HyperAdapt performs parameter-efficient fine-tuning by row- and column-wise diagonal scaling to induce high-rank updates with only n+m trainable parameters.
Soufiane Hayou, Nikhil Ghosh, and Bin Yu
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HyperAdapt: Simple High-Rank Adaptation
HyperAdapt performs parameter-efficient fine-tuning by row- and column-wise diagonal scaling to induce high-rank updates with only n+m trainable parameters.