RAG / 检索增强生成

Retrieval-GRPO: A Multi-Objective Reinforcement Learning Framework for Dense Retrieval in Taobao Search

检索-GRPO：面向淘宝搜索密集检索的多目标强化学习框架

Xingxian Liu, Dongshuai Li, Jiahui Wan, Tao Wen, Gui Ling, Yuliang Yan, Fuyu Lv, Dan Ou, Haihong Tang, Bo Zheng

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

AI总结 Retrieval-GRPO通过多目标强化学习框架解决密集检索中的硬负样本依赖和跷跷板效应问题，提升复杂长尾查询的语义泛化能力。

SVFusion: A CPU-GPU Co-Processing Architecture for Large-Scale Real-Time Vector Search

SVFusion：一种用于大规模实时向量搜索的CPU-GPU协同架构

Yuchen Peng, Dingyu Yang, Zhongle Xie, Ji Sun, Lidan Shou, Ke Chen, Gang Chen

专题命中 向量检索 ：vector search(title,abstract)；分类 cs.DB

AI总结 SVFusion通过CPU-GPU协同处理和动态更新机制，提升大规模实时向量搜索的性能和效率。

Comments This paper has been accepted for publication in PVLDB Volume 19(VLDB 2026)

Vector Search for the Future: From Memory-Resident, Static Heterogeneous Storage, to Cloud-Native Architectures

向未来迈进的向量搜索：从内存驻留、静态异构存储到云原生架构

Yitong Song, Xuanhe Zhou, Christian S. Jensen, Jianliang Xu

专题命中 向量检索 ：vector search(title,abstract)；分类 cs.DB

AI总结 本文从存储架构角度回顾了向量搜索技术的演变，涵盖内存驻留方法、异构存储技术及云原生系统的未来发展。

Comments Accepted as a tutorial at SIGMOD 2026

Cloud-Native Vector Search: A Comprehensive Performance Analysis

云原生向量搜索：全面性能分析

Zhaoheng Li, Wei Ding, Silu Huang, Zikang Wang, Yuanjin Lin, Ke Wu, Yongjoo Park, Jianjun Chen

专题命中 向量检索 ：vector search(title,abstract)；分类 cs.DB

AI总结 本文研究云原生向量搜索的性能，分析集群与图索引的优劣，指出图索引在高并发和高维数据场景中更优，并探讨缓存优化对索引性能的影响。

KBest: Efficient Vector Search on Kunpeng CPU

KBest: 面向 Kunpeng CPU 的高效向量搜索

Kaihao Ma, Meiling Wang, Senkevich Oleg, Zijian Li, Daihao Xue, Dmitriy Malyshev, Yangming Lv, Shihai Xiao, Xiao Yan, Radionov Alexander, Weidi Zeng, Yuanzhan Gao, Zhiyu Zou, Xin Yao, Lin Liu, Junhao Wu, Yiding Liu, Yaoyao Fu, Gongyi Wang, Gong Zhang, Fei Yi, Yingfan Liu

专题命中 向量检索 ：vector search(title,abstract)；分类 cs.IR

AI总结 KBest 是针对 Kunpeng 920 CPU 优化的高效向量搜索库，通过硬件感知和算法优化提升查询吞吐量超过 2 倍。

Journal ref ACM KDD 2026 | Jeju, Korea

Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval

Llama2Vec: 无监督适应大型语言模型用于密集检索

Zheng Liu, Chaofan Li, Shitao Xiao, Yingxia Shao, Defu Lian

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Beijing Academy of Artificial Intelligence（北京人工智能研究院） ； University of Science and Technology of China（中国科学技术大学） ； The Hong Kong Polytechnic University（香港理工大学） 纠错

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.CL

AI总结 Llama2Vec通过无监督适应LLM提升密集检索性能，实现新的最先进结果。

Comments ACL 2024

Does Generative Retrieval Overcome the Limitations of Dense Retrieval?

Yingchen Zhang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yixing Fan, Xueqi Cheng

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm

Jianting Tang, Dongshuai Li, Tao Wen, Fuyu Lv, Dan Ou, Linli Xu

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

Doc2Query++: Topic-Coverage based Document Expansion and its Application to Dense Retrieval via Dual-Index Fusion

Tzu-Lin Kuo, Wei-Ning Chiu, Wei-Yun Ma, Pu-Jen Cheng

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

Comments 11 pages, 4 figures

The Hybrid Multimodal Graph Index (HMGI): A Comprehensive Framework for Integrated Relational and Vector Search

Joydeep Chandra, Satyam Kumar Navneet, Yong Zhang

机构 * BNRIST, Tsinghua University（北京理工大学，清华大学） 纠错

专题命中 向量检索 ：vector search(title,abstract)；分类 cs.DB

Individualized non-uniform quantization for vector search

Mariano Tepper, Ted Willke

专题命中 向量检索 ：vector search(title,abstract)；分类 cs.IR

Graph-Based Vector Search: An Experimental Evaluation of the State-of-the-Art

Ilias Azizi, Karima Echihabi, Themis Palpanas

专题命中 向量检索 ：vector search(title,abstract)；分类 cs.IR

Gorgeous: Revisiting the Data Layout for Disk-Resident High-Dimensional Vector Search

Peiqi Yin, Xiao Yan, Qihui Zhou, Hui Li, Xiaolu Li, Lin Zhang, Meiling Wang, Xin Yao, James Cheng

专题命中 向量检索 ：vector search(title,abstract)；分类 cs.DB

Comments 12 pages, 19 figures

Filter-Centric Vector Indexing: Geometric Transformation for Efficient Filtered Vector Search

Alireza Heidari, Wei Zhang

专题命中 向量检索 ：vector search(title,abstract)；分类 cs.DB

Comments 9 pages

Static Pruning in Dense Retrieval using Matrix Decomposition

Federico Siciliano, Francesca Pezzuti, Nicola Tonellotto, Fabrizio Silvestri

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

GleanVec: Accelerating vector search with minimalist nonlinear dimensionality reduction

Mariano Tepper, Ishwar Singh Bhati, Cecilia Aguerrebere, Ted Willke

专题命中 向量检索 ：vector search(title,abstract)；分类 cs.IR

Designing Interfaces for Multimodal Vector Search Applications

Owen Pendrigh Elliott, Tom Hamer, Jesse Clark

专题命中 向量检索 ：vector search(title,abstract)；分类 cs.IR

Comments 12 pages, 8 figures, CIKM 2024 MMSR Workshop

Early Exit Strategies for Approximate k-NN Search in Dense Retrieval

Francesco Busolin, Claudio Lucchese, Franco Maria Nardini, Salvatore Orlando, Raffaele Perego, Salvatore Trani

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

Comments 6 pages, published at CIKM 2024

Interpreting Conversational Dense Retrieval by Rewriting-Enhanced Inversion of Session Embedding

Yiruo Cheng, Kelong Mao, Zhicheng Dou

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

Comments Accepted by ACL 2024. Repo: https://github.com/Ariya12138/ConvInv

Vector search with small radiuses

Gergely Szilvasy, Pierre-Emmanuel Mazaré, Matthijs Douze

专题命中 向量检索 ：vector search(title,abstract)；分类 cs.DB

Vector Search with OpenAI Embeddings: Lucene Is All You Need

Jimmy Lin, Ronak Pradeep, Tommaso Teofili, Jasper Xian

专题命中 向量检索 ：vector search(title,abstract)；分类 cs.IR

Generative Retrieval as Dense Retrieval

Thong Nguyen, Andrew Yates

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

Comments GenIR@SIGIR2023

Journal ref GenIR@SIGIR2023

Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data

Xinze Li, Zhenghao Liu, Chenyan Xiong, Shi Yu, Yu Gu, Zhiyuan Liu, Ge Yu

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

Comments Accepted by Findings of ACL 2023

A Personalized Dense Retrieval Framework for Unified Information Access

Hansi Zeng, Surya Kallumadi, Zaid Alibadi, Rodrigo Nogueira, Hamed Zamani

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

Comments Accepted to SIGIR 2023

Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval

Zhenghao Liu, Chenyan Xiong, Yuanhuiyi Lv, Zhiyuan Liu, Ge Yu

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

Comments Accepted by ICLR 2023

Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder

Zhenghao Liu, Han Zhang, Chenyan Xiong, Zhiyuan Liu, Yu Gu, Xiaohua Li

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

Comments Accepted by EMNLP 2022

Unsupervised Context Aware Sentence Representation Pretraining for Multi-lingual Dense Retrieval

Ning Wu, Yaobo Liang, Houxing Ren, Linjun Shou, Nan Duan, Ming Gong, Daxin Jiang

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

On Approximate Nearest Neighbour Selection for Multi-Stage Dense Retrieval

Craig Macdonald, Nicola Tonellotto

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

Query Embedding Pruning for Dense Retrieval

Nicola Tonellotto, Craig Macdonald

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval

Xiao Wang, Craig Macdonald, Nicola Tonellotto, Iadh Ounis

专题命中 向量检索 ：dense retrieval(title,abstract)；分类 cs.IR

Comments 10 pages

Journal ref Proceedings of ICTIR 2021