Reka releases Rho-1, a 19B omni model handling text, image, video and robot actions in one network
RekaAILabs · x · 2026-10-05
Reka AI has released a research preview of Rho-1, a 19B-parameter omni model that understands and generates text, images, video and robot actions inside a single neural network.
The team stresses its end-to-end design: no agent calling specialist models behind the curtain — every modality is handled by the one model. Author artetxem shared unedited screen recordings showing Rho-1 running as-is, including video understanding and robot action generation.
Related event: Reka unveils Rho-1, a 19B unified any-to-any model trained on 320 H100s(8 posts)→
More from Embodied
- NVIDIA open-sources Lyra 2.0: turn any photo into an explorable 3D world — Promptmethus · 2026-10-06
- NowWAM Swaps Future Prediction for Denoising in Robot Control, Hits 87.7% on LIBERO-Plus — Zanyi Wang · 2026-10-06
- CMU Safe AI Lab director launches Safeworld with $12.2M seed to test GenAI robot safety — Scobleizer · 2026-10-06
- A SOTA real2sim recipe for robotics: agents build sims with real physics and affordance — simonguozirui · 2026-10-06
- Ghost AI launches Core, a $3,499 personal AI computer running models fully on-device — Jackyhuang · 2026-10-06
- Smart Machines Are Transforming China's Farms — yogthos · 2026-10-06