Orthogonal growth recycles pre-trained MoE checkpoints via layer copying and noisy expert duplication, delivering 10.6% higher accuracy than training from scratch with equivalent extra compute.
All research ideas, methods, experiments, and analyses were fully developed and con- ducted by the authors
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts
Orthogonal growth recycles pre-trained MoE checkpoints via layer copying and noisy expert duplication, delivering 10.6% higher accuracy than training from scratch with equivalent extra compute.