pith. sign in

Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes

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

Post-Trained MoE Can Skip Half Experts via Self-Distillation

cs.LG · 2026-05-18 · unverdicted · novelty 6.0

ZEDA injects zero-output experts and uses two-stage self-distillation to adapt post-trained MoE models into dynamic ones that skip over half the experts, yielding 1.2x inference speedup with small accuracy drops.

citing papers explorer

Showing 1 of 1 citing paper.

  • Post-Trained MoE Can Skip Half Experts via Self-Distillation cs.LG · 2026-05-18 · unverdicted · none · ref 35

    ZEDA injects zero-output experts and uses two-stage self-distillation to adapt post-trained MoE models into dynamic ones that skip over half the experts, yielding 1.2x inference speedup with small accuracy drops.