OMoE applies Gram-Schmidt orthogonalization to expert representations in LoRA-based mixture-of-experts, improving fine-tuning performance with only two experts.
Title resolution pending
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
-
OMoE: Diversifying Mixture of Low-Rank Adaptation by Orthogonal Finetuning
OMoE applies Gram-Schmidt orthogonalization to expert representations in LoRA-based mixture-of-experts, improving fine-tuning performance with only two experts.