As of Oct 23, MarkTechPost reports that Kyutai released CADRE, a family of seven open causal diffusion video autoencoders for interactive world models, with world models said to run at 20 fps on one H100 and react in under 230 ms.
Timeline · newest first
Reported by MarkTechPost
Kyutai open-sources CADRE causal diffusion video autoencoders for interactive world models, per MarkTechPost
Not confirmed by the company — reported on Oct 23, 2026 (source: marktechpost.com).
MarkTechPost reports that Kyutai released CADRE, a family of seven open causal diffusion video autoencoders for interactive world models, with world models said to run at 20 fps on one H100 and react in under 230 ms.