AI RESEARCH
The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation
arXiv CS.LG
•
ArXi:2603.21928v1 Announce Type: cross Continual Test-Time Adaptation (CTTA) aims to enable models to adapt online to unlabeled data streams under distribution shift without accessing source data. Existing CTTA methods face an efficiency-generalization trade-off: updating parameters improves adaptation but severely reduces online inference efficiency. An ideal solution is to achieve comparable adaptation with minimal feature updates; we call this minimal subspace the golden subspace.