5 papers
Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models
Zhikai Li, Yue Zhao, Edward Zhongwei Zhang +4
Reinforcement learning from human feedback (RLHF) effectively promotes preference alignment of text-to-image (T2I) diffusion models. To improve computational efficiency, direct pre…
Effective Knowledge Transfer for Multi-Task Recommendation Models
Guohao Cai, Jun Yuan, Zhenhua Dong
The conversion rate (CVR) is a crucial metric for evaluating the effectiveness of platforms, as it quantifies the alignment of content with audience preferences. However, the limit…
RecSys Arena: Pair-wise Recommender System Evaluation with Large Language Models
Zhuo Wu, Qinglin Jia, Chuhan Wu +4
Evaluating the quality of recommender systems is critical for algorithm design and optimization. Most evaluation methods are computed based on offline metrics for quick algorithm e…
A Parameter Update Balancing Algorithm for Multi-task Ranking Models in Recommendation Systems
Jun Yuan, Guohao Cai, Zhenhua Dong
Multi-task ranking models have become essential for modern real-world recommendation systems. While most recommendation researches focus on designing sophisticated models for speci…
Confidence-Aware Multi-Field Model Calibration
Yuang Zhao, Chuhan Wu, Qinglin Jia +6
Accurately predicting the probabilities of user feedback, such as clicks and conversions, is critical for advertisement ranking and bidding. However, there often exist unwanted mis…