From the source
NVIDIA expanded its Cosmos platform with new training tools, simulation checkpoints and Cosmos Data Factory blueprints so developers can build world models for physical AI systems.
- Cosmos Data Factory now offers five cloud-native blueprints, available through
GitHub,
Microsoft Azure, Nebius and CoreWeave, covering autonomous vehicle dataset generation, image attribute augmentation, event video generation, defect image generation and video data augmentation.
- NVIDIA says the platform ranks top five on six different open models leaderboards.
- At GTC Berlin, NVIDIA extended Cosmos Framework training, optimization and deployment tools and recipes as agent skills to more open models, along with Cosmos 3, letting developers adapt models such as GR00T, Alpamayo, QWEN and Pi0.5 through fine-tuning and reinforcement learning.
- New Cosmos 3 Nano model variants for simulation let developers test autonomous policies in repeatable, hard-to-capture, multiview multisensor scenarios, and updated Cosmos 3 NIM microservices deliver up to 2x faster inference with no quality loss in validated configurations.
- Porsche is using Cosmos Data Factory through Voxel51 on Microsoft Azure, which is expected to reduce repeated physical test drives by up to 90% and shorten development cycle times by up to 85%.
