Reka AI's omni-model Rho-1 handles text, images, video, and robot control in a single model
🤖 AI-generated content — The title and summary were produced automatically by artificial intelligence, without human editorial review.
Reka AI released a research preview of Rho-1, a 19-billion-parameter omni-model that processes and generates text, images, video, and robot control actions within a single neural network. Using a shared context window without external models or tool calls, the system generates continuous real-time video and derives robot control signals from ordinary internet videos using an inverse dynamics model. The model was trained on 320 H100 GPUs over approximately three months.
Continue in the app — vote & join in ➔Source: The Decoder (AI) · via ahirlevel.hu