conftrace_

gradient-to-weight ratio

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

entropy-guided masking (1) downstream adaptation (1) sparse fine-tuning (1) parameter-efficient fine-tuning (1)

Papers

GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation AAAI 2026