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.
The power of scale for parameter-efficient prompt tuning
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.