World Models

Labeling 30,000 hours of video is an expensive path, and the bill scales fast. This article breaks down how the Latent Action Model (LAM) learns interaction from unlabeled images, and what that means economically and technically for agent training.

標註 30,000 小時影片的成本高昂。Genie 證明：只要數據夠純，模型自己會長出骨架。本文分析 LAM 如何從無標註影像中學習互動，以及這對 Agent 訓練的經濟與技術衝擊。