October 5, 2026 · The Decoder
Reka AI releases Rho-1, a 19B omni-model that also controls robots
Rho-1 is a 19-billion-parameter model that processes and generates text, images, video, and robot control actions in one network, treating every modality as tokens in a shared context window. Reka says it was trained on 320 H100 GPUs in about three months, far less compute than top models use.
Why it matters: A single model covering language, vision and action without routing to specialists is the architecture robotics efforts are converging on. If the low-compute training claim holds, it suggests smaller labs can still compete in embodied AI.
Related updates
- Transformer compresses 1GB of Wikipedia to 105MB losslesslyNov 21
- ByteDance's open Axion 1.0 agent rivals top models with three training phasesNov 21
- OpenAI ships GPT-Live-1.1 voice model and cuts idle billingNov 21
- Stanford posts all-human Riemann hypothesis proof hours after Anthropic's Claude claimNov 21