AI Paper Atlas

Research map / Architectures and efficiency / Quantization

LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolution

Tianxing Wu, Zheng Chen, Cirou Xu, Bowen Chai, Yong Guo, Yutong Liu, Linghe Kong, Yulun Zhang

ICML 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs · 0 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 DRAQ instead of no scaling (ablation)LSGQuant (W4A4) · UDM10PSNR: 23.72 -> 23.80Improved
add DRAQ instead of no scaling (ablation)LSGQuant (W4A4) · UDM10DOVER: 0.3996 -> 0.4333Improved
use static calibrated channel scaling instead of DRAQ (ablation)LSGQuant (W4A4) · UDM10PSNR: 23.80 -> 20.04Hurt
use static calibrated channel scaling instead of DRAQ (ablation)LSGQuant (W4A4) · UDM10DOVER: 0.4333 -> 0.0231Hurt
add QAO (ablation)LSGQuant (W4A4) · UDM10PSNR: 23.23 -> 23.80Improved
add QAO (ablation)LSGQuant (W4A4) · UDM10DISTS: 0.2582 -> 0.2348Improved
add QAO (ablation)LSGQuant (W4A4) · UDM10DOVER: 0.4162 -> 0.4333Improved
three-tier VOLTS instead of uniform fully optimized training (ablation)LSGQuant (W4A4) · UDM10PSNR: 23.43 -> 23.80Improved
three-tier VOLTS instead of uniform lightly adapted training (ablation)LSGQuant (W4A4) · UDM10PSNR: 23.74 -> 23.80Improved
three-tier VOLTS instead of frozen + fully optimized only (ablation)LSGQuant (W4A4) · UDM10DOVER: 0.4571 -> 0.4333Mixed
three-tier VOLTS instead of frozen + lightly adapted only (ablation)LSGQuant (W4A4) · UDM10PSNR: 23.75 -> 23.80Improved
enlarge calibration set from 50 to 200 samples (ablation)LSGQuant (W4A4) · layer sensitivity thresholdsdelta_1,low (x1e-5): 3.03 -> 2.47No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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