MyVLM
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Personalized Grounding | MyVLM | Precision100 | 14 | |
| Recognition | MyVLM | Single Recall98.4 | 11 | |
| Image Captioning | MyVLM | Caption Recall (Single)0.975 | 11 | |
| instance-aware caption generation | MyVLM benchmark | CLIP Image Similarity27.06 | 4 | |
| Instance Identification | MyVLM benchmark | Positive Score97 | 3 |
Showing 5 of 5 rows