POEM constructs dynamic partial-order sequences from multi-task ranking scores to enhance real-time sequential recommendation, reporting 0.2% watch-time lifts when deployed on Kuaishou.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
POEM: Partial-Order Enhanced Real-Time Sequential Modeling for Recommendation
POEM constructs dynamic partial-order sequences from multi-task ranking scores to enhance real-time sequential recommendation, reporting 0.2% watch-time lifts when deployed on Kuaishou.