GRFT selects whole rows or columns of weight matrices with the largest squared-gradient sums for fine-tuning, adds L2 regularization, and reports gains over GPS, LoRA, and adapters on FGVC, VTAB, and GLUE.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Gradient-based Fine-Tuning through Pre-trained Model Regularization
GRFT selects whole rows or columns of weight matrices with the largest squared-gradient sums for fine-tuning, adds L2 regularization, and reports gains over GPS, LoRA, and adapters on FGVC, VTAB, and GLUE.