AI & Computingpreprint2026-09-13

Inflation-Aware Quantization: Restoring INT4 Reasoning Token-Cost Parity with Distillation

Open access0 citations

Abstract

This manuscript is a non-peer-reviewed preprint.

// Source

View paper (DOI)Open access versionOpenAlexZenodo (CERN European Organization for Nuclear Research)Published 2026-09-13

Authors: Guan-Yuan Chen, Ya-Fen Yeh

Institutions: National Tsing Hua University, North Carolina Exploring Cultural Heritage Online