Signals 4 · free daily AI digest

RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models

Paper recorded by Signals 4 on 2026-09-23 in cs.CV. 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.CV · 计算机视觉 · first seen 2026-09-24

Abstract

Deploying deep learning models on edge CPUs is bottlenecked by computational and memory constraints. Mixed-precision quantization promises to reduce inference latency while preserving accuracy. However, quantization affects different layer types in inconsistent ways, so identifying where accuracy loss is minimized and latency reduction is maximized is critical, as the effect accumulates over a ful

Read on arXiv →

#13 most recent of 301 cs.CV papers we have recorded · ↑ newer: Benchmarking Hyperspectral Foundation Models for Hyperspectral Unmixin · ↓ older: Generalizable Robotic Insertion with World Models
Cite this page: RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models: the #13 most recent of 301 cs.CV papers we have recorded (as of 2026-09-23). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/ramp-robust-adaptive-mixed-precision-quantization-for-edge-cpu-vision-models.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV 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