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.
Or read this on Venture Beat