{"slug": "kyutai-cadre-video-autoencoders-that-cut-world-model-lag-below-230-ms", "title": "Kyutai CADRE: Video Autoencoders That Cut World Model Lag Below 230 ms", "summary": "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 a single Nvidia H100 and react in under 230 ms, according to the company. The release targets latency in interactive world models, where response lag limits real-time use.", "body_md": "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.\n\nThe post [Kyutai CADRE: Video Autoencoders That Cut World Model Lag Below 230 ms](https://www.marktechpost.com/2026/10/23/kyutai-cadre-video-autoencoders-interactive-world-models/) appeared first on [MarkTechPost](https://www.marktechpost.com).", "url": "https://wpnews.pro/news/kyutai-cadre-video-autoencoders-that-cut-world-model-lag-below-230-ms", "canonical_source": "https://www.marktechpost.com/2026/10/23/kyutai-cadre-video-autoencoders-interactive-world-models/", "published_at": "2026-10-23 23:26:53+00:00", "updated_at": "2026-10-24 01:12:26.824167+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "generative-ai", "ai-research", "ai-tools"], "entities": ["Kyutai", "CADRE", "Nvidia", "H100", "MarkTechPost"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/kyutai-cadre-video-autoencoders-that-cut-world-model-lag-below-230-ms", "markdown": "https://wpnews.pro/news/kyutai-cadre-video-autoencoders-that-cut-world-model-lag-below-230-ms.md", "text": "https://wpnews.pro/news/kyutai-cadre-video-autoencoders-that-cut-world-model-lag-below-230-ms.txt", "jsonld": "https://wpnews.pro/news/kyutai-cadre-video-autoencoders-that-cut-world-model-lag-below-230-ms.jsonld"}}