Rethinking Weight-Averaged Model-merging

arXiv:2411.09263 · cs.LG, cs.CV · Submitted 2026-08-18 · Read on arXiv

Hu Wang, Congbo Ma, Ibrahim Almakky, Ian Reid, Gustavo Carneiro, Mohammad Yaqub

cs.LG, cs.CV

Submitted: 2026-08-18

Updated: 2026-08-19

Code: https://github.com/billhhh/Rethink-Merge

Terminology

• Model Merging — 53× in this paper · explained in 2 episodes
• Accuracy — 39× in this paper · explained in 1 episode
• Robustness — 14× in this paper · explained in 5 episodes
• Regularization — 11× in this paper · explained in 3 episodes
• Alignment — 8× in this paper · explained in 1 episode
• Interpretability — 8× in this paper · explained in 15 episodes
• Activation Function — 7× in this paper · explained in 1 episode
• Generalization — 5× in this paper · explained in 13 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• AUROC — 3× in this paper · explained in 2 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Distillation — 3× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Federated Learning — 2× in this paper · explained in 15 episodes
• AI Alignment — 1× in this paper · explained in 2 episodes
• Adversarial Robustness — 1× in this paper · explained in 3 episodes
• Area Under the Receiver Operating Characteristic Curve — 1× in this paper
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Convolutional Neural Networks (CNNs) — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 6 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Optimal Transport — 1× in this paper · explained in 5 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Vision Transformer (ViT) — 1× in this paper · explained in 2 episodes

Sources

• Git Re-Basin: Merging Models modulo Permutation Symmetries
• MedMerge: Merging Models for Effective Transfer Learning to Medical Imaging Tasks
• Model Merging by Uncertainty-Based Gradient Matching
• Controlled Text Generation via Language Model Arithmetic
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks
• Editing Models with Task Arithmetic
• REPAIR: REnormalizing Permuted Activations for Interpolation Repair
• MergeDistill: Merging Pre-trained Language Models using Distillation
• Deep Model Fusion: A Survey
• Efficient Estimation of Word Representations in Vector Space
• Equivariant Deep Weight Space Alignment
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Landscaping Linear Mode Connectivity
• How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
• ZipIt! Merging Models from Different Tasks without Training
• An Empirical Study of Multimodal Model Merging
• In-Model Merging for Enhancing the Robustness of Medical Imaging Classification Models
• Federated Learning with Matched Averaging
• Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks