Get the latest tech news

Nvidia’s Cosmos-Transfer1 makes robot training freakishly realistic—and that changes everything

Nvidia releases Cosmos-Transfer1, a groundbreaking AI model that generates photorealistic simulations for training robots and autonomous vehicles by bridging the gap between virtual and real-world environments.

Unlike previous simulation models, Cosmos-Transfer1 introduces an adaptive multimodal control system that allows developers to weight different visual inputs—such as depth information or object boundaries—differently across various parts of a scene. Traditional approaches to training physical AI systems involve either collecting massive amounts of real-world data — a costly and time-consuming process — or using simulated environments that often lack the complexity and variability of the real world. Cosmos-Transfer1 addresses this dilemma by allowing developers to use multimodal inputs (like blurred visuals, edge detection, depth maps, and segmentation) to generate photorealistic simulations that preserve crucial aspects of the original scene while adding natural variations.

Get the Android app