Vision Model Merging on Vision Model Merging 16 tasks
92.11Average Absolute AccuracyIndividual
Evaluation results
| Method | Links | ||
|---|---|---|---|
| IndividualBackbone=ViT-L-14, Fine-tuning setting=LoRA2026.03 | 92.11 | — | |
| IndividualBackbone=ViT-B-16, Fine-tuning setting=LoRA2026.03 | 89.11 | — | |
| IndividualBackbone=ViT-B-32, Fine-tuning setting=LoRA2026.03 | 87.5 | — | |
| DC-MergeBackbone=ViT-L-14, Fine-tuning setting=LoRA2026.03 | 79.53 | 85.71 | |
| Iso-CTSBackbone=ViT-L-14, Fine-tuning setting=LoRA2026.03 | 77.5 | 83.65 | |
| TSV-MBackbone=ViT-L-14, Fine-tuning setting=LoRA2026.03 | 74.37 | 80.31 | |
| KnOTS-TIESBackbone=ViT-L-14, Fine-tuning setting=LoRA2026.03 | 72.19 | 77.98 | |
| WUDI-MergingBackbone=ViT-L-14, Fine-tuning setting=LoRA2026.03 | 71.79 | 77.59 | |
| DC-MergeBackbone=ViT-B-16, Fine-tuning setting=LoRA2026.03 | 70.57 | 78.91 | |
| Task ArithmeticBackbone=ViT-L-14, Fine-tuning setting=LoRA2026.03 | 69.98 | 75.58 | |
| Iso-CTSBackbone=ViT-B-16, Fine-tuning setting=LoRA2026.03 | 69.88 | 78.22 | |
| TSV-MBackbone=ViT-B-16, Fine-tuning setting=LoRA2026.03 | 67.21 | 75.35 | |
| DC-MergeBackbone=ViT-B-32, Fine-tuning setting=LoRA2026.03 | 66.27 | 75.8 | |
| Iso-CTSBackbone=ViT-B-32, Fine-tuning setting=LoRA2026.03 | 64.61 | 74.02 | |
| WUDI-MergingBackbone=ViT-B-16, Fine-tuning setting=LoRA2026.03 | 64.59 | 72.51 | |
| KnOTS-TIESBackbone=ViT-B-16, Fine-tuning setting=LoRA2026.03 | 64.31 | 72.29 | |
| TSV-MBackbone=ViT-B-32, Fine-tuning setting=LoRA2026.03 | 63.51 | 72.72 | |
| Task ArithmeticBackbone=ViT-B-16, Fine-tuning setting=LoRA2026.03 | 62.4 | 70.16 | |
| KnOTS-TIESBackbone=ViT-B-32, Fine-tuning setting=LoRA2026.03 | 61.78 | 70.78 | |
| WUDI-MergingBackbone=ViT-B-32, Fine-tuning setting=LoRA2026.03 | 61.24 | 70.27 | |
| Task ArithmeticBackbone=ViT-B-32, Fine-tuning setting=LoRA2026.03 | 60.04 | 68.94 |