AI RESEARCH

Representation Finetuning for Continual Learning

arXiv CS.AI

ArXi:2603.11201v1 Announce Type: cross The world is inherently dynamic, and continual learning aims to enable models to adapt to ever-evolving data streams. While pre-trained models have shown powerful performance in continual learning, they still require finetuning to adapt effectively to downstream tasks. However, prevailing Parameter-Efficient Fine-Tuning (PEFT) methods operate through empirical, black-box optimization at the weight level.