Signals 4 · free daily AI digest

Predicting Quantization Price for Selecting PTQ Configurations Before Deployment

Paper recorded by Signals 4 on 2026-09-23 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-23 on arXiv · recorded by Signals 4 on 2026-09-24

Category: cs.CL · 自然语言处理 · first seen 2026-09-24

Abstract

Weight-space post-training quantization (PTQ) must choose finite formats, granularities, quantizer families, transformations, and bits before the completed quantized model reveals its output-distribution drift. Existing PTQ methods predict important pieces of this degradation, including reconstruction error, Hessian sensitivity, transformation effects, and downstream loss, but these pieces are usu

Read on arXiv →

#6 most recent of 239 cs.CL papers we have recorded · ↑ newer: Towards Efficient Reasoning: Learning Causal Shortcuts for Diffusion L · ↓ older: Complementary Roles of Activation and Parametric Memory in Few-Shot Le
Cite this page: Predicting Quantization Price for Selecting PTQ Configurations Before Deployment: the #6 most recent of 239 cs.CL papers we have recorded (as of 2026-09-23). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/predicting-quantization-price-for-selecting-ptq-configurations-before-deployment.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions