ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

~ similar to 2606.23642· 20 results

cs.IRcs.AIcs.LGRecentMay 28, 2026

No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval

Lixuan Guo, Yifei Wang, Tiansheng Wen, Aosong Feng +2 more

The paper introduces Single-stage Sparse Retrieval (SSR), a method that replaces computationally expensive vector clustering with sparse autoencoding to achieve highly efficient multi-vector retrieval…

View →
cs.CVcs.AIcs.CLEmpiricalRecentAug 3, 2026

UEmbed: Unified Sparse and Dense Multimodal Embeddings

Tingyu Song, Mingxin Li, Yanzhao Zhang, Dingkun Long +4 more

The paper introduces UEmbed, a decoder-only multimodal embedding model that produces both sparse lexical and dense representations in one forward pass.

View →
cs.IRcs.CLEmpiricalRecentJun 15, 2026

SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG

Nathanaël Langlois

The paper proposes SCAR, an adaptive retrieval policy that improves recall in Retrieval-Augmented Generation by selectively expanding neighboring chunks.

View →
cs.IREmpiricalRecentNov 12, 2026

AntEmbed: Dual-Mode Multimodal Embedding Model for Efficient and Fine-Grained Retrieval

Kehang Jia, Teng Liu, Juntao Li, Hua Chen +3 more

The paper proposes AntEmbed, a dual-mode multimodal embedding model for efficient retrieval and reasoning-enhanced fine-grained matching.

View →
cs.CLRecentMay 31, 2026

LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning

Mengmeng Ji, Ravi Shanker Raju, Jonathan Lingjie Li, Chen Wu

LongAttnComp introduces a novel, two-stage fine-tuning framework for context compression that significantly improves long-context reasoning performance, matching or exceeding full-context accuracy on…

View →
cs.IREmpiricalRecentJun 18, 2026

Stellar: Scalable Multimodal Document Retrieval for Natural Language Queries

Yuxiang Guo, Zhonghao Hu, Yuren Mao, Yuhang Liu +4 more

This paper presents Stellar, a scalable multimodal document retrieval framework that reduces memory overhead and query latency without compromising retrieval effectiveness.

View →
cs.IREmpiricalRecentJul 7, 2026

Learn to Pool: Lightweight Fine-Tuning for Flexible Multi-Vector Compression

Stefan Josef

The paper proposes lightweight fine-tuning as an alternative to pooling-aware training for reducing vector count in late interaction models, achieving broad gains and high compression rates.

View →
cs.DCcs.AIcs.CLRecentJun 1, 2026

Self-Conditioned Positional HNSW for Overlap-Aware Retrieval in Chunked-Document RAG Systems: Method and Industrial Evidence-Quality Audit

Nataraj Agaram Sundar, Tejas Morabia

The paper introduces Self-Conditioned Positional HNSW (SCP-HNSW), a method that modifies chunk embeddings and retrieval process to mitigate redundant evidence retrieval from overlapping document chunk…

View →
cs.DScs.IRTheoreticalRecentJun 22, 2026

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings

Rajesh Jayaram

This paper proves that single-vector embeddings require a larger representation size than multi-vector embeddings to approximate certain similarities.

View →
cs.IREmpiricalRecentJun 22, 2026

Unified Multi-Task Relevance Modeling for E-Commerce: Comparing Task Routing Architectures Across LLMs and Cross-Encoders

Md Omar Faruk Rokon, Jhalak Nilesh Acharya, Shasvat Desai, Hong Yao +1 more

This paper proposes a unified multi-task framework for handling six different entity pair relationship types in e-commerce with a shared relevance model.

View →
cs.IRcs.CLEmpiricalRecentJul 21, 2026

PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID

Xiao Wang, Sean MacAvaney, Craig Macdonald

This paper introduces PLAID-PRF, a method for performing Pseudo-Relevance Feedback (PRF) over PLAID, a centroid-based dense retrieval model, to improve retrieval effectiveness.

View →
cs.IRcs.AIcs.CLEmpiricalRecentJun 16, 2026

Non-negative Elastic Net Decoding for Information Retrieval

Koki Okajima, Yasutoshi Ida, Tsukasa Yoshida, Yasuaki Nakamura

This paper proposes a new paradigm for information retrieval using dense embeddings, called Non-Negative elastic Net (NNN) decoding, which selects documents jointly with the context of the entire corp…

View →
cs.CLRecentMay 31, 2026

Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking

Fachrina Dewi Puspitasari, Chaoning Zhang, Jiaquan Zhang, Zhicheng Wang +5 more

The paper proposes InSemRAG, an enhanced RAG framework that improves retrieval accuracy and knowledge integrity by incorporating intent-aware retrieval and semantics-preserving chunking, achieving sta…

View →
cs.CLcs.IREmpiricalRecentJul 7, 2026

Inject or Navigate? Token-Efficient Retrieval for LLM Analysis of Transactional Legal Documents

Mahmoud Hany, Mourad ElSheraey, Mahmoud Said, Peter Naoum

This paper compares three methods for answering questions over legal documents: full-corpus injection, embedding retrieval, and LLM navigation over a compact structured index. The results show that th…

View →
cs.CLRecentMay 30, 2026

Chunking Methods on Retrieval-Augmented Generation - Effectiveness Evaluation Against Computational Cost and Limitations

Mateusz Śmigielski, Michał Rajkowski, Mateusz Zbrocki, Michał Bernacki-Janson +4 more

This study systematically evaluates a wide range of chunking methods for Retrieval-Augmented Generation (RAG) to assess their effectiveness and highlight the overlooked challenges associated with chun…

View →
cs.IREmpiricalRecentJul 11, 2026

SVD-RAG: Efficient Tree-Organized Retrieval-Augmented Generation via Singular Value Decomposition

Zhihui Sun

This paper introduces SVD-RAG, a cost-efficient and content-adaptive summarization method for hierarchical Retrieval-Augmented Generation systems using Singular Value Decomposition on dense sentence e…

View →