作者位次 #2/8ACL 2026Poster· Natural Language Processing
Evolutionary Negative Module Pruning for Better L o RA Merging
Anda Cao · Zhuo Gou · Yi Wang · Kaixuan Chen · Yu Wang · Can Wang · Mingli Song · Jie Song
摘要
Merging multiple Low-Rank Adaptation (LoRA) experts into a single backbone is a promising approach for efficient multi-task deployment. While existing methods strive to alleviate interference via weight interpolation or subspace alignment, they rest upon the implicit assumption that all LoRA matr...