"Nvidia announced new infrastructure and AI models on Monday as it works to build the backbone technology for physical AI, including robots and autonomous vehicles that can perceive and interact with the real world. The semiconductor giant announced Alpamayo-R1, an open reasoning vision language model for autonomous driving research at the NeurIPS AI conference in San Diego, California. The company claims this is the first vision language action model focused on autonomous driving."
"This new model is based on Nvidia's Cosmos Reason model, a reasoning model that thinks through decisions before it responds. Nvidia initially released the Cosmos model family in January 2025. Additional models were released in August. Technology like the Alpamayo-R1 is critical for companies looking to reach level 4 autonomous driving, which means full autonomy in a defined area and under specific circumstances, Nvidia said in a blog post."
"This new model is available on GitHub and Hugging Face. Alongside the new vision model, Nvidia also uploaded new step-by-step guides, inference resources and post-training workflows to GitHub - collectively called the Cosmos Cookbook - to help developers better use and train Cosmos models for their specific use cases. The guide covers data curation, synthetic data generation, and model evaluation."
Nvidia introduced Alpamayo-R1, an open reasoning vision-language action model for autonomous driving research unveiled at NeurIPS in San Diego. The model builds on the Cosmos Reason family, which Nvidia began releasing in January 2025 with additional models in August. Alpamayo-R1 aims to enable vehicles to perceive environments and apply stepwise reasoning for nuanced driving decisions to help reach level 4 autonomy in defined areas. Nvidia published the model on GitHub and Hugging Face and provided the Cosmos Cookbook with guides on data curation, synthetic data generation, inference, post-training workflows, and model evaluation. Nvidia positions physical AI as a core priority for its GPU roadmap.
Read at TechCrunch
Unable to calculate read time
Collection
[
|
...
]