This repository is dedicated to studying and organizing information about Model Merging.
Qualitatively characterizing neural network optimization problems (ICLR 2015)
Linear Mode Connectivity and the Lottery Ticket Hypothesis (ICML 2020)
Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs (NIPS 2018)
The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks (ICLR 2024)
Essentially No Barriers in Neural Network Energy Landscape (ICML 2018)
Averaging Weights Leads to Wider Optima and Better Generalization (UAI 2018)
Merging Models with Fisher-Weighted Averaging (NeurIPS 2022)
Git Re-Basin: Merging Models modulo Permutation Symmetries (ICLR 2023)
Editing Models with Task Arithmetic (ICLR 2023)
TIES-Merging: Resolving Interference When Merging Models (NeurIPS 2023)
Model Merging by Uncertainty-Based Gradient Matching (ICLR 2024)
ZipIt! Merging Models from Different Tasks without Training (ICLR 2024)
AdaMerging: Adaptive Model Merging for Multi-Task Learning (ICLR 2024)