作者位次 #9/11ACL 2026Findings· Findings of ACL
H yper A da L o RA : Accelerating L o RA Rank Allocation During Training via Hypernetworks without Sacrificing Performance
Hao Zhang · Zhenjia Li · Yifan Gao · Xi Xiao · Heng Zhang · Shuyang Zhang · Xiaoxincc · Bo Huang · Yuhang Wu · Tianyang Wang · Hao Xu
摘要
Parameter-Efficient Fine-Tuning (PEFT), especially Low-Rank Adaptation (LoRA), has emerged as a promising approach to fine-tuning large language models(LLMs) while reducing computational and memory overhead. However, LoRA assumes a uniform rank r for each incremental matrix, not accounting for th...