NVIDIA Launches Alpamayo 2 Super Open Reasoning Model for Robotaxis

NVIDIA today introduced NVIDIA Alpamayo 2 Super, a 32-billion-parameter reasoning‑based vision language action (VLA) model that extends the NVIDIA Alpamayo family of open AI models, simulation frameworks and physical AI datasets for safe, level 4 robotaxi development.

Vision-language-action models connect visual perception and language reasoning with physical actions, helping robots interpret scenes and respond appropriately.