Perceptron 开源 360 亿参数机器人模型检查点

原标题:Robotics is getting the pretrained-checkpoint economy that made language models move so fast.
72AI 研判分

Perceptron AI 在 Hugging Face 与 LeRobot 上发布了 360 亿参数机器人模型的即用型检查点,每个检查点已针对特定机械臂完成微调。用户下载匹配检查点后即可用纯文本指令驱动机器人,并可进一步微调适配自有任务。这标志着机器人领域开始形成类似语言模型的预训练检查点生态。

报道正文

Rohan Paul (@rohanpaul_ai) · 2026-11-20 17

Robotics is getting the pretrained-checkpoint economy that made language models move so fast.

Perceptron AI just released ready-to-run versions of its 36B-parameter robot model on Hugging Face, each already fine-tuned for a specific robot arm.

Owners of a supported arm download the matching checkpoint, and the arm acts on plain-text instructions, with the option to fine-tune it further for their own tasks.

↳ 引用 @perceptroninc (Perceptron AI): Isaac 0.5 now has ready-to-run checkpoints for YAM, SO-100/101, and LIBERO. Supported through Hugging Face 🤗 and LeRobot.

Download and run them today.

推文配图