Reka AI's Rho-1 handles text, images, video, and robot control in a single model
Original titleReka AI's omni-model Rho-1 handles text, images, video, and robot control in a single model
- Outlet
- The Decoder
- Published
- Importance
- 4/5
Summary
Reka AI released Rho-1, a 19-billion-parameter omni-model that processes and generates text, images, video, and robot control actions in a single neural network. Trained on 320 H100 GPUs in about three months, it uses a fraction of the compute that today's top models require.
Original excerpt
Reka AI's Rho-1 is a 19-billion-parameter omni-model that processes and generates text, images, video, and robot control actions in a single neural network. Trained on 320 H100 GPUs in about three months, it uses a fraction of the compute today's top models need. Instead of routing tasks to specialized systems, Rho-1 runs all modalities as tokens in one shared context window. The article Reka AI's omni-model Rho-1 handles text, images, video, and robot control in a single model appeared first on The Decoder.