LiberAI 发布 Liber-0：用 220 万小时人类视频预训练的世界模型
LiberAI 用 220 万小时人类视频训练 Liber-0，不用一条机器人演示数据就跑了 60 个任务，做具身智能的可以看看这条路线。
LiberAI 发布了世界模型 Liber-0，预训练数据来自 220 万小时以上的人类经验记录。在没有任何目标任务的机器人演示数据的情况下，它在 60 个任务、600 次试验中达到 36.0% 的成功率。模型通过 action grounding 和 embodiment alignment 将人类经验转化为机器人可执行的动作。这种做法降低了对机器人采集数据的依赖，训练新任务不必再让机器人全程参与。
LiberAI just released Liber-0, a WAM pretrained on 2.2M+ hours of human experience.
With zero robot demos for the target task, it reached 36.0% success across 60 tasks and 600 trials. Action grounding and embodiment alignment let it turn human experience into actions a robot can execute.
Human experience is much easier to get than robot data. If this holds up, it could make collecting training data a lot faster and cheaper, and you wouldn't need a robot in the loop for every new task.
