Spatial enrichment on CV-Bench 2D
80AccuracyS^3-FT
Evaluation Results
| Method | Links | |
|---|---|---|
| S^3-FTBackbone=Qwen3-VL-8B, Mode=Single-view2026.05 | 80 | |
| S^3-FTBackbone=Qwen3-VL-8B, Mode=Cross-viewpoint2026.05 | 78.7 | |
| S^3-FTBackbone=Qwen2.5-VL-7B, Mode=Cross-viewpoint2026.05 | 77.3 | |
| S^3-FTBackbone=Qwen2.5-VL-7B, Mode=Single-view2026.05 | 76.6 | |
| Qwen2.5-VL-7BMode=base2026.05 | 75.2 | |
| Qwen3-VL-8BMode=base2026.05 | 70.3 |