Shared and domain-specific LoRAs are constrained to the column and left null spaces of pretrained weights, but experimental benefits are mixed.
Parameter-efficient fine-tuning for large models: A comprehensive survey
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
-
Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning
Shared and domain-specific LoRAs are constrained to the column and left null spaces of pretrained weights, but experimental benefits are mixed.