"XPENG VLA 2.0","description":"XPENG's mass-produced billion-parameter-scale foundation model for physical AI. Uses a novel 'Vision-Implicit Token-Action' path that eliminates the language translation step, achieving end-to-end direct generation from visual signals to action commands. First in industry to deploy billion-parameter model on-vehicle (2250 TOPS via Turing AI chip). Cross-domain: simultaneously drives AI cars, IRON humanoid robot, and flying cars. Trained on ~100M real driving video clips without annotation. Rolled out to XPENG Ultra models Q1 2026.","identifier":"61c27e6d-6315-44b9-9ebf-128b8c6a68de","applicationCategory":"foundation-model","publisher":{"@id":"https://deploy.report/#organization"}},"framework_metadata":{"framework_schema_version":"0.1.0","verification_status":"verified","maturity_stage":"production","lifecycle_state":null,"architectural_position":{"cohort":null,"sub_cohorts":[]},"within_cohort_verified_vs_claimed_pair":null,"cap_flags":[],"verification_depth":{"sources_count":5,"primary_source_types":[]}}}