Induction Labs 搞了个新套路：不用动作标签，只看视频就能学会模拟桌面、跳棋和台球物理。106B 参数的 MoE 模型，一次预训练就够了。
Induction Labs 推出 Imagination Models 架构，其候选模型 Photon-1 为稀疏 106B-A5B MoE，仅在未标注动作的原始视频上完成单次预训练。Photon-1 能够模拟桌面操作、玩跳棋，并建模台球物理。该架构挑战了传统需动作标签的预训练范式。
Induction Labs Photon-1 Simulates Desktops, Plays Checkers, and Models Billiard Physics From One Pretraining Run
Most agents that learn from video need to know what action produced each frame. Induction Labs is arguing that this requirement is the bottleneck. Last week, they released imagination models, a foundation model architecture that pretrains on raw video with no action labels at all. Their test system is Photon-1, a sparse 106B-A5B mixture-of-experts (MoE) […] The post Induction Labs Photon-1 Simulates Desktops, Plays Checkers, and Models Billiard Physics From One Pretraining Run appeared first on MarkTechPost .