Kyutai CADRE: Autoencoders de video que reducen la latencia de los modelos de mundo a menos de 230 ms

Este es el extracto disponible del feed. Puede estar abreviado o en el idioma original.

Kyutai has released CADRE, open causal diffusion representation autoencoders for interactive world models. The Kyutai CADRE video autoencoder targets one problem: action lag. Many world models borrow autoencoders from text-to-video generators. Those autoencoders pack many frames into one latent, so every action waits. Per 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 p