Public KG record
LocateAnything-3B
Recorded overview
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Capabilities: feature extraction / embeddings
- Capabilities: object detection
- Integrations: transformers integration
- Integrations: safetensors integration
- Supported types: image input
- Supported types: text output
- Requirements: 3B parameters
Evidence coverage
The KG currently records 9 known information dimensions and has 9 undocumented dimensions, linked to 2 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- NVIDIA — develops
- WeVisOne-VL — competes with
- LocateAnything — part of
- WeVisOne-VL — competes with