AI Daybook
AI Daybook
Today's issue
LLM

Reka releases Rho-1, a 19B omni-reasoning model for text, video, and robot actions

Original titleReka Releases Rho-1: A 19B Omni-Reasoning Model That Understands, Generates Video and Outputs Robot Actions in One

Outlet
MarkTechPost
Published
Importance
4/5

Summary

Reka released Rho-1, a 19-billion-parameter omni-reasoning model trained from scratch. One network reads and generates text, images, video, and robot actions over a shared KV cache. A distilled variant produces a 5.3-second clip in about one second. It is a research preview with no public weights yet.

Original excerpt

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. A distilled variant returns a 5.3-second clip in about a second. It is a research preview with no public weights yet. The post Reka Releases Rho-1: A 19B Omni-Reasoning Model That Understands, Generates Video and Outputs Robot Actions in One appeared first on MarkTechPost.

#multimodal#video generation#reka#rho-1#robot control
Read the original
See all →