https://mu0.ai/tags/video/Recent content in Video on mu0Hugo -- 0.152.2en-usMon, 28 Sep 2026 09:00:00 +1000https://mu0.ai/posts/predicting-video-in-representation-space/Mon, 28 Sep 2026 09:00:00 +1000https://mu0.ai/posts/predicting-video-in-representation-space/A working plan: encode each video frame with a frozen image transformer, compress it into a handful of continuous visual tokens, and train a causal transformer to predict the next frame’s tokens — learning how scenes evolve without ever translating them into text or pixels.