Big news from CES 🥳
Cosmos Reason 2 is here, our most advanced reasoning vision-language model for physical AI, now topping the Physical AI Bench leaderboard🏆
What’s new:
- Enhanced physical reasoning & spatio-temporal understanding
- Flexible deployment with 2B & 8B model sizes
- Long-context understanding (up to 256K tokens)
- Object detection with 2D/3D point localizations and trajectory data
- New Cosmos Cookbook Recipes for faster onboarding
📖 Learn More
👉 Download Cosmos Reason 2
On top of Cosmos Reason 2, we also rolled out other new updates, including:
- Cosmos Predict 2.5 – A unified Text2World/Image2World/Video2World model trained on 200M clips, delivering higher-quality, better-aligned synthetic video worlds.
- Cosmos Transfer 2.5-2B – Lightweight, high-fidelity world-to-world translation with stronger physics alignment, fewer hallucinations, and more stable long videos.
- NVIDIA GR00T N1.6 – An open robot foundation model for general-purpose robotic learning and control, now available on Hugging Face and integrated with Cosmos Reason.
📺 Watch our new demo
Get started with the Cosmos Cookbook 🧑🏻🍳