AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Gradient-Aligned Calibration for Post-Training Quantization of Diffusion Models

Dung Anh Hoang, Cuong Pham, Trung Le, Jianfei Cai, Thanh-Toan Do

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 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
learn gradient-aligned sample weights for calibrationTFMQ-DM · CIFAR-10 W4A32FID: 4.73 -> 4.28Improved
learn gradient-aligned sample weightsTFMQ-DM · LSUN-Bedrooms W4A32FID: 3.60 -> 3.14Improved
learn gradient-aligned sample weightsTFMQ-DM · ImageNet W4A32FID: 10.50 -> 10.17Improved
learn gradient-aligned sample weightsTFMQ-DM · ImageNet W4A8FID/sFID: sFID 7.35 -> 7.55; FID 10.29 -> 9.96Mixed
apply to extreme 2/4-bit quantizationTFMQ-DM · ImageNet W2A4FID: 300.03 -> 226.27Improved
apply with few sampling steps (5)TFMQ-DM · ImageNet W4A32, 5 stepsFID: 19.10 -> 18.22Improved
lower temperature from 1 to 0.2 (ablation)Ours · CIFAR-10 W4A32FID: 4.28 -> 4.85Hurt
enlarge validation set from 5% to 20% (ablation)Ours · CIFAR-10 W4A32FID: 4.32 -> 4.75Hurt
more timestep groups (5 to 20) (ablation)Ours · CIFAR-10 W4A32FID: 4.28 -> 4.26No clear effect
use a single group (uniform task) instead of 5 (ablation)Ours · CIFAR-10 W4A32FID: 4.63 -> 4.28Improved

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