Kyutai open-sources CADRE causal video autoencoders for real-time world models
Kyutai released seven causal video autoencoders, where each frame depends only on past frames, along with 1.2B-parameter world models built on them. The world models reach about 20 fps on a single H100 with action lag under a quarter second. Code is MIT-licensed and weights are non-commercial.
Why it matters
Targets the latency bottleneck that blocks playable, interactive video world models.
Source: Read the full story on Kyutai