Get the latest tech news

1X’s generative model first to predict real-world robot interactions


Generative models trained on raw data from robots learn world models that can simulate physical environments with photorealistic quality.

To bridge this gap, 1X’s new model learns to simulate the real world by being trained on raw sensor data collected directly from the robots. The data was collected from EVE humanoid robots doing diverse mobile manipulation tasks in homes and offices and interacting with people. “We’ve seen dramatic progress in generative video modeling over the last couple of years, and results like OpenAI Sora suggest that scaling data and compute can go quite far,” Jang said.

Get the Android app

Or read this on Venture Beat

Read more on:

Photo of robots

robots

Photo of 1X releases

1X releases

Related news:

News photo

Chipotle Is Testing Out Using Robots to Make Guacamole

News photo

Will humans accept robots that can lie? Scientists find it depends on the lie

News photo

Alleged fraudster got $10 million in royalties using robots to stream AI-made music