The Decoder· Matthias Bastian·· 2026-10-06AI score40
Reka AI Releases 19-Billion-Parameter Omni-Modal Model Rho-1, Unifying Text, Image, Video, and Robot Control
Reka AI's omni-model Rho-1 handles text, images, video, and robot control in a single model
AI briefing
Reka AI released a research preview of Rho-1, a 19-billion-parameter omni-modal model that processes and generates text, images, video, and robot control actions within a single neural network. All modalities operate as tokens in the same context window, requiring no tool calls or external models.
Open original the-decoder.com
Video GenerationImage GenerationModel Releases#Model release#Video generation#Image generation#Research