Reka Releases Rho-1: A 19B Omni-Reasoning Model That Understands, Generates Video and Outputs Robot Actions in One
Reka has released Rho-1, a 19B omni-reasoning model that processes and generates text, images, video, and robot control actions in a single network. It was trained from scratch on 320 H100 GPUs in about three months.
Reka has released Rho-1, a 19B omni-reasoning model trained from scratch. One network reads and generates text, images, video and robot actions over a shared KV cache. Instead of routing tasks to specialized systems, Rho-1 runs all modalities as tokens in one shared context window.
Rho-1 was trained on 320 H100 GPUs in about three months, using a fraction of the compute today's top models need. A distilled variant returns a 5.3-second clip in about a second. It is a research preview with no public weights yet.
This item is a summary. The full, checkable version is at the original source:
Read the original at MarkTechPost ↗Read the original at The Decoder ↗