perspectiva aiqbenchProduse AI

Reka's Rho-1 introduces a unified architecture where text, visual generation, and robotic control share a single key-value cache, aiming to streamline multi-modal reasoning. While weights remain unreleased for now, the model's ability to generate video clips in under five seconds suggests significant progress toward integrated human-robot interaction systems. This development represents a notable step forward in consolidating distinct AI capabilities into a cohesive framework rather than relying on separate specialized models.

Sursă care acoperăMarkTechPost

Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

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

MarkTechPost6 octombrie 20261 min de cititArticolul și perspectiva sunt în engleză.

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.

Citește articolul complet pe MarkTechPost

Citește pe MarkTechPost ↗Întreabă despre acest articol