AI Paper Atlas

Research map / Architectures and efficiency / Quantization

QuEPT: Quantized Elastic Precision Transformers with One-Shot Calibration for Multi-Bit Switching

Ke Xu, Yixin Wang, Zhongcheng Li, Hao Cui, Jinshui Hu, Xingyi Zhang

AAAI 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add weight clipping parameters (ablation)QuEPT · ImageNet ViT-S W4A4top-1 accuracy: 69.2 -> 70.1Improved
add MB-CLoRA to clipping (ablation)QuEPT · ImageNet ViT-Stop-1 accuracy: W4A4 70.1 -> 72.2; W6A6 80.2 -> 79.2; W8A8 81.1 -> 80.7Mixed
add MB-ToMe to clipping (ablation)QuEPT · ImageNet ViT-S W4A4top-1 accuracy: 70.1 -> 73.0Improved
add MB-ToMe on top of MB-CLoRA (ablation)QuEPT · ImageNet ViT-S W4A4top-1 accuracy: 72.2 -> 73.6Improved
use MAE loss instead of MSE loss (ablation)QuEPT · ImageNet ViT-S W4A4top-1 accuracy: 73.6 -> 74.7Improved
use cascaded MB-CLoRA instead of independent LoRA (ablation)QuEPT · LLaMA2-7B W4A4 0-shot avgaccuracy: 59.2 -> 61.6Improved
use cascaded MB-CLoRA instead of fully shared LoRA (ablation)QuEPT · LLaMA2-7B W4A4 0-shot avgaccuracy: 60.9 -> 61.6Improved
use cascaded MB-CLoRA instead of independent LoRA at high bits (ablation)QuEPT · LLaMA2-7B W7A7/W8A8accuracy: 65.7 vs 65.6No clear effect
use selective merge MB-ToMe instead of random selection (ablation)QuEPT · LLaMA2-7B W4A40-shot avg accuracy: 55.7 -> 61.6Improved
use selective merge MB-ToMe instead of uniform fusion (ablation)QuEPT · LLaMA2-7B W4A40-shot avg accuracy: 60.2 -> 61.6Improved
use selective merge MB-ToMe instead of random selection (ablation)QuEPT · ImageNet ViT-S W4A4top-1 accuracy: 74.5 -> 75.1Improved
use QuEPT multi-bit instead of PTMQQuEPT vs PTMQ · ImageNet ViT-B W6A6/W7A7/W8A8top-1 accuracy: +6.1%, +5.6%, +5.2%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy