AI Paper Atlas

Research map / Video / Video segmentation and tracking

Relative Advantage Debiasing for Watch-Time Prediction in Short-Video Recommendation

Emily Liu, Kuan Han, Minfeng Zhan, Bocheng Zhao, Guanyu Mu, Yang Song

AAAI 2026 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 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
use two-stage RAD-U instead of one-stage CQE (ablation)RAD · KuaiRand-Pure (10 user clusters)XGAUC: 0.7044 -> 0.7131Improved
use learned multiquantile embedding instead of CQE (ablation)RAD-U · KuaiRand-Pure (10 user clusters)Wasserstein distance: 9.3945 -> 2.2793Improved
replace exact empirical CDF with learned embedding (ablation)RAD · KuaiRand-PureXGAUC: 0.7131 -> 0.7101No clear effect
fuse user and video sides (RAD-UV) vs RAD-U (ablation)RAD · KuaiRand-PureXAUC: 0.7151 -> 0.7178Improved
fuse user and video sides (RAD-UV) vs RAD-V (ablation)RAD · KuaiRand-PureMAE: 18.050 -> 18.050No clear effect
fuse user and video sides (RAD-UV) vs RAD-V (ablation)RAD · KuaiRand-PureVideo Group XAUC: 0.6803 -> 0.6786Hurt
RAD instead of D2QRAD · KuaiRand-PureMAE: 19.763 -> 18.050Improved
RAD instead of CQERAD · Offline industrialVideo Group XAUC: 0.594 -> 0.631Improved
deploy RAD-UV vs production modelRAD · Online A/BSkip Rate: -0.8640%Improved
deploy RAD-V vs production modelRAD · Online A/BWatch Time: 0.0562%No 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