← Search

Yuqing DING

3 accepted papers

2026

OneSearch: A Preliminary Exploration of the Unified End-to-End Generative Framework for E-commerce Search

ICML 2026poster

Traditional e-commerce search systems employ multi-stage cascading architectures (MCA) that suffer from fragmented computation and optimization objective collisions across stages, ultimately limiting their performance ceiling. We propose OneSearch, the first industrial-deployed end-to-end generative…

Cited by 0SourceScholar
2025

InfoGain-RAG: Boosting Retrieval-Augmented Generation through Document Information Gain-based Reranking and Filtering

EMNLP 2025

Retrieval-Augmented Generation (RAG) has emerged as a promising approach to address key limitations of Large Language Models (LLMs), such as hallucination, outdated knowledge, and lacking reliable reference. However, current RAG frameworks often struggle with identifying whether retrieved documents

Cited by 0SourcePDFScholar