Frozen random backbones with low-rank LoRA adapters recover 96-100% of fully trained performance on diverse architectures while training only 0.5-40% of parameters.
Real-time computing without stable states: A new framework for neural computation based on perturba- tions.Neural Computation, 14(11):2531– 2560, 2002
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Little Rank Goes a Long Way: Random Scaffolds with LoRA Adapters Are All You Need
Frozen random backbones with low-rank LoRA adapters recover 96-100% of fully trained performance on diverse architectures while training only 0.5-40% of parameters.