AI Paper Atlas

Research map / Architectures and efficiency / Quantization

SHARP-Q: Spectral Hessian Alignment and Rectification for Post-training Quantization

Menghao Lv, Huiqiong Wang, Li Sun, Mingli Song

ICML 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs

Read the paper

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 Hessian-Aware Rectification (HAR) to MSE reconstruction (ablation)MSE baseline · ImageNet (ResNet-18, W2A2)Top-1 accuracy (%): 52.85 -> 54.18Improved
add HAR to MSE reconstruction (ablation)MSE baseline · ImageNet (RegNetX-600MF, W2A2)Top-1 accuracy (%): 40.06 -> 41.69Improved
add HAR to MSE reconstruction (ablation)MSE baseline · ImageNet (ViT-S, W3A3)Top-1 accuracy (%): 39.17 -> 40.51Improved
add HAR to MSE reconstruction (ablation)MSE baseline · ImageNet (DeiT-T, W3A3)Top-1 accuracy (%): 47.25 -> 48.63Improved
add Dynamic Fisher-Subspace Compensation (DFSC) on top of HAR (ablation)SHARP-Q · ImageNet (ViT-S, W3A3)Top-1 accuracy (%): 40.51 -> 66.93Improved
add DFSC on top of HAR (ablation)SHARP-Q · ImageNet (DeiT-T, W3A3)Top-1 accuracy (%): 48.63 -> 56.14Improved
add DFSC on top of HAR (ablation)SHARP-Q · ImageNet (RegNetX-600MF, W2A2)Top-1 accuracy (%): 41.69 -> 46.89Improved
add DFSC on top of HAR (ablation)SHARP-Q · ImageNet (ResNet-18, W2A2)Top-1 accuracy (%): 54.18 -> 56.74Improved
use SHARP-Q instead of CL-CalibCNN PTQ · ImageNet (ResNet-18, W2A2)Top-1 accuracy (%): 54.45 -> 56.74Improved
use SHARP-Q instead of CL-CalibCNN PTQ · ImageNet (RegNetX-600MF, W2A2)Top-1 accuracy (%): 42.19 -> 46.89Improved
use SHARP-Q instead of CL-CalibCNN PTQ · ImageNet (ResNet-50, W4A4)Top-1 accuracy (%): 75.38 -> 75.25No clear effect
use SHARP-Q instead of CL-CalibCNN PTQ · ImageNet (MNasNet, W2A4)Top-1 accuracy (%): 63.46 -> 63.44No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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