IT之家 2 月 12 日消息,小米今日对外发布开源 VLA 模型 Xiaomi-Robotics-0,拥有 47 亿参数、兼具视觉语言理解与高性能实时执行能力,刷新多项 SOTA。它不仅在三大主流的仿真测试中获得优异成绩,更在现实真机任务中实现了物理智能的泛化 —— 动作连贯、反应灵敏, 且能在消费级显卡上实现实时推理 。
Whether or not 2026 really is the big year of physical AI (I think it’s likelier to be the year when agentic AI breaks out) and robotics, much hype surrounds recent comments made by the great Nvidia ...
小米今日正式发布开源视觉语言动作(VLA)模型Xiaomi-Robotics-0,该模型以47亿参数规模实现视觉语言理解与实时动作执行的双重突破,在仿真测试与真实机器人任务中均刷新多项最优成绩。其核心创新在于构建了"感知-决策-执行"的完整闭环系统, ...
小米科技在机器人领域实现重大突破,其机器人团队近日正式开源发布全新具身智能VLA模型Xiaomi-Robotics-0,并首次对外公开真机运行画面,迅速引发科技界高度关注。该模型凭借47亿参数规模,不仅具备强大的视觉语言理解能力,还能实现高性能实时执行,为机器人技术发展注入新动能。
2月12日,小米雷军通过微博披露,小米机器人团队正式开源Xiaomi-Robotics-0,一个47亿参数的具身智能VLA模型。该模型采用Mixture-of-Transformers混合架构,在LIBERO、CALVIN和SimplerEnv三大仿 ...
Investing.com - Richtech Robotics Inc. (NASDAQ:RR) 股价在周二交易中跳涨44.6%,此前该公司宣布通过微软AI联合创新实验室与微软展开合作。根据 InvestingPro 数据,该股票在过去六个月内价格回报率达96.7%,继续保持其波动性交易模式,贝塔系数为-3.67,通常与更广泛的市场趋势呈反向变动。
After receiving “substantial inbound investor interest,” AI-powered robotics company Apptronik says it raised $520 million in an extension of its $415 million Series A in February 2025, bringing the ...
小米机器人团队开源发布全新具身智能VLA模型Xiaomi-Robotics-0,参数规模达47亿,具备视觉语言理解与高性能实时执行能力。该模型在三大主流仿真测试中横扫行业标杆,拿下全项SOTA成绩,并在真实机器人上实现流畅动作。其创新点在于能在消费级显卡上实现实时推理,打破高端模型依赖昂贵专业显卡的局限,降低技术落地门槛。小米自研的Mixture-of-Transformers架构为机器人装上“双 ...
Motiv Space Systems and PickNik Robotics Collaborate on Software for NASA’s Fly Foundational Robotics (FFR) Mission ...
Overview: AI robotics moves from labs to factories, warehouses, and homes, reshaping real-world operationsLeading companies integrate intelligence hardware and ...
Robotics stocks gain attention as AI advances boost drone defence, surgical robotics and hybrid autonomy across global markets.