AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Convection-Diffusion Equation: A Theoretically Certified Framework for Neural Networks

Tangjun Wang, Chenglong Bao, Zuoqiang Shi

TPAMI 2025 · Image generation › Fast diffusion sampling · approach: Diffusion theory and learned samplers · 5 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 diffusion layers after ResNet (ablation)ResNet · Prostate cancer classificationaccuracy: 78.23 -> 80.35Improved
add diffusion layers after ResNet (ablation)ResNet · Prostate cancer classificationAUPRC: 0.7100 -> 0.7598Improved
add diffusion layers after ResNet (ablation)ResNet · Prostate cancer classificationROC-AUC: 0.7635 -> 0.8001Improved
use graph-based COIN instead of GCNGCN · England COVID-19 missing dataMSE: 0.7607 -> 0.7168Improved
add recurrent temporal modulesDCRNN, MPNN-LSTM, EvolveGCN · England COVID-19 missing dataMSE: 0.8197 -> 0.9384Hurt
use COIN instead of Diff-ResNetDiff-ResNet · miniImageNet 1-shotaccuracy: 73.47 -> 74.85Improved
use COIN instead of Diff-ResNetDiff-ResNet · CUB 1-shotaccuracy: 87.74 -> 89.20Improved
use COIN on CiteseerDiff-ResNet · Citeseer node classificationaccuracy: 74.6 -> 75.8Improved
use COIN on CoraAPPNP · Cora node classificationaccuracy: 82.7 -> 82.2No clear effect
increase total diffusion strength K*sigma^2 (ablation)COIN · node classificationaccuracyMixed
double layers K from 20 to 40 at same total strength (ablation)COIN · node classificationaccuracyNo clear effect

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