精选理由
Robbyant这个视频动作模型直接用视频训练机器人，别家还没见过类似的。论文和代码全公开，搞机器人和具身智能的可以看看。
LingBot VA-V2是Robbyant（蚂蚁集团旗下）开发的视频动作基础模型，原生用于机器人控制。该模型接收视频输入即可生成机器人动作指令，无需额外传感器。项目页面和完整论文已在GitHub公开，提供技术细节与基准评测。
原文 · elvis
Very impressed with this video-action foundation model built natively for robot control, from @robby...
Very impressed with this video-action foundation model built natively for robot control, from @robbyant_brain , an embodied AI company under Ant Group. Project page. technology.robbyant.com/lingbot-va-v2 Paper: github.com/Robbyant/lingb… 💬 0 🔄 0 ❤️ 2 👀 159 📊 1 ⚡