Haotian Wang

Generative Retrieval (GR) is rapidly transforming e-commercesearch by replacing traditional multi-stage pipelines with the autoregressivedecoding of structured Semantic IDs (SIDs). Despitethis architectural efficiency, aligning GR models with nuanced, realworlduser preferences remains a critical...

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,...

While semantic ID-based generative retrieval enables efficient end-to-end modeling in industrial applications, these methods face a persistent trade-off. On one hand, data-rich head items often suffer from ID collisions, which blur their distinct features and degrade downstream tasks. On the othe...

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...