AI Squawk the real-time terminal for AI news

↗

RELEASE 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.

Source tier 3: +10
Category RELEASE: +30
Other adjustment (same-source burst decay, or scored under an earlier weighting): −5
Base score: 35
Velocity (0 corroborating sources): +0
Model mention: not accelerating vs. the prior week, no velocity bonus
Age decay (21d since published): −35
Effective score right now: 0