Reka Launches Rho-1, a 19B Multimodal Model Capable of Video Generation and Robotics
AI startup Reka has introduced Rho-1, a 19 billion parameter omni-reasoning model that processes text, images, video, and robot actions through a single shared architecture. Currently available as a research preview without public weights, the model marks a significant step toward unified multimodal AI systems capable of cross-domain reasoning and rapid video generation.
Source: MarkTechPost