Pith. sign in

Explaining neural scaling laws

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

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Scaling Laws for Upcycling Mixture-of-Experts Language Models

cs.LG · 2025-02-05 · conditional · novelty 6.0

Upcycled MoE language-model loss follows a multiplicative power law in dense and upcycled training tokens, with a log-D1 interaction that caps the benefit of upcycling at large compute budgets.

citing papers explorer

Showing 1 of 1 citing paper.

  • Scaling Laws for Upcycling Mixture-of-Experts Language Models cs.LG · 2025-02-05 · conditional · none · ref 3

    Upcycled MoE language-model loss follows a multiplicative power law in dense and upcycled training tokens, with a log-D1 interaction that caps the benefit of upcycling at large compute budgets.