PulseAugur
EN
LIVE 22:53:36

Reka AI launches Rho-1, a 19B omni-model for text, image, video, and robot control · 4 sources tracked

Reka AI has unveiled Rho-1, a 19-billion-parameter omni-model capable of processing and generating text, images, and video, while also controlling robot actions within a single neural network. This architecture integrates all modalities as tokens in a shared context window, eliminating the need for separate specialized models and reducing latency. The model was trained using a fraction of the compute power required by many current top-tier models. AI

IMPACT This unified model architecture could streamline AI agent development by reducing reliance on complex, multi-model pipelines.

RANK_REASON Frontier-lab model release with system card

Read on The Decoder →

AI-generated summary · Google Gemini · from 4 sources. How we write summaries →

Reka AI launches Rho-1, a 19B omni-model for text, image, video, and robot control · 4 sources tracked

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Frontier Release
Frontier-lab model release with system card
Source corroboration
4 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
48 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [4]

  1. The Decoder TIER_1 English(EN) · Matthias Bastian ·

    Reka AI's omni-model Rho-1 handles text, images, video, and robot control in a single model

    <p><img alt="" class="attachment-full size-full wp-post-image" height="1152" src="https://the-decoder.com/wp-content/uploads/2026/10/rho1_images.png" style="height: auto; margin-bottom: 10px;" width="2048" /></p> <p> Reka AI's Rho-1 is a 19-billion-parameter omni-model that proce…

  2. MarkTechPost TIER_1 English(EN) · Michal Sutter ·

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

    <p>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 weig…

  3. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Reka has released Rho-1, a 19B omni-reasoning model that processes text, images, video and robot actions in one neural network. It uses two weight streams with

    Reka has released Rho-1, a 19B omni-reasoning model that processes text, images, video and robot actions in one neural network. It uses two weight streams with a shared KV cache to handle understanding and generation across modalities. https://www. marktechpost.com/2026/10/05/re …

  4. Mastodon — mastodon.social TIER_1 Polski(PL) · aisight ·

    Startup Reka AI released the research version of the Rho-1 model with 19 billion parameters. The architecture combines multimedia processing with robot motion control.

    Startup Reka AI udostępnił wersję badawczą modelu Rho-1 z 19 miliardami parametrów. Architektura łączy przetwarzanie multimediów ze sterowaniem ruchem robota w ramach jednej sieci neuronowej. # si # ai # sztucznainteligencja # wiadomości # informacje # technologia https:// aisigh…