Amortized-Precision Quantization for Early-Exit Vision Transformers

ArXi:2605.07317v1 Announce Type: cross Vision Transformers (ViTs) achieve strong performance across vision tasks, yet their deployment with low-precision early exiting remains fragile. Existing quantization methods assume static full-depth execution, making them unstable when exit decisions are perturbed by quantization noise, which can amplify errors along dynamic inference paths. In this paper, we