Li Auto Releases ME-Brain-1.0, ME-U0 World-Action Model and ME-VLM
Li Auto Ships Embodied Trilogy: ME-Brain-1.0, ME-U0 Unified WAM and Edge ME-VLM
The stack treats driving as an embodied-AI system, with a world-action model and a compressed edge VLM that can run locally on automotive silicon — an architecture automakers beyond Li Auto will likely copy. Teams building in-cabin or driver-assistance intelligence can study the 35B-A3B-to-4B split as a template for cloud-to-edge model deployment. It also signals Chinese automakers competing on foundation-model depth, not just features.
Li Auto's Foundation Model team has shipped an embodied AI stack consisting of three releases: ME-Brain-1.
0, the ME-U0 unified world-action model, and the ME-VLM cognitive model family.ME-VLM comes in a 35B-A3B configuration plus a smaller 4B edge variant running on the M100 SoC.
The company framed the releases around system architecture rather than vehicle branding.
Li Auto Ships Embodied Trilogy: ME-Brain-1.0, ME-U0 Unified WAM and Edge ME-VLM
Li Auto's Foundation Model team released ME-Brain-1.0, the ME-U0 unified world-action model and ME-VLM cognitive models (35B-A3B plus a 4B edge SKU on the M100 SoC), emphasizing system architecture over vehicle branding.
This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Li Auto, ME-Brain-1.0, ME-VLM, embodied AI.
Primary source verification: published directly by pandaily with first-party authority.
