cd /news/artificial-intelligence/kyutai-cadre-video-autoencoders-that… · home › topics › artificial-intelligence › article
[ARTICLE · art-156503] src=marktechpost.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

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

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.

by read1 min views3 publishedOct 23, 2026

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.

source & further reading
marktechpost.com — original article Moonshot AI Releases Kimi K3.1 Pro: A 2.8T Total/104B Active Params (MoE) Model with 1M Context TinyFish Breaks Down Agentic Search Architecture for Production AI Agents You.com Launches Inference Router: 12 Open-Weight Models With 99.9% Uptime SLA
── more in #artificial-intelligence 4 stories · sorted by recency
── more on @kyutai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/kyutai-cadre-video-a…] indexed:0 read:1min 2026-10-23 · —