Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-task Model Merging Evaluation on Cross-task Utility Aggregate 8 Vision Datasets

67.23Average Accuracy

Unprotected Baseline

2.427619.251336.07552.8987Jun 29, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.06
67.23-
2026.06
67.1961.32
2026.06
67.1761.43
2026.06
67.1762.25
2026.06
66.8329.38
2026.06
37.45-
2026.06
5.87-
2026.06
5.74-
2026.06
4.92-