4 papers
SSR-GRPO: Integrating Supervision and Semantic IDs into Reinforcement Learning for Dense Retrieval in E-commerce
Guangxin Song, Xing Fang, Mingmin Jin +5
Embedding-based retrieval (EBR) is pivotal in e-commerce search but often struggles with complex semantics. While recent methods often fine-tune large language models (LLMs) for re…
TMallGS: Scaling Unified Feature and Sequence Modeling for Generative E-commerce Search
Zhentao Song, Yufeng Gao, Xing Fang +5
In industrial search and ranking systems, Click-Through Rate (CTR) prediction is shifting from traditional Deep Learning Recommendation Models (DLRM) toward unified, compute-intens…
Learning to Forget: Satiation-Aware Long-Sequence Transducers for Mitigating Post-Purchase Redundancy
Yipin Dai, Ruocong Tang, Xing Fang +4
Sequential recommendation models predominantly interpret user interactions as positive signals for preference accumulation. However, in e-commerce scenarios, a purchase action ofte…
DSIRM: Learning Query-Bridged Discrete Semantic Identifiers for E-commerce Relevance Modeling
Bokang Wang, Xing Fang, Mingmin Jin +4
Despite rapid progress of continuous embeddings for e-commerce search relevance, a long-standing open problem is the difficulty in capturing fine-grained attribute distinctions. Wh…