Spatial enrichment on BLINK
59.2AccuracyS^3-FT
Evaluation Results
| Method | Links | |
|---|---|---|
| S^3-FTBackbone=Qwen3-VL-8B, Mode=Single-view2026.05 | 59.2 | |
| S^3-FTBackbone=Qwen3-VL-8B, Mode=Cross-viewpoint2026.05 | 57.5 | |
| Qwen3-VL-8BMode=base2026.05 | 57.1 | |
| Qwen2.5-VL-7BMode=base2026.05 | 54.4 | |
| S^3-FTBackbone=Qwen2.5-VL-7B, Mode=Single-view2026.05 | 53.7 | |
| S^3-FTBackbone=Qwen2.5-VL-7B, Mode=Cross-viewpoint2026.05 | 53.4 |