2 papers
cs.LG2026
CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning
Jingze Ge, Xue Geng, Yun Liu +6
To mitigate the memory constraints associated with fine-tuning large pre-trained models, existing parameter-efficient fine-tuning (PEFT) methods, such as LoRA, rely on low-rank upd…
cs.AI2026
Compress Then Adapt? No, Do It Together via Task-aware Union of Subspaces
Jingze Ge, Yun Liu, Xue Geng +4
Adapting large pretrained models to diverse tasks is now routine, yet the two dominant strategies of parameter-efficient fine-tuning (PEFT) and low-rank compression are typically c…