A framework for real-time LLM-based user interest personas in large-scale video recommendations, using distillation, async inference, and video clustering to balance interests with novel topics and improve viewer value via A/B tests.
Quiet Companionability Seeker
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
NBQ is a plug-and-play framework for adaptive question selection in conversations to produce structured user profiles, with QuickMatch enabling scalable reciprocal matching through approximate vector search.
citing papers explorer
-
LLM-Based User Personas for Recommendations at Scale
A framework for real-time LLM-based user interest personas in large-scale video recommendations, using distillation, async inference, and video clustering to balance interests with novel topics and improve viewer value via A/B tests.
-
NBQ: Next-Best-Question for Dynamic Profiling
NBQ is a plug-and-play framework for adaptive question selection in conversations to produce structured user profiles, with QuickMatch enabling scalable reciprocal matching through approximate vector search.