iCreatAI News
Skip to content
Trending storyUpdating

NVIDIA releases four Cosmos 3 open-weight models

1 reports1 sources10 hr agoUpdated

Understand this story

AI overview

NVIDIA has added four Cosmos 3 open-weight checkpoints under the Cosmos world model platform, all post-trained versions of Cosmos 3 Nano, each with 16B trainable parameters, for generating interactive world simulations and multi-sensor, multi-view driving scenarios. The four models use the OpenMDW1.1 license, which permits commercial and non-commercial use under its terms. Running them requires Linux, an NVIDIA GPU, Docker, and the NVIDIA Container Toolkit; the vLLM-Omni configuration published by NVIDIA was tested on a single GB200, but that configuration is not a minimum VRAM requirement.

AI overview based on source reports · Updated 10 hr ago

Coverage timeline

Follow the coverage to explore different perspectives.

Nov 6
  1. Hugging Face BlogFeatured
    New NVIDIA Cosmos 3 Open Models for Interactive World Simulation

    NVIDIA's Cosmos world model platform adds four new open-weight checkpoints to its Cosmos 3 family: Cosmos3-Nano-Transfer-Auto for multi-view driving data with varied weather, lighting and time of day; Cosmos3-Nano-Sim-Auto for streaming synchronized camera and LiDAR driving simulation; Cosmos3-Nano-Sim-Transfer for turning simulator controls and text prompts into photorealistic video; and Cosmos3-Nano-Sim-Bimanual for predicting video from robot or camera actions. All four are post-trained examples of Cosmos 3 Nano with 16B trainable parameters and use OpenMDW1.1, permitting commercial and non-commercial use under its terms. The post also details a four-stage training recipe (bidirectional adaptation, teacher forcing, consistency distillation, self-forcing) and post-training guidance for adapting the models to new sensor rigs and embodiments.

Activity for this story

Current comparable activity
8
Peak comparable activity
10Nov 6 04:00
Change in the past 24 hours
–

Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.