2 papers
cs.LG2025
MemLoRA: Distilling Expert Adapters for On-Device Memory Systems
Massimo Bini, Ondrej Bohdal, Umberto Michieli +3
Memory-augmented Large Language Models (LLMs) have demonstrated remarkable consistency during prolonged dialogues by storing relevant memories and incorporating them as context. Su…
cs.LG2025
DeLoRA: Decoupling Angles and Strength in Low-rank Adaptation
Massimo Bini, Leander Girrbach, Zeynep Akata
Parameter-Efficient FineTuning (PEFT) methods have recently gained significant popularity thanks to the widespread availability of large-scale pretrained models. These methods allo…