精选理由
开源、60K小时数据、覆盖多种机器人，LingBot-VLA 2.0 在长周期任务上表现出色，值得研究具身智能的你看一看。
LingBot-VLA 2.0 是全新开源具身模型，在单臂机器人到人形平台等多样化配置上训练。模型整合了60K小时精选机器人与人类数据，形成通用策略。在复杂长周期任务中显著提升机器人性能。由 @robbyant_brain 团队发布。
原文 · elvis
LingBot-VLA 2.0 is an impressive new embodied model. Open source and is trained across diverse robo...
LingBot-VLA 2.0 is an impressive new embodied model. Open source and is trained across diverse robot configurations, from single-arm robots to humanoid platforms. It packs 60K hours of curated robot and human data into one generalist policy. It improves robots on difficult long-horizon tasks. Great release by @robbyant_brain . Your browser does not support the video tag. 🔗 View on Twitter 💬 4 🔄 1 ❤️ 8 👀 2900 📊 6 ⚡