MoRA: MoE Pruning via Router Bias Learning and Expert Approximation

arXiv:2610.00367 · cs.LG · Submitted 2026-09-30 · Read on arXiv

cs.LG

Submitted: 2026-09-30

Updated: 2026-09-30

Terminology

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

Sources

• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• LightMoE: Reducing Mixture-of-Experts Redundancy through Expert Replacing
• GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
• Muon is Scalable for LLM Training
• Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
• MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router
• Qwen3 Technical Report

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