Model Merging via Data-Free Covariance Estimation

arXiv:2604.01329 · cs.LG · Submitted 2026-04-01 · Read on arXiv

cs.LG

Submitted: 2026-04-01

Updated: 2026-09-30

Code: https://github.com/marawangamal/actmat

Terminology

• Model Merging — 3× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes

Sources

• Evaluating Large Language Models Trained on Code
• Olmo 3
• Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Merging by Matching Models in Task Parameter Subspaces
• Instruction-Following Evaluation for Large Language Models

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