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.
Explaining neural scaling laws
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Scaling Laws for Upcycling Mixture-of-Experts Language Models
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.