Vision Model Merging on Vision Model Merging 12 tasks
93.57Average Absolute AccuracyIndividual
Evaluation results
| Method | Links | ||
|---|---|---|---|
| IndividualBackbone=ViT-L-14, Fine-tuning setting=LoRA2026.03 | 93.57 | — | |
| IndividualBackbone=ViT-B-16, Fine-tuning setting=LoRA2026.03 | 90.76 | — | |
| IndividualBackbone=ViT-B-32, Fine-tuning setting=LoRA2026.03 | 88.9 | — | |
| DC-MergeBackbone=ViT-L-14, Fine-tuning setting=LoRA2026.03 | 83.62 | 89.31 | |
| Iso-CTSBackbone=ViT-L-14, Fine-tuning setting=LoRA2026.03 | 81.35 | 86.87 | |
| TSV-MBackbone=ViT-L-14, Fine-tuning setting=LoRA2026.03 | 79.67 | 85.13 | |
| KnOTS-TIESBackbone=ViT-L-14, Fine-tuning setting=LoRA2026.03 | 75.64 | 80.9 | |
| WUDI-MergingBackbone=ViT-L-14, Fine-tuning setting=LoRA2026.03 | 74.25 | 79.45 | |
| Task ArithmeticBackbone=ViT-L-14, Fine-tuning setting=LoRA2026.03 | 73.69 | 78.84 | |
| DC-MergeBackbone=ViT-B-16, Fine-tuning setting=LoRA2026.03 | 73.12 | 80.56 | |
| Iso-CTSBackbone=ViT-B-16, Fine-tuning setting=LoRA2026.03 | 71.52 | 78.87 | |
| TSV-MBackbone=ViT-B-16, Fine-tuning setting=LoRA2026.03 | 68.92 | 76.06 | |
| DC-MergeBackbone=ViT-B-32, Fine-tuning setting=LoRA2026.03 | 68.4 | 77.22 | |
| KnOTS-TIESBackbone=ViT-B-16, Fine-tuning setting=LoRA2026.03 | 66.35 | 73.38 | |
| Iso-CTSBackbone=ViT-B-32, Fine-tuning setting=LoRA2026.03 | 66.28 | 75.01 | |
| TSV-MBackbone=ViT-B-32, Fine-tuning setting=LoRA2026.03 | 65.3 | 73.86 | |
| WUDI-MergingBackbone=ViT-B-16, Fine-tuning setting=LoRA2026.03 | 65.29 | 72.29 | |
| Task ArithmeticBackbone=ViT-B-16, Fine-tuning setting=LoRA2026.03 | 64.26 | 71.12 | |
| KnOTS-TIESBackbone=ViT-B-32, Fine-tuning setting=LoRA2026.03 | 63.03 | 71.43 | |
| WUDI-MergingBackbone=ViT-B-32, Fine-tuning setting=LoRA2026.03 | 62.2 | 70.64 | |
| Task ArithmeticBackbone=ViT-B-32, Fine-tuning setting=LoRA2026.03 | 60.76 | 69.12 |