Meet Kyutai REKI: The 2.4B VLA Model Bringing Efficient Memory to Robot Manipulation
Quick Answer
Kyutai, in collaboration with Inria and École des Ponts, has introduced REKI, a 2.4B vision-language-action model designed for efficient robot manipulation.
Quick Take
Pretrained on public data, REKI features a low-cost memory of its recent past and outperforms many larger models on three out-of-distribution benchmarks.
Key Points
- REKI is a 2.4B vision-language-action model for robot manipulation.
- The model is pretrained solely on publicly available data.
- REKI includes a low-cost memory feature for recent past actions.
- It ranks highly on three out-of-distribution benchmarks.
- Only larger models, about twice its size, outperform REKI.
Article Excerpt
From source RSS / original summaryKyutai, 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. It also carries a cheap memory of its recent past. On three out-of-distribution benchmarks, only models about twice its size beat it. All weights are live on […] The post Meet Kyutai REKI: The 2. 4B VLA Model Bringing Efficient Memory to Robot Manipulation 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 →Microsoft AI Releases Microsoft-Decision-1: A Qwen3.5-9B Decision-Scoring Model
Microsoft has launched Microsoft-Decision-1, a decision-scoring model derived from Alibaba's Qwen3.5-9B. This model focuses on routing, classification, verification, and agent control, providing calibrated probabilities for fixed answer options instead of generating text. It is now available in Microsoft Foundry and OpenRouter.