Models

Documentation for fine-tuning, exporting, and integrating models used with the VSS blueprint: embedding models for semantic search (RT-CV and RT-Embedding), and computer vision models for warehouse perception (TAO Sparse4D and RT-DETR).

Start with Model customization overview for a cross-service summary, then dive into the per-model pages below.

• Model customization overview
• RADIO-CLIP object embeddings
• Cosmos-Embed1 (video embedding)
• Sparse4D (3D multi-camera)
• RT-DETR (2D warehouse detection)