MarkTechPost:Meet Kyutai REKI: The 2.4B VLA Model Bringing Efficient Memory to Robot Manipulation
原文摘要: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 onl 来源:MarkTechPost。建议继续查看原文,重点核对它影响的工具入口、成本、风险和真实使用场景。