FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming Recommendation 文章

ArXiv CS.AI2026-05-28NEWSen作者: Xinhang Yuan, Zexi Huang, Anjia Cao, Xudong Lu, Zikai Wang, Penghao Zhou, Chang Liu, Wentao Guo, Qinglei Wang

摘要

arXiv:2605.21832v2 Announce Type: replace Abstract: Modern recommender systems rely heavily on ID-based collaborative filtering: each item is represented by a unique ID embedding that accumulates collaborative signals from user interactions. Livestreaming recommendation, however, faces a unique challenge in this paradigm: a live room typically broadcasts for only tens of minutes, so its item ID remains poorly learned in a persistent cold-start state and ID-centric ranking models fail to generalize. We present FLUID, the first framework to fully retire the candidate-side item ID from a production-scale livestreaming ranker. FLUID introduces a cross-domain multimodal encoder, jointly trained on short videos and livestreams, to produce discrete hierarchical semantic codes, called LUCID, for content-based item characterization.

相关公司

暂无数据

相关人物

暂无数据