Trending topics
#
Bonk Eco continues to show strength amid $USELESS rally
#
Pump.fun to raise $1B token sale, traders speculating on airdrop
#
Boop.Fun leading the way with a new launchpad on Solana.
EMER can rank short video content more intelligently.
It's an end-to-end multi-objective ensemble ranking framework that replaces manual heuristics with learned personalization. It designs a new loss for ambiguous supervision, uses a transformer-based architecture to model candidate relationships, and ensures offline-online consistency in evaluation.
Deployed at Kuaishou (hundreds of millions of users), EMER boosted app stay time by 1.39% and 7-day user lifetime by 0.196%—a major leap for industrial-scale recommendation systems.
An End-to-End Multi-objective Ensemble Ranking Framework for Video Recommendation
Paper:
Our report:

Top
Ranking
Favorites

