NVIDIA announces four open Cosmos 3 models for interactive simulation
🎧 Listen to this story
NVIDIA announced four open-weight checkpoints in the Cosmos 3 Nano family: Cosmos3-Nano-Transfer-Auto, Cosmos3-Nano-Sim-Auto, Cosmos3-Nano-Sim-Transfer and Cosmos3-Nano-Sim-Bimanual. The company says they generate driving data under varied environmental conditions, combine synchronized camera video and LiDAR observations, turn simulator controls into photorealistic video, and predict video from robot or camera actions.
The models have 16 billion trainable parameters and use OpenMDW1.1, which allows commercial and non-commercial use under its terms. Transfer-Auto can generate up to 11 camera views and joint RGB and LiDAR data, while its Sim-Auto variant produces continuous sequences for interactive simulations. NVIDIA presents the checkpoints as an open foundation for researchers and developers to adapt, while noting that their limits for policy training and evaluation still need to be assessed.
Why it matters · editorial interpretation
Opening these checkpoints could give researchers and developers an adaptable base for building simulations that combine video, LiDAR, and robot or camera actions. NVIDIA itself notes that the models’ limits for policy training and evaluation still need to be assessed, an important caution before using them in those contexts.