EvoESAP uses evolutionary search guided by a speculative-decoding-inspired ESAP metric to discover non-uniform layer-wise sparsity allocations for MoE expert pruning, improving generation accuracy up to 19.6% at 50% sparsity.
Finding fantastic experts in moes: A unified study for expert dropping strategies and observations
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3representative citing papers
Pruning pretrained MoE models outperforms training from scratch under fixed budget, different expert compression methods converge after continued training, and progressive pruning plus multi-token KD improves the final 23A2B model.
Moderate pruning of MoE models preserves in-domain biomedical utility and reliability but both degrade rapidly in cross-domain settings and at extreme pruning ratios.
citing papers explorer
-
EvoESAP: Non-Uniform Expert Pruning for Sparse MoE
EvoESAP uses evolutionary search guided by a speculative-decoding-inspired ESAP metric to discover non-uniform layer-wise sparsity allocations for MoE expert pruning, improving generation accuracy up to 19.6% at 50% sparsity.
-
SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training
Pruning pretrained MoE models outperforms training from scratch under fixed budget, different expert compression methods converge after continued training, and progressive pruning plus multi-token KD improves the final 23A2B model.
-
On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain
Moderate pruning of MoE models preserves in-domain biomedical utility and reliability but both degrade rapidly in cross-domain settings and at extreme pruning ratios.