---
title: "Kyutai releases CADRE video autoencoders for low-latency world models"
url: https://www.parallelquant.com/posts/kyutai-releases-cadre-video-autoencoders-for-low-latency-world-models-7f920c
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/10/23/kyutai-cadre-video-autoencoders-interactive-world-models/
published: 2026-10-23T23:26:53.000Z
topics: ["research", "open source"]
publisher: "Parallel Quant"
---

# Kyutai releases CADRE video autoencoders for low-latency world models

*2026-10-23 · Source: [MarkTechPost](https://www.marktechpost.com/2026/10/23/kyutai-cadre-video-autoencoders-interactive-world-models/)*

Kyutai released CADRE, a family of 7 open causal diffusion video autoencoders for interactive world models. World models built on CADRE run at 20 frames per second on a single H100 GPU and react in under 230 ms.

**Why it matters:** Interactive world models have been held back by lag; sub-230 ms response on one GPU moves them toward real-time use in simulation, games and robot training. Releasing the autoencoders openly lets other labs build on the same latent space rather than training their own.

**Topics:** research, open source

---
Read the original: https://www.marktechpost.com/2026/10/23/kyutai-cadre-video-autoencoders-interactive-world-models/
Canonical: https://www.parallelquant.com/posts/kyutai-releases-cadre-video-autoencoders-for-low-latency-world-models-7f920c
Published by Parallel Quant — https://www.parallelquant.com