Understand this story
Under the Cosmos world model platform, NVIDIA has added four new Cosmos 3 open-weight checkpoints, all post-trained versions of Cosmos 3 Nano, containing 16B trainable parameters and released under the OpenMDW1.1 license, permitting commercial and non-commercial use. The four models respectively target multi-view driving data generation, synchronized streaming simulation of cameras and LiDAR, simulator-controlled generation of photorealistic video, and video prediction from dual-arm robot actions. The original text also presents a four-stage training recipe covering bidirectional adaptation, teacher forcing, consistency distillation, and self-forcing.
AI-generated from public reports
Latest development · Report
NVIDIA Releases Four Open-Weight World Models in the Cosmos 3 SeriesDevelopments
1 confirmed developments
- Source:Hugging Face
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 6
Hugging FaceFirst-partySelected
NVIDIA Releases Four Open-Weight World Models in the Cosmos 3 Series
Under the Cosmos world model platform, NVIDIA has added four Cosmos 3 open-weight checkpoints, all post-trained versions of Cosmos 3 Nano, containing 16B trainable parameters and released under the OpenMDW1.1 license, which permits commercial and non-commercial use. The four models respectively target multi-view driving data generation, synchronized streaming simulation of cameras and LiDAR, simulator-controlled generation of photorealistic video, and video prediction from dual-arm robot actions. The original text also provides a four-stage training recipe covering bidirectional adaptation, teacher forcing, consistency distillation, and self-forcing.