AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Length-Adaptive Interest Network for Balancing Long and Short Sequence Modeling in CTR Prediction

Zhicheng Zhang, Zhaocheng Du, Jieming Zhu, Jiwei Tang, Fengyuan Lu, Wang Jiaheng, Song-Li Wu, Qianhui Zhu, Jingyu Li, Hai-Tao Zheng, Zhenhua Dong

AAAI 2026 · Architectures and efficiency › Attention and transformers · approach: State space and recurrent sequence models · 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 LAIN to backbonesDIN/DIEN/SIM/SDIM/TWIN · EBNeRD-smallAUC: e.g. TWIN 0.6993 -> 0.7074Improved
add LAIN to backbonesDIN · MicroVideo1.7MGAUC: 0.7023 -> 0.7019 (AUC 0.7093 -> 0.7101)No clear effect
add LAIN to DIENDIEN · EBNeRD-smallGAUC: 0.7090 -> 0.7078Hurt
add LAIN to TWIN, short sequencesTWIN · MicroVideo1.7M (0-100 length)AUC: 0.7108 -> 0.7184Improved
add LAIN to TWIN, long sequencesTWIN · MicroVideo1.7M (200+ length)AUC: 0.7125 -> 0.7238Improved
add length-modulated attention (ablation)LAIN on TWIN · MicroVideo1.7MAUC: 0.7189 -> 0.7233Improved
add query-key conditioning (ablation)LAIN on TWIN · MicroVideo1.7MAUC: 0.7195 -> 0.7233Improved
add temperature scaling (ablation)LAIN on TWIN · MicroVideo1.7MAUC: 0.7212 -> 0.7233Improved
add length-conditioned prompting (ablation)LAIN on TWIN · MicroVideo1.7MAUC: 0.7228 -> 0.7233Improved
apply LAIN to short-term branch (ablation)LAIN on TWIN · MicroVideo1.7Mlogloss: 0.4137 -> 0.4097Improved
add LAIN lowers attention Ginibaseline CTR models · EBNeRD-smallGini coefficient: 0.346 -> 0.318 (short, L=1000 baseline)Improved
vary prompt/Fourier/hidden dims (12 configs) (ablation)LAIN on TWIN · MicroVideo1.7MAUC: 0.7216 to 0.7248 vs baseline 0.7158No 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