NVIDIA Alpamayo 2 Super: 34B Open Vision-Language-Action Model
NVIDIA introduces Alpamayo 2 Super, a 34B open vision-language-action model for robotaxis.
NVIDIA has unveiled the Alpamayo 2 Super model, a 34 billion parameter system designed for robotaxis and autonomous driving. It features a 32B VLM backbone built on the Cosmos 3 Super Reasoner and a 2.3B diffusion-based action decoder. This model ranks first on LingoQA, marking a significant advancement for autonomous systems.