| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| element-level text-to-image alignment evaluation | RichHF | SRCC73.3 | 17 | |
| Artifact Localization | RichHF (test) | mIoU12.6 | 10 | |
| Human Feedback Score Prediction | RichHF-18K (test) | Text-image Alignment PLCC0.487 | 6 | |
| Visual Reasoning | RichHF | SRCC70.8 | 5 | |
| Implausibility heatmap prediction | RichHF-18K (test) | MSE (All data)0.0092 | 3 | |
| Text misalignment heatmap prediction | RichHF-18K GT = 0 (test) | MSE0.0001 | 3 | |
| Text misalignment heatmap prediction | RichHF-18K All data (test) | MSE0.003 | 3 |