Block-LoRA partitions and shares the down-projection of LoRA, but this reduces mathematically to a standard LoRA with a lower rank.
Parameter-efficient fine-tuning of large-scale pre-trained language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
One Head Eight Arms: Block Matrix based Low Rank Adaptation for CLIP-based Few-Shot Learning
Block-LoRA partitions and shares the down-projection of LoRA, but this reduces mathematically to a standard LoRA with a lower rank.