CrossMean: Model Merging by Pairing Merged and Expert Activations

arXiv:2610.14762 · cs.LG · Submitted 2026-10-10 · Read on arXiv

cs.LG

Submitted: 2026-10-10

Updated: 2026-10-10

Terminology

• Model Merging — 1× in this paper · explained in 2 episodes

Sources

• Rethinking Layer-wise Model Merging through Chain of Merges
• Deep Learning for Classical Japanese Literature
• DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
• Gaussian Error Linear Units (GELUs)
• Fine-Grained Visual Classification of Aircraft
• Correcting Biased Centered Kernel Alignment Measures in Biological and Artificial Neural Networks
• Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks