ASLoRA shares the low-rank A matrix across all layers and adaptively merges similar B matrices during fine-tuning, claiming LoRA-level or better performance with roughly 75% fewer trainable parameters.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ASLoRA: Adaptive Sharing Low-Rank Adaptation Across Layers
ASLoRA shares the low-rank A matrix across all layers and adaptively merges similar B matrices during fine-tuning, claiming LoRA-level or better performance with roughly 75% fewer trainable parameters.