Skip to main content
Search

# Cosmos 3

2 related articles

Subscribe to updates
  1. World models move to closed loop: a Transfer-Auto reference run on four GPUs returns seven 720p videos and 99 LiDAR sweeps

    NVIDIA has packaged world-foundation-model training, optimization and inference into Cosmos Framework, with agent-callable skills and checkpoints that run out of the box. Developers previously had to fit a model to their own sensors, action space and data, then get it into an application, two separate rework efforts. The released Cosmos 3 Nano simulation recipes cover driving, robotics and surgery: a Transfer-Auto reference run on four GPUs returns seven 720p videos and 99 LiDAR sweeps, while Sim-Auto, distilled into a causal few-step model, generates observations step by step from driving-policy input and returns them to the policy for closed-loop evaluation.

  2. NVIDIA opens four Cosmos 3 checkpoints so driving and dual-arm robots can act and see the next frame

    NVIDIA's Cosmos world-model development platform adds four open-weight checkpoints, each post-trained from Cosmos 3 Nano with 16B trainable parameters, covering multi-view driving data generation, synchronized camera-LiDAR streaming driving simulation, photorealistic rendering from simulator controls, and video prediction from dual-arm robot actions. The checkpoints ship with a four-stage post-training recipe under OpenMDW1.1, which permits commercial and non-commercial use; NVIDIA also states that measuring where these models faithfully support policy learning and evaluation, and where their limits lie, remains ahead.

You’re all caught up