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

24 October 2026 3 min read هدهد تك | Hudhud Tech

Kyutai has released CADRE, a family of open causal diffusion video autoencoders for interactive world models. The primary focus of the CADRE video autoencoder is to minimize action lag. Many world models borrow autoencoders from text-to-video generators. Those autoencoders pack many frames into one latent, causing delays in action response. According to the research paper, CADRE world models run at 20 fps on 1 H100 and react within 230 ms.

TL;DR

Size: 7 autoencoders, each about 476M trained parameters plus a frozen 86M DINOv3 ViT-B/16. The world model is 1.2B parameters. Video runs at 288×512, 20 fps.
Runs on: 1 H100 (bf16, batch 1). Quantized variants: Not disclosed.
Performance: CADRE forms most of the latency-quality frontier. It is as fast and better in 42 of 48 comparisons with MIRA, Wan 2.2, Cosmos and LTX-2.
Best: Driving FVD of 162.6 (CADRE-2×16×16, 1 step) against 599.7 for Wan 2.2.
Worst: Robot manipulation action following (ARR) of 0.45 for CADRE-2×32×32, against 0.85 for Wan 2.2.

What is CADRE?

CADRE is a family of video autoencoders from Kyutai built for action-conditioned world models. A world model generates in the autoencoder’s latent space. So the autoencoder’s compression sets both cost per frame and action delay.

Compression is written τ×s×s. τ is frames per latent, and s is the spatial factor. The research gives the latency as τ/f plus generation and decode time. At τ = 8 and 20 fps, the chunk alone adds 400 ms. Humans notice their own movement lagging beyond about 230 ms.

How does CADRE work?

The encoder reuses the MIRA recipe. A frozen DINOv3 extracts per-patch features from each frame. One trained 3D convolution then compresses them into a 64-channel latent. Only this bottleneck changes between the 7 members.

The decoder is a causal diffusion transformer with 24 blocks. It streams chunk by chunk. Progressive self-distillation teaches it to decode in 1 or 2 steps. This happens in a single training stage, without an adversarial loss.

The autoencoders train on 23 public video sources, about 76k hours. The mix spans web, robot, driving and game video.

How was CADRE evaluated?

Kyutai trained the same 1.2B causal diffusion transformer on each autoencoder. It used 4 environments: robot manipulation (ABC), human manipulation (EgoDex), driving (PhysicalAI AV) and indoor navigation (RealEstate10K). Each model sees 2 s of real video, then generates 4.8 s.

Scores cover image quality (FID), motion quality (FVD) and action following (ARR). ARR uses a frozen inverse dynamics probe. An ARR of 1 matches real video.