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.
There’s plenty of room right here: Biological sys- tems as evolved, overloaded, multi-scale ma- chines.Biomimetics, 8(1)
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.