Induction Labs 发布 Photon-1 想象模型

Yann LeCun (@ylecun) 转发了 Haiyu Wu (@HaiyuWu1) 的帖子： Learning causality from internet videos in latent space first, and then using RL to teach the foundation model how to act. This approach is 30× cheaper than Gemini 3.1 Flash on pretraining and achieves a better result. JEPA is all you need! However, actions are still learned during post-training. Figuring out how to automatically learn actions without action labels is still very important! > **引用原帖 Induction Labs (@induction_labs):** > We’re introducing imagination models: a new foundation model architecture that unlocks learning from internet-scale video. > Our first imagination model, Photon-1, learned to use a computer by watching 18 years of screen recording video without action labels. https://t.co/DMhRqL28si > https://x.com/induction_labs/status/2080322704973160760