tech
December 3, 2025
Nvidia announces new open AI models and tools for autonomous driving research
Nvidia continues its push into physical AI with the release of a new reasoning world model and other tools for physical AI.
TL;DR
- Nvidia announced Alpamayo-R1, an open reasoning vision language model for autonomous driving research.
- Alpamayo-R1 is described as the first vision language action model focused on autonomous driving.
- The model is built on Nvidia's Cosmos-Reason model, designed for decision-making.
- Nvidia aims for these models to provide autonomous vehicles with 'common sense' for nuanced driving.
- The Alpamayo-R1 model is available on GitHub and Hugging Face.
- Nvidia also released the Cosmos Cookbook, offering guides and resources for developers using Cosmos models.
- The company is increasing its focus on physical AI, seeing it as the next major AI wave.
Continue reading
the original article