AI RESEARCH

CADS: Conformal Adaptive Decision System for Cost-Efficient Image Classification

arXiv CS.LG

ArXi:2605.16401v1 Announce Type: cross While high-capacity AI models have advanced state-of-the-art performance, their practical deployment is often hindered by high inference costs, environmental impact, and a "one-size-fits-all" approach that ignores varying sample complexity. In clinical settings for instance, the waste of computational resources on routine cases is a significant barrier to sustainable AI. In this paper, we