List your company
ResearchFormerly WizWand

Model Merging on Sustainability to large-scale tasks 4 tasks

98.3Average AccuracyDOGE AM
84.88488.36791.8595.333Aug 5, 2025
Updated 6mo ago

Evaluation results

MethodLinks
DOGE AMBackbone=ViT-B/32, Method Category=Test-Time Adaption2025.0898.3
Layer-wise AdaMergingBackbone=ViT-B/32, Method Category=Test-Time Adaption2025.0896
TSV-MBackbone=ViT-B/32, Method Category=Data-Free2025.0895.9
RegMean++Backbone=ViT-B/32, Method Category=Training-Free2025.0895.6
RegMeanBackbone=ViT-B/32, Method Category=Training-Free2025.0895.5
DOGE TABackbone=ViT-B/32, Method Category=Data-Free2025.0893.9
Iso-CBackbone=ViT-B/32, Method Category=Data-Free2025.0893.7
Iso-CTSBackbone=ViT-B/32, Method Category=Data-Free2025.0893.7
Fisher MergingBackbone=ViT-B/32, Method Category=Training-Free2025.0890.2
Task ArithmeticBackbone=ViT-B/32, Method Category=Data-Free2025.0889.1
Model SoupsBackbone=ViT-B/32, Method Category=Data-Free2025.0888
TIES-MergingBackbone=ViT-B/32, Method Category=Data-Free2025.0885.4