PARA uses post-optimization SVD with a global singular-value threshold to allocate non-uniform ranks to LoRA layers, cutting parameters 75-90% with no loss in benchmark performance.
ISBN 9781479930227
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Post-Optimization Adaptive Rank Allocation for LoRA
PARA uses post-optimization SVD with a global singular-value threshold to allocate non-uniform ranks to LoRA layers, cutting parameters 75-90% with no loss in benchmark performance.