PRIME: Frequency-Aware Unified Pruning and Merging for MoE Compression

arXiv:2610.13982 · cs.LG, stat.ML · Submitted 2026-09-23 · Read on arXiv

cs.LG, stat.ML

Submitted: 2026-09-23

Updated: 2026-09-23

Code: https://github.com/project-numina/aimo-progress-prize

Terminology

• Pruning — 1× in this paper · explained in 4 episodes

Sources

• Program Synthesis with Large Language Models
• DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning
• Evaluating Large Language Models Trained on Code
• Task-Specific Expert Pruning for Sparse Mixture-of-Experts
• Training Verifiers to Solve Math Word Problems
• Cluster-Driven Expert Pruning for Mixture-of-Experts Large Language Models
• Mixture Compressor for Mixture-of-Experts LLMs Gains More
• Fantastic Generalization Measures and Where to Find Them
• Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
• Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
• Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
• WizardCoder: Empowering Code Large Language Models with Evol-Instruct
• MergeMoE: Efficient Compression of MoE Models via Expert Output Merging
• MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router

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