Sulong Xu

Recommender systems aim to leverage user interaction signals to recommend items that users are likely to be interested in. Motivated by the success of Large Language Model (LLMs), generative recommendation (GR) has recently gained increasing attention, typically following a two-stage paradigm: su...

Novelty recommendation sustains long-term user engagement by exposing users to content that is both relevant and meaningfully different from their recent consumption. In large-scale e-commerce, this requires composing coherent yet non-redundant recommendation lists, a task fundamentally constrain...

Generative Retrieval (GR) offers a promising paradigm for recommendation through next-token prediction (NTP). However, scaling it to large-scale industrial systems introduces three challenges: (i) within a single request, the identical model inputs may produce inconsistent outputs due to the pagi...

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...

User interest modeling plays a vital role in industrial recommendation systems (RSs). Existing generative recommendation (GR) methods rely on single-step direct inference, which falls short of deeply modeling complex and dynamically evolving user interest. Recent chain-of-thought (CoT)-based GR m...