Zhenlin He

Generative retrieval formulates document retrieval as an identifiergeneration task. While prevailing methods increasingly adopt SemanticIDs (SIDs), their opaque nature and rigid mappings strugglewith the dynamic inventory and strict interpretability requirementsof E-commerce search. Furthermore,...

Large-scale search and recommendation systems typically adopt a cascaded architecture of retrieval, pre-ranking, ranking, and re-ranking to balance efficiency and accuracy. However, pre-ranking still faces challenges of behavioral sparsity, limited interest diversity, and computational latency. W...