AI RESEARCH
Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models
arXiv CS.LG
•
ArXi:2604.15609v1 Announce Type: new Test-Time Adaptation (TTA) for black-box models accessible only via APIs remains a largely unexplored challenge. Existing approaches such as post-hoc output refinement offer limited adaptive capacity, while Zeroth-Order Optimization (ZOO) enables input-space adaptation but faces high query costs and optimization challenges in the unsupervised TTA setting. We