Approximate Nearest Neighbor Search

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 26

All topics

Better Nearest Neighbor Graph Indices via (Efficient) LLM-Guided Pruning
Sep 28, 2026Fangzhou Wu, Haike Xu, Sandeep SilwalSemantic Search Graph-Based Retrieval
University of Wisconsin–Madison · MIT
When Does Low-Bit Quantization Preserve the Decisions of Vector Search?
Sep 9, 2026Wenxuan Xiao, Xu CaoVector Quantization Low-Bit Quantization
Astrmira Tech.
A Power Law in Logarithm's Clothing: On the Scalability of Graph-Based Vector Search
Sep 2, 2026Sajad Faghfoor Maghrebi, Navid Eslami, Niv DayanApproximate Nearest Neighbor Search
University of Toronto Canada
RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search
Aug 31, 2026Rastislav Lenhardt, Teodora Dobos, Thomas Vecchiato +2Rotation-Based Quantization Vector Quantization
Google Zurich, Switzerland · Technical University of Munich Munich, Germany · University of Copenhagen Copenhagen, Denmark +1
QASP: Query-Adaptive Robust Vector Search Policy
Jul 31, 2026Hakan Ferhatosmanoglu, Kushal Kumar, Tal Wagner +1Approximate Nearest Neighbor Search
Amazon Vancouver, Canada
DSCH-Loss: A Dynamic Semantic Channel Objective for Deep Semantic Hashing
Jul 27, 2026Tobias J. Bauer, Christian Riess, Daniel Loebenberger +1Cross-Modal Representation Learning Cross-Modal Retrieval
Fraunhofer Institute for Applied and Integrated Security AISEC · Friedrich-Alexander-Universität Erlangen-Nürnberg · Ostbayerische Technische Hochschule Amberg-Weiden
ANNLib: A Development Framework for Efficient Approximate Nearest Neighbor Search
Jul 20, 2026Zheqi Shen, Jingbo Su, Zijin Wan +2Graph-Based Retrieval Approximate Nearest Neighbor Search
UC Riverside Riverside CA, USA · W&M Williamsburg VA, USA
D-NOVA: In-Storage Retrieval Accelerator via Dual-Bound 3D NAND-Optimized Similarity Search with Vector Adaptation
Jul 20, 2026Chang Eun Song, Sumukh Pinge, Tianqi Zhang +3Retrieval-Augmented Generation Dense Retrieval
University of California, San Diego La Jolla, USA
HNSW with Accuracy Guarantees Using Graph Spanners
Jul 2, 2026Minghao Li, Raghav Mittal, Sanjivni Rana +3Graph-Based Retrieval Approximate Nearest Neighbor Search
University of Toronto Toronto, Canada · The University of Texas At Arlington Arlington, Texas, USA · IIT Bombay Mumbai, India
Scaling Laws for Grid-Based Approximate Nearest Neighbor Search in High Dimensions
Jul 1, 2026Matthew J Liu, Wei Hang Zheng, Vidhan Purohit +4Approximate Nearest Neighbor Search
University of California, Berkeley · University of Toronto, St. George · Independent Researcher +1
Filtered ANN as a Phase Transition: When Selectivity-Estimation Error Causes Plan Regret
Jun 15, 2026Madhulatha Mandarapu, Sandeep KunkunuruRegret Minimization Dense Retrieval
VaidhyaMegha Private Limited, India
Aperon Technical Report: Hierarchical No-Pointer Tangent-Local Search for High-Dimensional Approximate Nearest Neighbors
Jun 7, 2026Yong FuLocal Search Approximate Nearest Neighbor Search
Substratum Labs
LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
Jun 3, 2026Shahrzad Esmat, Chaunte W. Lacewell, Sameh Gobriel +2Large Language Model-Guided Optimization Hyperparameter Optimization
Iowa State University · Intel Corporation
Distributional Approximate Nearest Neighbour Search for Uncertainty-Aware Retrieval
Jun 3, 2026Olivier JeunenRecommender Systems Approximate Nearest Neighbor Search
aampe · Antwerp, Belgium
ANN Search: Recall What Matters
Jun 3, 2026Dimitris Dimitropoulos, Nikos MamoulisIR Evaluation Approximate Nearest Neighbor Search
University of Ioannina & Archimedes, Athena RC · Ioannina, Greece
IVF-TQ: Calibration-Free Streaming Vector Search via a Codebook-Free Residual Layer
May 17, 2026Tarun SharmaVector Quantization Approximate Nearest Neighbor Search
Independent Researcher USA
Geometric Analysis of Self-Supervised Vision Representations for Semantic Image Retrieval
Apr 27, 2026Esteban Rodríguez-Betancourt, Edgar Casasola-MurilloNeural Representation Geometry Self-Supervised Visual Representation Learning
Posgrado en Computación e Informática Universidad de Costa Rica · Escuela de Ciencias de la Computación Universidad de Costa Rica
Large-Scale Data Parallelization of Product Quantization and Inverted Indexing Using Dask
Apr 23, 2026Ashley N. Abraham, Andrew Strelzoff, Haley R. Dozier +2Information Retrieval Product Quantization
Information Technology Laboratory, U.S Army Engineer Research and Development Center, Vicksburg, MS, USA · Environmental Laboratory, U.S Army Engineer Research and Development Center,2026 Vicksburg, MS, USA
2L-LSH: A Locality-Sensitive Hash Function-Based Method For Rapid Point Cloud Indexing
Apr 23, 2026Shurui Wang, Yuhe Zhang, Ruizhe Guo +3k-Nearest Neighbors Approximate Nearest Neighbor Search
School of Information Science and Technology, Northwest University, Xi’an, PR China
Semantic Recall for Vector Search
Apr 22, 2026Leonardo Kuffo, Ioanna Tsakalidou, Roberta De Viti +3IR Evaluation Approximate Nearest Neighbor Search
CWI · EPFL · MPI-SWS +1
Onyx: Cost-Efficient Disk-Oblivious ANN Search
Apr 22, 2026Deevashwer Rathee, Jean-Luc Watson, Zirui Neil Zhao +2Privacy-Preserving ML Approximate Nearest Neighbor Search
UC Berkeley, NVIDIA · NVIDIA · UT Austin, NVIDIA +1
Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments
Apr 21, 2026Jianyang Gao, Yutong Gou, Yuexuan Xu +5Vector Quantization KV-Cache Quantization
ETH Zurich · Nanyang Technological University · University of Michigan +2
Efficient K-generalizable Learned Search
Mar 6, 2026Yifan Peng, Jiafei Fan, Xingda Wei +7Inference-Time Search Graph-Based Retrieval
Shanghai Jiao Tong University · Boston University · Alibaba Group
Sublinear Sketches for Approximate Nearest Neighbor and Kernel Density Estimation
Oct 27, 2025Ved Danait, Srijan Das, Sujoy BhoreRandomized Sketching Kernel Density Estimation
Department of Computer Science & Engineering, Indian Institute of Technology Bombay, Mumbai, India. · Department of Computer Science & Engineering and Centre for Machine Intelligence & Data Science (CMINDS), Indian Institute of Technology Bombay, Mumbai, India.
Panorama: Fast-Track Nearest Neighbors
Oct 1, 2025Vansh Ramani, Alexis Schlomer, Akash Nayar +3Product Quantization Approximate Nearest Neighbor Search
IIT Delhi & CMU & UCPH · Carnegie Mellon University · Indian Institute of Technology Delhi +1
CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search
Aug 4, 2025Xiaoya Li, Albert Wang, Guoyin Wang +2Learning-Augmented Algorithms Approximate Nearest Neighbor Search
DeepReinforce Team
The kernel of graph indices for vector search
Jun 25, 2025Mariano Tepper, Ted WillkeGraph-Based Retrieval Kernel Methods
IBM WatsonX

Sep 28, 2026, cs.AIJ/K move · Enter open · S save

Better Nearest Neighbor Graph Indices via (Efficient) LLM-Guided Pruning

Fangzhou Wu, Haike Xu, Sandeep Silwal

University of Wisconsin–Madison · MIT

Semantic Search Graph-Based Retrieval Approximate Nearest Neighbor Search

Open paper AskPDF arXiv

Graph-based approximate nearest neighbor search (ANNS) is widely used for large-scale semantic search. Its indices are constructed primarily based on geometric relationships among embeddings of an input dataset (e.g., documents or images), rather than explicitly optimizing for semantic relevance. However, when using these indices for downstream query retrieval, performance is evaluated based on the semantic relevance of the retrieved results to the query. This creates a fundamental "geometry-semantic" mismatch between how the indices are constructed and how their retrieval results are evaluated. While existing LLM-based reranking methods can partially mitigate this mismatch at query time, they leave this underlying structural problem in the graph unresolved. We therefore propose LLM-Guided Graph Pruning (LGP), a general framework that addresses this mismatch directly by leveraging LLM reasoning to refine an existing ANN graph index itself. LGP identifies structurally "low-value" neighbors of nodes and replaces them with LLM-selected alternatives that provide useful semantic information while retaining desired geometric structures of the original graph, including sparsity and efficient navigability. Experiments on representative semantic retrieval benchmarks show that LGP consistently improves end-to-end retrieval performance over both vanilla greedy graph search and LLM-based reranking across widely used graph-based ANN indices such as DiskANN and HNSW.

Momentum

Related topics

Latest papers 26