8 papers
BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE
Juntong Wu, Jialiang Cheng, Qishen Yin +5
Mixture-of-Experts (MoE) architectures enhance the efficiency of large language models by activating only a subset of experts per token. However, standard MoE employs a fixed Top-K…
SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE Models
Juntong Wu, Jialiang Cheng, Fuyu Lv +2
Mixture-of-Experts (MoE) architectures employ sparse activation to deliver faster training and inference with higher accuracy than dense LLMs. However, in production serving, MoE m…
Synthetic Data Powers Product Retrieval for Long-tail Knowledge-Intensive Queries in E-commerce Search
Gui Ling, Weiyuan Li, Yue Jiang +6
Product retrieval is the backbone of e-commerce search: for each user query, it identifies a high-recall candidate set from billions of items, laying the foundation for high-qualit…
Retrieval-GRPO: A Multi-Objective Reinforcement Learning Framework for Dense Retrieval in Taobao Search
Xingxian Liu, Dongshuai Li, Jiahui Wan +7
Dense retrieval, as the core component of e-commerce search engines, maps user queries and items into a unified semantic space through pre-trained embedding models to enable large-…
C2T-ID: Converting Semantic Codebooks to Textual Document Identifiers for Generative Search
Yingchen Zhang, Ruqing Zhang, Jiafeng Guo +4
Designing document identifiers (docids) that carry rich semantic information while maintaining tractable search spaces is a important challenge in generative retrieval (GR). Popula…
LLMs as Sparse Retrievers:A Framework for First-Stage Product Search
Hongru Song, Yu-an Liu, Ruqing Zhang +6
Product search is a crucial component of modern e-commerce platforms, with billions of user queries every day. In product search systems, first-stage retrieval should achieve high…