<ul><li>Continual learning aims to learn multiple tasks sequentially.</li><li>Pareto Continual Learning (ParetoCL) is a novel framework for balancing the stability and plasticity trade-off in continual learning.</li><li>ParetoCL formulates the trade-off as a multi-objective optimization problem and introduces a preference-conditioned model to dynamically adapt during inference.</li><li>Extensive experiments show that ParetoCL outperforms state-of-the-art methods in diverse continual learning scenarios.</li></ul>

Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off

Discover more