SR-LoRA sets each LoRA layer's rank to the stable rank of that layer's pretrained weight matrix, improving few-shot transfer on large domain gaps without rank search.
Parameter-efficient fine-tuning of large-scale pre-trained language models.Nature Machine In- telligence, 5(3):220–235, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Low-Rank Tuning: Model Prior-Guided Rank Allocation for Effective Transfer in Low-Data and Large-Gap Regimes
SR-LoRA sets each LoRA layer's rank to the stable rank of that layer's pretrained weight matrix, improving few-shot transfer on large domain gaps without rank search.