1
Continual Learning of Domain-Invariant Representations
持续学习新方法：学习域不变表示，提升模型对未见领域的泛化能力，解决捷径学习问题。
arXiv:2605.15775v1 Announce Type: new Abstract: Continual learning (CL) aims to train models sequentially over multiple domains without forgetting pre…