Meet Kyutai REKI: The 2.4B VLA Model Bringing Efficient Memory to Robot Manipulation
Kyutai introduced REKI, a 2.4B vision-language-action model for memory-efficient robot manipulation.
MarkTechPost introduces Kyutai REKI, a 2.4 billion-parameter vision-language-action model for robot manipulation. The headline emphasis is efficient memory so the model can handle manipulation without the cost of larger VLAs. The item body provided here is almost entirely cookie-consent text, so architecture and benchmark details are not included.
- REKI is a 2.4 billion-parameter vision-language-action model
- It targets robot manipulation with more efficient memory use
- The model is presented by AI lab Kyutai
- Supplied page text is mostly cookies, so benchmarks are unavailable
From the original article
14 min read at marktechpost.comKyutai, with Inria and École des Ponts, has released REKI, a 2. 4B vision-language-action model (VLA) for robot manipulation. The REKI vision-language-action model is pretrained only on public data.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.