Wireva

Reka AI's Rho-1 Omni-Model Unifies Text, Images, Video and Robot Control

Reka AI has unveiled Rho-1, a 19-billion-parameter omni-model that processes and generates text, images, video and robot control actions within a single neural network, trained on 320 H100 GPUs in roughly three months.

Monitoring item. The full text is not distributed. Extract and source below.

Reka AI has unveiled Rho-1, a 19-billion-parameter omni-model that processes and generates text, images, video and robot control actions within a single neural network, trained on 320 H100 GPUs in roughly three months.