MarkTechPost59

Kyutai CADRE: Video Autoencoders That Cut World Model Lag Below 230 ms

Name: AI HOT 精选数据集（復刻站）
License: https://aihot.yuenlau.org/llms.txt

2026/10/24 07:26· 4小时前

AI 摘要

Kyutai released CADRE, a family of 7 open causal diffusion video autoencoders for interactive world models. World models built on CADRE run at 20 fps on 1 H100 and react in under 230 ms. The post Kyutai CADRE: Video Autoencoders That Cut World Model Lag Below 230 ms appeared first on MarkTechPost .

查看原文（MarkTechPost）