Progressive Semantic Residual Quantization for Multimodal-Joint Interest Modeling in Music Recommendation
对残差量化的修改
Recommendation
HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation
利用 LLM 高效生成个性化广告语
On the Reliability of Sampling Strategies in Offline Recommender Evaluation
不同采样策略在不同曝光偏差下的区分性, 鲁棒性, 一致性
SEvo
Is Every Item Worth An Embedding?
是否每个 Item 都值得一个可学习的 Embedding 呢