AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

DMGIN: How Multimodal LLMs Enhance Large Recommendation Models for Lifelong User Post-click Behaviors

Zhuoxing Wei, Qingchen Xie, Qi Liu, Jingsong Yu

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 2 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 interest statistics features (ablation)DMGIN-simple · IndustryAUC: 0.7129 -> 0.7134Improved
add intra-group behavior evolution (ablation)DMGIN-simple · IndustryAUC: 0.7110 -> 0.7134Improved
add interest statistics features (ablation)DMGIN-simple · AmazonAUC: 0.7679 -> 0.7701Improved
add intra-group behavior evolution (ablation)DMGIN-simple · AmazonAUC: 0.7685 -> 0.7701Improved
add interest statistics features (ablation)DMGIN-simple · IndustryGAUC: 0.6435 -> 0.6440Improved
add intra-group behavior evolution (ablation)DMGIN-simple · AmazonGAUC: 0.6984 -> 0.6986Improved
add temporal group evolution transformer (HSTU) on top of DMGIN-simple (ablation)DMGIN · IndustryAUC: 0.7134 -> 0.7161Improved
add temporal group evolution transformer (HSTU) on top of DMGIN-simple (ablation)DMGIN · AmazonAUC: 0.7701 -> 0.7747Improved
increase TGETM depth from 1 to 6 HSTU layers (ablation)DMGIN · AmazonAUC: about 0.3%-0.5% AUC gainImproved
use DMGIN instead of DSIN FullDSIN Full · IndustryAUC: 0.7121 -> 0.7161Improved
use DMGIN instead of DSIN FullDSIN Full · AmazonAUC: 0.7663 -> 0.7747Improved
use full lifelong sequences (DIN Full) instead of short-sequence DINDIN · AmazonAUC: 0.7245 -> 0.7634Improved

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