AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

iFusion: Integrating Dynamic Interest Streams via Diffusion Model for Click-Through Rate Prediction

Ziheng Ni, Congcong Liu, Yuying Chen, Zhiwei Fang, Changping Peng, Zhangang Lin, Ching Law, Jingping Shao

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools

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 disentangled classifier-free guidance (DCFG) instead of no guidance (ablation)iFusion · Industrial CTR datasetAUC: 0.7607 -> 0.7685Improved
add DCFG instead of standard CFG (ablation)iFusion · Industrial CTR datasetAUC: 0.7663 -> 0.7685Improved
add MARN autoregressive denoising instead of NAR-MLP (ablation)iFusion · Industrial CTR datasetAUC: 0.7644 -> 0.7685Improved
add MARN instead of NAR attention network (ablation)iFusion · Industrial CTR datasetAUC: 0.7650 -> 0.7685Improved
use AR attention network instead of MARN (ablation)iFusion · Industrial CTR datasetAUC: 0.7685 -> 0.7689No clear effect
add consistency loss (ablation)iFusion · Industrial CTR datasetAUC: 0.7686 -> 0.7685No clear effect
add consistency loss (ablation)iFusion · Industrial CTR datasetinference speed: 12.9 -> 16.2 batches/secImproved
increase sampling steps under consistency training (ablation)iFusion · Industrial CTR datasetAUCHurt
set core-interest guidance gamma_cp to 2.0 and gamma_tf to 1.0 (ablation)iFusion · Industrial CTR datasetAUC: 0.7685Improved
replace best baseline MTGR with iFusioniFusion · Amazon CTR datasetAUC: 0.8440 -> 0.8512Improved
replace best baseline MTGR with iFusioniFusion · Industrial CTR datasetAUC: 0.7648 -> 0.7685Improved
deploy iFusion online versus production baseiFusion · Online A/B testCTR: +2.44%Improved

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