PulseAugur
EN
LIVE 09:11:11

Research paper on action-aware video recommendation withdrawn

A research paper titled "Action-Aware Generative Sequence Modeling for Short Video Recommendation" has been withdrawn by its author, Wenhao Li. The paper proposed a novel modeling paradigm called Action-Aware Generative Sequence Network (A2Gen) to improve short video recommendations by considering the temporal sequence of user actions and their contextual features. Initial experiments on Kuaishou and Tmall datasets showed superiority, and a large-scale online A/B test on Kuaishou reported significant improvements in user watch time, interaction rate, and retention, leading to daily deployment for over 400 million users. AI

IMPACT A proposed AI model for short video recommendation was withdrawn by its author, removing potential advancements in user engagement and retention.

RANK_REASON The cluster contains a withdrawn academic paper. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Research paper on action-aware video recommendation withdrawn

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Wenhao Li, Zihan Lin, Zhengxiao Guo, Jie Zhou, Shukai Liu, Yongqi Liu, Chuan Luo, Chaoyi Ma, Ruiming Tang, Han Li ·

    Action-Aware Generative Sequence Modeling for Short Video Recommendation

    arXiv:2604.25834v2 Announce Type: replace Abstract: With the rapid development of the Internet, users have increasingly higher expectations for the recommendation accuracy of online content consumption platforms. However, short videos often contain diverse segments, and users may…