Multi-modal to multi-modal retrieval on OVEN (held-out)
67.6R@5UniIR-CLIPSF
Evaluation Results
| Method | Links | |
|---|---|---|
| UniIR-CLIPSFEvaluation Protocol=Supervised2026.06 | 67.6 | |
| ELVA-7B*Evaluation Protocol=Zero-shot, Training Exposure=Trained on other tasks without exposure to the three held-out tasks2026.06 | 64.4 | |
| LamRA-Ret*Evaluation Protocol=Zero-shot, Training Exposure=Trained on other tasks without exposure to the three held-out tasks2026.06 | 62.8 | |
| Vision-R1Evaluation Protocol=Zero-shot2026.06 | 57.4 | |
| UniIR-BLIPFFEvaluation Protocol=Supervised2026.06 | 55.8 | |
| Qwen2.5-VLEvaluation Protocol=Zero-shot2026.06 | 53.6 |