AI RESEARCH

Abstraction as a Memory-Efficient Inductive Bias for Continual Learning

arXiv CS.LG

ArXi:2603.17198v1 Announce Type: new The real world is non-stationary and infinitely complex, requiring intelligent agents to from scratch. While online continual learning offers a framework for this setting, learning new information often interferes with previously acquired knowledge, causes forgetting and degraded generalization. To address this, we propose Abstraction-Augmented