Understand this story
Kyutai releases the open-source causal diffusion representation autoencoder CADRE, aimed at interactive world models. According to a MarkTechPost report on October 24, 2026, CADRE runs at 20 fps on 1 H100, with action latency below 230 ms. The autoencoder contains 7 autoencoders of about 476M parameters each, paired with a frozen 86M DINOv3 ViT-B/16; the world model has 1.2B parameters, and the video resolution is 288×512. The report states a driving-scene FVD of 162.6, compared with 599.7 for Wan 2.2; however, the action-following ARR for robotic manipulation is 0.45, lower than 0.85 for Wan 2.2. The code uses the MIT license, the Hugging Face weights are CC BY-NC 4.0, and commercial licensing is not included. There are currently no subsequent development facts.
AI-generated from public reports
Latest development · Report
Kyutai open-sources CADRE video autoencoder, reducing world model action latency to under 230 msDevelopments
1 confirmed developments
- Source:MarkTechPost
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 24
MarkTechPost
Kyutai open-sources CADRE video autoencoder, reducing world model action latency to under 230 ms
Kyutai releases the open-source causal diffusion representation autoencoder CADRE, aimed at interactive world models, running at 20 fps on 1 H100 with action latency below 230 ms. CADRE contains 7 autoencoders of about 476M parameters each, paired with a frozen 86M DINOv3 ViT-B/16; the world model has 1.2B parameters, and the video resolution is 288×512. The driving-scenario FVD is 162.6, compared with 599.7 for Wan 2.2; however, the action-following ARR for robotic manipulation is 0.45, lower than 0.85 for Wan 2.2. The code uses the MIT license, the Hugging Face weights are CC BY-NC 4.0, and commercial authorization is not included.