collaborators

11 papers

cs.CL2026

Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers

Yu Wang, Shengyao Zhuang, Xueguang Ma +4

A single model scale challenges the flexibility of a production retrieval system: some settings need it faster, others need a smaller index, and the right trade-off changes with th…

cs.IR2026

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget

Zhichao Xu, Xueguang Ma, Shengyao Zhuang +5

Modern reranking recipes---billion-scale cross-encoders, mixture-of-experts (MoE) backbones, and distillation against strong teachers---have outpaced the training infrastructure av…

cs.CL2026

Rethinking On-policy Optimization for Query Augmentation

Zhichao Xu, Shengyao Zhuang, Xueguang Ma +6

Recent advances in large language models (LLMs) have led to a surge of interest in query augmentation for information retrieval (IR). Two main approaches have emerged. The first pr…

cs.IR2026

Improving Long-Context Retrieval with Multi-Prefix Embedding

Zhenglin Yu, Xueguang Ma, Shengyao Zhuang +4

Long-context retrieval exposes a tension: single-vector embeddings lose fine-grained detail, while token-level multi-vector methods incur prohibitive storage. We propose Multi-Pref…

cs.IR2026

Towards Retrieving Interaction Spaces for Agentic Search

Shengyao Zhuang, Yuansheng Ni, Hengxin Fun +2

Retrieval for search agents is still inherited from non-agentic information retrieval: a retriever ranks the corpus and the agent reads a small set of returned documents. Recent di…

cs.IR2026

Layer-wise Token Compression for Efficient Document Reranking

Shengyao Zhuang, Zhichao Xu, Ivano Lauriola

Transformer-based document cross-encoder rerankers are a central component of modern information retrieval systems. Despite their success, these models suffer from high computation…