一作ACL 2026Poster· Natural Language Processing
K-Merge: Online Continual Merging of Adapters for On-device Large Language Models
Donald Shenaj · Ondrej Bohdal · Taha Ceritli · Mete Ozay · Pietro Zanuttigh · Umberto Michieli
摘要
On-device deployment of Large Language Models (LLMs) frequently leverages Low-Rank Adapters (LoRAs) to support diverse downstream tasks under tight resource constraints. To address the limited storage capacity of mobile devices, recent works have explored model merging techniques to fuse multiple...
效率与系统OpenReview 项目页