Nvidia unveils Alpamayo VLA for reasoning AVs at CES 2026…

Nvidia Launches Alpamayo: Open-Source AI Models for Autonomous Vehicles with Human-Like Judgment

  • NVIDIA unveiled the open reasoning vision-language-action system “Alpamayo” at CES 2026.
  • Alpamayo includes the 10-billion-parameter model Alpamayo 1, the AlpaSim simulator, and Physical AI Open Datasets with 1,700+ hours of driving data.
  • Alpamayo 1 is described as the industry’s first chain-of-thought reasoning VLA model for autonomous vehicle research and is available on Hugging Face.
  • AlpaSim is a fully open-source simulation framework on GitHub for high-fidelity AV development and closed-loop testing.
  • Companies such as Lucid, JLR, Uber and Berkeley DeepDrive have expressed interest; Nvidia shares rose modestly after the announcement.

At the Consumer Electronics Show (CES) 2026, Nvidia CEO Jensen Huang introduced the open reasoning vision-language-action suite called Alpamayo to help autonomous vehicles perceive, reason and act with humanlike judgment. The package includes the Alpamayo 1 model, the AlpaSim simulator and Physical AI Open Datasets to enable safer, more robust and scalable vehicle development. This release aims to give developers tools to fine-tune, distill and test reasoning-capable AV systems.

- Advertisement -

Alpamayo 1 is a 10‑billion‑parameter chain‑of‑thought reasoning VLA model built for the autonomous vehicle research community and can be adapted into smaller runtime models for vehicle development. The model is available on Hugging Face and is designed to take sensor input and produce action outputs with explainable reasoning.

AlpaSim is a fully open‑source, end‑to‑end simulation framework hosted on GitHub. It offers realistic sensor modeling, configurable traffic dynamics and scalable closed‑loop testing environments for rapid validation and policy refinement.

The Physical AI Open Datasets include more than 1,700 hours of driving data collected across varied geographies and conditions to advance reasoning architectures. “The ChatGPT moment for physical AI is here — when machines begin to understand, reason and act in the real world,” Huang said, as stated in the company release. “Not only does [Alpamayo] take sensor input and activate steering wheel, brakes and acceleration, it also reasons about what action it is about to take,” he added.

Industry groups including Lucid, JLR, Uber and Berkeley DeepDrive have shown interest in using Alpamayo for developing level‑4 autonomy stacks. After the announcement, NVDA shares rose about 0.5% in after‑hours trading and are up more than 25% over the past year, while retail sentiment on Stocktwits moved from bearish to bullish.

- Advertisement -

✅ Follow BITNEWSBOT on Telegram, Facebook, LinkedIn, X.com, and Google News for instant updates.

Previous Articles:

- Advertisement -

Latest News

Hyperscale hits 500k TPS, peaks over 700k in public test

Radix Hyperscale sustained 500,000 transactions per second (TPS) with peaks over 700,000 TPS during...

JPMorgan Projects Gold Skyrocketing to $8,000 by 2030

JP Morgan projects Gold (XAU/USD) could surge to $8,000 by 2030, a prediction following...

Crypto VC Inflows Hit $1.4B Through Early 2026

Institutional and venture capital commitments to crypto companies reached $1.4 billion at the start...

Brazil Sells $61B in US Treasuries, Buys Gold in 2026

Brazil sold $61 billion in U.S. Treasury securities in 2026, using the proceeds to...

U.S. Sanctions Crypto Exchanges Aiding Iran’s Regime

The U.S. Treasury Department has, for the first time, sanctioned entire cryptocurrency exchanges under...
- Advertisement -

Must Read

What Is a Sim Swap Hack?

You've likely heard the term 'sim-swap,' but do you really know what it means? It's a type of fraud that's rapidly increasing, where scammers...
🔥 #AD Get 20% OFF any new 12 month hosting plan from Hostinger. Click here!