
What happened
Reka AI released a research preview of Rho-1, a 19-billion-parameter omni-model that processes and generates text, images, video and robot control actions in one neural network, trained on 320 H100 GPUs over about three months.
Why it matters
Unlike most AI systems that route tasks to specialized models with tool calls or external models, Rho-1 runs all modalities as tokens in one shared context window, which appears to simplify multimodal AI and enable real-time video with on-the-fly instructions.
What to watch
The approach hinges on whether one model can match specialized systems, but it is a research preview so production readiness is unproven; watch for updates on the inverse dynamics model that pulls control signals from ordinary internet videos.
WHO IT HITSThis matters to AI researchers and robotics teams exploring unified models, who may see new ways to handle multimodal tasks without specialized tools.
Summaries like this, every morning.
Reka AI has a track record in multimodal AI: in April 2024 it shipped Reka Core, a multimodal language model that competed with GPT-4, Claude 3, and Gemini Ultra on benchmarks. The new Rho-1 release fits a broader push in AI research toward so-called world models, which aim to understand and simulate environments. Unlike most systems that route tasks to specialized models, Rho-1 runs all modalities as tokens in one shared context window with no tool calls or external models, and it generates continuous video in real time while responding to new instructions without restarting. The same weights that predict camera images also drive robot movements, with an inverse dynamics model extracting control signals from ordinary internet videos to work around scarce robot training data.
The outcome hinges on whether this unified approach can match or exceed specialized models in practice, and on how the research community responds to the trade-offs of a single model versus modular systems. For now, Rho-1 is a research preview, so its path to production and real-world deployment is likely still being explored.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Warby Parker is launching AI smart glasses starting at $395 on Nov

OpenAI's Performance Factory, built on Codex, completed over 1,700 investigations in three months and pinpoint…

At the ThinkingAI Summit 2026 Tokyo on November 10, 2026, Daniel Wang, co-CEO and vice president of Hong Kong-…

Polimill said on Nov 19, 2026 that QommonsAI, its generative AI for government, now supports domestic inferenc…

AgeAI, led by CEO Gen Mikami, joined the Gotanda Valley Acceleration Program 2026 from its September 17 kickof…

Since late October, users of OpenAI's paid plans have reported Codex and ChatGPT Work burning through usage qu…
