Multi-Concept Personalized VLM Benchmark
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Visual Question Answering | Multi-Concept Personalized VLM Benchmark | VQA Accuracy69.8 | 3 | |
| Visual Grounding | Multi-Concept Personalized VLM Benchmark | VG72.3 | 3 | |
| Recognition | Multi-Concept Personalized VLM Benchmark | Recognition Rate87.8 | 3 |
Showing 3 of 3 rows