Reconstruction-Optimized Expert Pruning for Mixture-of-Experts Language Models
arXiv:2610.27123v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models reduce computation through sparse expert activation, but deployment still requires storing a large number of expert parameters. We study post-training expert pruning using task-domain calibration data as a subset-select…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-21 04:00 · arXiv cs.LG
Reconstruction-Optimized Expert Pruning for Mixture-of-Experts Language Models