pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

EPnG: Adaptive Expert Prune-and-Grow for Parameter-Efficient MoE Fine-tuning

cs.LG · 2026-07-02 · unverdicted · novelty 6.0

EPnG reallocates LoRA capacity in MoE models by pruning experts with low router gate probabilities and expanding high-importance ones via rank growth, outperforming standard LoRA and nearing full fine-tuning performance with 0.55-0.72% parameters updated.

citing papers explorer

Showing 1 of 1 citing paper.

  • EPnG: Adaptive Expert Prune-and-Grow for Parameter-Efficient MoE Fine-tuning cs.LG · 2026-07-02 · unverdicted · none · ref 20

    EPnG reallocates LoRA capacity in MoE models by pruning experts with low router gate probabilities and expanding high-importance ones via rank growth, outperforming standard LoRA and nearing full fine-tuning performance with 0.55-0.72% parameters updated.