3 papers
cs.LG2026
PGSB: Pretrained-Guided Shared Basis for LoRA Model Merging
Muqing Liu, Chongjie Si, Zhuoya Liu +1
Large pretrained models have achieved remarkable success across diverse domains, yet adapting them to multiple downstream tasks remains challenging: full fine-tuning is costly, whi…
cs.LG2026
FlexLoRA: Entropy-Guided Flexible Low-Rank Adaptation
Muqing Liu, Chongjie Si, Yuheng Jia
Large pre-trained models achieve remarkable success across diverse domains, yet fully fine-tuning incurs prohibitive computational and memory costs. Parameter-efficient fine-tuning…
cs.LG2025
Weight Spectra Induced Efficient Model Adaptation
Chongjie Si, Xuankun Yang, Muqing Liu +5
Large-scale foundation models have demonstrated remarkable versatility across a wide range of downstream tasks. However, fully fine-tuning these models incurs prohibitive computati…