Reka Releases Rho-1: A 19B Omni-Reasoning Model That Understands, Generates Video and Outputs Robot Actions in One
Quick Answer
Reka has introduced Rho-1, a 19 billion parameter omni-reasoning model capable of reading and generating text, images, video, and robot actions.
Quick Take
This model operates over a shared KV cache and features a distilled variant that can produce a 5.3-second video clip in approximately one second. Currently, it is a research preview with no public weights available.
Key Points
- Rho-1 is a 19B parameter model trained from scratch.
- It can generate text, images, video, and robot actions.
- A distilled version outputs a 5.3-second video in about one second.
- Currently, Rho-1 is available as a research preview only.
- No public weights are available for this model yet.
Article Excerpt
From source RSS / original summaryReka 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.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from MarkTechPost
See more →Meet Flash-KMeans: An IO-Aware, Exact K-Means That Runs Over 200× Faster Than FAISS on GPUs
Flash-KMeans is an open-source, IO-aware k-means implementation that operates over 200× faster than FAISS on NVIDIA H200 GPUs. It achieves 17.9× end-to-end and 33× speedup over cuML by optimizing distance calculations and updating mechanisms without approximating results. This advancement significantly enhances performance for data scientists and machine learning practitioners.