Task alignment serves as an efficient proxy for hyperparameter selection in model merging, accelerating the process by orders of magnitude while preserving performance in vision models with heterogeneous decoders.
arXiv preprint arXiv:2412.12153 (2024) 3
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
ACE-Merging estimates task input covariances from parameter differences to enable closed-form data-free merging that reduces interference and outperforms prior baselines on vision and language tasks.
citing papers explorer
-
Task Alignment: A simple and effective proxy for model merging in computer vision
Task alignment serves as an efficient proxy for hyperparameter selection in model merging, accelerating the process by orders of magnitude while preserving performance in vision models with heterogeneous decoders.
-
ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation
ACE-Merging estimates task input covariances from parameter differences to enable closed-form data-free merging that reduces interference and outperforms prior baselines on vision and language tasks.