Kyutai 发布 2.4B 视觉-语言-动作模型 REKI，带低成本记忆机制
Meet Kyutai REKI: The 2.4B VLA Model Bringing Efficient Memory to Robot Manipulation
法国团队 Kyutai 开源了 2.4B 的机器人操作模型 REKI，用公开数据训练还带记忆，比它大的模型才跑得过它。
Kyutai 联合 Inria 和 École des Ponts 发布机器人操作 VLA 模型 REKI，参数量 2.4B。该模型仅使用公开数据预训练，并带有对近期历史的低成本记忆机制。在三个分布外基准上，只有约两倍于它参数量的模型成绩超过它。全部权重已开源。
Meet Kyutai REKI: The 2.4B VLA Model Bringing Efficient Memory to Robot Manipulation
Kyutai, 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 .
