Flexi-LoRA adapts LoRA ranks to input complexity at both train and test time, achieving higher accuracy with fewer parameters on reasoning and speech tasks.
Available: https://aclanthology.org/N19-1246
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Flexi-LoRA with Input-Adaptive Ranks: Efficient Finetuning for Speech and Reasoning Tasks
Flexi-LoRA adapts LoRA ranks to input complexity at both train and test time, achieving higher accuracy with fewer parameters on reasoning and speech tasks.