Datature Blog

Learn how to finetune NVIDIA's Cosmos-Reason2 vision-language model on Datature Vi to bring chain-of-thought reasoning to physical AI applications like warehouse automation, enabling robots to not just detect objects but reason about safety, spatial relationships, and physical interactions.

SAM 3 is Meta’s next-generation segmentation model that shifts from geometric, prompt-based segmentation to concept-level understanding through Promptable Concept Segmentation, enabling open-vocabulary instance detection via text or visual exemplars.

This article introduces 3D segmentation, partitioning volumetric data into labeled regions for applications in medical imaging, robotics, and more. Focusing on 3D semantic segmentation, it uses the Swin UNETR architecture for brain tumor segmentation as an example. The article covers core concepts, training on the BraTS dataset including MRI normalization, input/output processing, computational challenges, and adapting Swin UNETR for 3D image classification.