Shared Low-rank Basis Factorization for Data-free Mixture-of-Experts Compression

cs.LG, cs.AI

Submitted: 2026-10-07

Updated: 2026-10-07

Comments: Accepted to Findings of EMNLP 2026

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Program Synthesis with Large Language Models
• Task-Specific Expert Pruning for Sparse Mixture-of-Experts
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Training Verifiers to Solve Math Word Problems
• Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations
• REAM: Merging Improves Pruning of Experts in LLMs
• Mixtral of Experts
• DeepSeek-V3 Technical Report
• Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
• Muon is Scalable for LLM Training
• MoLAE: Mixture of Latent Experts for Parameter-Efficient Language Models
• Qwen3 Technical Report
• Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts
• MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router
• 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