ShadowPEFT replaces distributed low-rank weight perturbations with a centralized, depth-shared shadow module that evolves parallel hidden states layer by layer, matching or beating LoRA and DoRA on generation and understanding tasks at similar parameter budgets.
Parameter-efficient fine-tuning for large models: A comprehensive survey.Trans
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning
ShadowPEFT replaces distributed low-rank weight perturbations with a centralized, depth-shared shadow module that evolves parallel hidden states layer by layer, matching or beating LoRA and DoRA on generation and understanding tasks at similar parameter budgets.