Rohan Paul· @rohanpaul_ai · X·· 2026-08-26AI 评分44
AI 导读
Skild 发布机器人基础模型 S1，用视频演示替代语言指令来定义任务。只需提供 1 段人类视频，S1 即可直接执行长达 10 分钟的多步骤新任务，无需重新训练或微调。若规模化，基础模型训练的高昂数据成本可摊薄至数千个新任务，有望改变机器人学习的经济性。
正文 · 原文
Robotics is more and more getting close to get its version of in-context learning.
Skild just released S1, a robot foundation model that uses video demonstrations to define tasks instead of language instructions.
Give S1 1 human video showing a long, multi-step task, and the robot executes it straight away. No retraining. No fine-tuning.
If this scales, you pay the enormous data bill once during foundation-model training, then amortize it across thousands of new tasks through prompting. That could change the economics of robot learning completely.
Introducing S1, our new foundation model that learns from one example. It can be taught 10-minute long tasks that it has never seen before, from one video prompt without any fine-tuning. Watch S1 operate in real-time via in-context learning:在 X 查看被引用的帖子
来源：Rohan Paul · x.com