This repo collects papers, documents, and codes about vector search for anyone who wants to research it. We are continuously improving the project. Welcome to PR the works (papers, repositories) that the repo misses.

last updated: 2026-03-07

• [arXiv] IVF-RaBitQ (GPU): GPU-Native Approximate Nearest Neighbor Search with IVF-RaBitQ [Hardware] [Compression]

• [arXiv] GPU-Accelerated Algorithms for Graph Vector Search: Taxonomy, Empirical Study, and Research Directions [Hardware] [Survey]

• [arXiv] Filtered Approximate Nearest Neighbor Search in Vector Databases: System Design and Performance Analysis [Filter] [Survey]

• [arXiv] UBIS: Updatable Balanced Index for Stable Streaming Similarity Search over Large-Scale Fresh Vectors [Streaming]

• [arXiv] LEMUR: Learned Multi-Vector Retrieval [Multi Vector]

• [SIGMOD] RAIRS: Optimizing Redundant Assignment and List Layout for IVF-Based ANN Search [IVF]

• [arXiv] GPU-Accelerated ANNS: Quantized for Speed, Built for Change [Hardware]

• [arXiv] Scalable Distributed Vector Search via Accuracy Preserving Index Construction [Distributed]

• [arXiv] Passing the Baton: High Throughput Distributed Disk-Based Vector Search with BatANN [Hardware]

• [SIGMOD] Distribution-Aware Exploration for Adaptive HNSW Search [Graph]

• [arXiv] Graph-Based Approximate Nearest Neighbor Search Revisited: Theoretical Analysis and Optimization [Graph] [Theory]

• [SIGMOD] SAQ: Pushing the Limits of Vector Quantization through Code Adjustment and Dimension Segmentation [Compression]

• [arXiv] Towards the Distributed Large-scale k-NN Graph Construction by Graph Merge [Graph] [Distributed]

• [arXiv] SINDI: an Efficient Index for Approximate Maximum Inner Product Search on Sparse Vectors [Sparse]

• [arXiv] Filtered Approximate Nearest Neighbor Search: A Unified Benchmark and Systematic Experimental Study [Experiment, Analysis & Benchmark] [Filter] [code]

• [arXiv] DISTRIBUTEDANN: Efficient Scaling of a Single DISKANN Graph Across Thousands of Computers [Graph] [Distributed]

• [arXiv] BAMG: A Block-Aware Monotonic Graph Index for Disk-Based Approximate Nearest Neighbor Search [Graph] [Hardware]

• [SIGMOD] WoW: A Window-to-Window Incremental Index for Range-Filtering Approximate Nearest Neighbor Search [Filter] [code]

• [arXiv] PGTuner: An Efficient Framework for Automatic and Transferable Configuration Tuning of Proximity Graphs [Tuning] [Graph]

• [SIGMOD] TRIM: Accelerating High-Dimensional Vector Similarity Search with Enhanced Triangle-Inequality-Based Pruning [DCO]

• [arXiv] Accelerating High-Dimensional Nearest Neighbor Search with Dynamic Query Preference [Tuning]

• [arXiv] CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search [Learning] [code]

• [arXiv] Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Search [Hybrid] [code]

• [arXiv] Benchmarking Filtered Approximate Nearest Neighbor Search Algorithms on Transformer-based Embedding Vectors [Filter] [Survey] [code]

• [arXiv] CleANN: Efficient Full Dynamism in Graph-based Approximate Nearest Neighbor Search [Streaming]

• [VLDB] SIEVE: Effective Filtered Vector Search with Collection of Indexes [Filter] [code]

• [VLDB] Breaking the Storage-Compute Bottleneck in Billion-Scale ANNS: A GPU-Driven Asynchronous I/O Framework [Hardware] [code]

• [arXiv] Towards Efficient and Scalable Distributed Vector Search with RDMA [Hardware]

• [arXiv] OneDB: A Distributed Multi-Metric Data Similarity Search System [Multimodel]

• [arXiv] Towards Robustness: A Critique of Current Vector Database Assessments [Experiment]

• [ISCA] REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing [Hardware]

• [KDD] Empowering Graph-based Approximate Nearest Neighbor Search with Adaptive Awareness Capabilities [Graph]

• [SIGMOD] HARMONY: A Scalable Distributed Vector Database for High-Throughput Approximate Nearest Neighbor Search [Distributed]

• [arXiv] EnhanceGraph: A Continuously Enhanced Graph-based Index for High-dimensional Approximate Nearest Neighbor Search [Graph] [code]

• [arXiv] LEANN: A Low-Storage Vector Index [Hardware]

• [OSDI] Quake: Adaptive Indexing for Vector Search [Streaming] [code]

• [SIGMOD] VecFlow: A High-Performance Vector Data Management System for Filtered-Search on GPUs [Filter] [Hardware] [code]

• [arXiv] VIBE: Vector Index Benchmark for Embeddings [Benchmark] [code]

• [arXiv] Cosmos: A CXL-Based Full In-Memory System for Approximate Nearest Neighbor Search [Hardware]

• [VLDB] HAKES: Scalable Vector Database for Embedding Search Service [Streaming] [code]

• [arXiv] Bang for the Buck: Vector Search on Cloud CPUs [Experiment]

• [arXiv] Survey of Filtered Approximate Nearest Neighbor Search over the Vector-Scalar Hybrid Data [Survey] [Filter] [code]

• [arXiv] RetroInfer: A Vector-Storage Approach for Scalable Long-Context LLM Inference [KVCache] [code]

• [arXiv] Efficient Graph-Based Approximate Nearest Neighbor Search Achieving: Low Latency Without Throughput Loss [Graph] [Serving]

• [arXiv] MINT: Multi-Vector Search Index Tuning [Tuning]

• [arXiv] TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate [Compression]

• [SIGIR] Dynamic Superblock Pruning for Fast Learned Sparse Retrieval [Sparse] [code]

• [SIGIR] Stitching Inner Product and Euclidean Metrics for Topology-aware Maximum Inner Product Search [MIPS] [code]

• [SIGMOD] AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference [KVCache]

• [SIGMOD] MicroNN: An On-device Disk-resident Updatable Vector Database [Hardware]

• [arXiv] ESG: Elastic Graphs for Range-Filtering Approximate 𝑘-Nearest Neighbor Search [Filter]

• [arXiv] LIRA: A Learning-based Query-aware Partition Framework for Large-scale ANN Search [Tuning]

• [arXiv] PilotANN: Memory-Bounded GPU Acceleration for Vector Search [Hardware]

• [arXiv] VSAG: An Optimized Search Framework for Graph-based Approximate Nearest Neighbor Search [Framework] [code]

• [VLDB] Maximum Inner Product is Query-Scaled Nearest Neighbor [MIPS] [code]

• [SIGMOD] PDX: A Data Layout for Vector Similarity Search [Hardware] [code]

• [WWW'25] Scalable Overload-Aware Graph-Based Index Construction for 10-Billion-Scale Vector Similarity Search [Graph]

• [SIGMOD] Accelerating Graph Indexing for ANNS on Modern CPUs [Graph] [code]

• [arXiv] In-Place Updates of a Graph Index for Streaming Approximate Nearest Neighbor Search [Streaming]

• [arXiv] Inference-time sparse attention with asymmetric indexing [KVCache]

• [SIGMOD] DEG: Efficient Hybrid Vector Search Using the Dynamic Edge Navigation Graph [Filter] [code]

• [arXiv] Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs [KVCache] [code]

• [arXiv] Scalable k-Means Clustering for Large k via Seeded Approximate Nearest-Neighbor Search [Clustering] [code]

• [SIGMOD] Graph-Based Vector Search: An Experimental Evaluation of the State-of-the-Art [Graph]

• [arXiv] Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search [Compression] [code]

• [ICLR] Qinco2: Vector Compression and Search with Improved Implicit Neural Codebooks [Compression] [code]

• [VLDB] SHG: Accelerating Approximate Nearest Neighbor Search in Hierarchical Graphs: Efficient Level Navigation with Shortcuts [Graph]

• [ISCA] ANSMET: Approximate Nearest Neighbor Search with Near-Memory Processing and Hybrid Early Termination [Hardware]

• [ICDE] Timestamp Approximate Nearest Neighbor Search over High-Dimensional Vectors [Filter] [Graph]

• [VLDB] Fast Graph Vector Search via Hardware Acceleration and Delayed Synchronization [Graph] [Hardware]

• [CIDR] VectraFlow: Integrating Vectors into Stream Processing [Streaming]

• [SIGMOD] Building Stateless Serverless Vector DBs via Block-based Data Partitioning [Database]

• [SIGMOD] High-Throughput, Cost-Effective Billion-Scale Vector Search with a Single GPU [Hardware] [code]

• [SIGMOD] Integrating Vector Databases across Embedding Models [Database]

• [SIGMOD] DiskJoin: Large-scale Vector Similarity Join with SSD [Hardware] [Database]

• [SIGMOD] Beyond Vector Search: Querying With and Without Predicates [Filter]

• [SIGMOD] Dynamically Detect and Fix Hardness for Efficient Approximate Nearest Neighbor Search [Graph] [code]

• [VLDB] Select Edges Wisely: Monotonic Path Aware Graph Layout Optimization for Disk-Based ANN Search [code]

• [SIGIR Tutorial] Neural Lexical Search with Learned Sparse Retrieval [Sparse]

• [OSDI] Achieving Low-Latency Graph-Based Vector Search via Aligning Best-First Search Algorithm with SSD [Graph] [Hardware]

• [SIGMOD] Efficient Dynamic Indexing for Range Filtered Approximate Nearest Neighbor Search [Filter] [code]

• [SIGMOD] DIGRA: A Dynamic Graph Indexing for Approximate Nearest Neighbor Search with Range Filter [Filter]

• [SIGMOD] MIRAGE-ANNS: Mixed Approach Graph-based Indexing for Approximate Nearest Neighbor Search [Graph] [code]

• [SIGMOD] RWalks: Random Walks as Attribute Diffusers for Filtered Vector Search [Filter] [Graph]

• [ICML] Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of Graphs [Graph]

• [ICML] Graph-Based Algorithms for Diverse Similarity Search [Filter] [Graph] [code]

• [ICDE] Boosting Accuracy and Efficiency for Vector Retrieval with Local Scaling Graph [Graph]

• [VLDB] UNIFY: Unified Index for Range Filtered Approximate Nearest Neighbors Search [Filter] [code]

• [VLDB] Efficient Data-aware Distance Comparison Operations for High-Dimensional Approximate Nearest Neighbor Search [DCO] [code]

• [SIGMOD] Subspace Collision: An Efficient and Accurate Framework for High-dimensional Approximate Nearest Neighbor Search [DCO]

• [SIGMOD] SymphonyQG: Towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor Search [Graph] [code]

• [arXiv] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference [KVCache] [code]

• [arXiv] Efficient and Effective Retrieval of Dense-Sparse Hybrid Vectors using Graph-based Approximate Nearest Neighbor Search [Hybrid] [Graph]

• [NeurIPS] LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search [Compression] [code]

• [arXiv] MagicPIG: LSH Sampling for Efficient LLM Generation [KVCache] [code]

• [VLDB] Revisiting the Index Construction of Proximity Graph-Based Approximate Nearest Neighbor Search [Graph] [code]

• [FAST] FusionANNS: An Efficient CPU/GPU Cooperative Processing Architecture for Billion-scale Approximate Nearest Neighbor Search

• [arXiv] RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval [KVCache]

• [SIGMOD] Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search [Compression] [code]

• [SIGMOD] iRangeGraph: Improvising Range-dedicated Graphs for Range-filtering Nearest Neighbor Search [Filter] [code]

• [VLDB] Steiner-Hardness: A Query Hardness Measure for Graph-Based ANN Indexes [Graph]

• [VLDB] RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search [Graph] [code]

• [CIKM] Pairing Clustered Inverted Indexes with kNN Graphs for Fast Approximate Retrieval over Learned Sparse Representations [Sparse]

• [CIKM] A Real-Time Adaptive Multi-Stream GPU System for Online Approximate Nearest Neighborhood Search [Hardware] [Streaming]

• [SIGMOD] PQCache: Product Quantization-based KVCache for Long Context LLM Inference [KVCache] [code]

• [arXiv] ColPali: Efficient Document Retrieval with Vision Language Models [Multi Vector] [Multimodal] [code]

• [arXiv] CANDY: A Benchmark for Continuous Approximate Nearest Neighbor Search with Dynamic Data Ingestion [Benchmark] [Streaming] [code]

• [VLDB] DET-LSH: A Locality-Sensitive Hashing Scheme with Dynamic Encoding Tree for Approximate Nearest Neighbor Search [LSH] [code]

• [NeurIPS] MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings [Multi Vector] [Compression]

• [SIGMOD] RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search [Compression] [code]

• [SIGIR] Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations [Sparse] [code]

• [ICDE] Effective and General Distance Computation for Approximate Nearest Neighbor Search [DCO] [code]

• [arXiv] AiSAQ: All-in-Storage ANNS with Product Quantization for DRAM-free Information Retrieval [Hardware] [code]

• [SIGMOD] GTS: GPU-based Tree Index for Fast Similarity Search [Hardware] [code]

• [NeurIPS] SOAR: Improved Indexing for Approximate Nearest Neighbor Search [IVF] [code]

• [arXiv] Dimensionality-Reduction Techniques for Approximate Nearest Neighbor Search: A Survey and Evaluation [Survey]

• [SIGMOD] ACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured Data [Filter]

• [ICML] Probabilistic Routing for Graph-Based Approximate Nearest Neighbor Search [Graph] [code]

• [ICML] Approximate Nearest Neighbor Search with Window Filters [Filter] [code]

• [ICML] Residual Quantization with Implicit Neural Codebooks [Compression] [code]

• [arXiv] BANG: Billion-Scale Approximate Nearest Neighbor Search using a Single GPU [Hardware] [code]

• [arXiv] Curator: Efficient Indexing for Multi-Tenant Vector Databases [Multitenancy]

• [SIGMOD] Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment [Hardware] [Graph] [code]

• [SIGMOD] Navigating Labels and Vectors: A Unified Approach to Filtered Approximate Nearest Neighbor Search [Filter] [code]

• [SIGMOD] SeRF: Segment Graph for Range-Filtering Approximate Nearest Neighbor Search [Filter] [Graph]

• [VLDB] SingleStore-V: An Integrated Vector Database System in SingleStore [Database]

• [SIGIR] Efficient Approximate Nearest Neighbor Search on a Raspberry Pi [Hardware]

• [ATC] Scalable Billion-point Approximate Nearest Neighbor Search Using SmartSSDs [Hardware]

• [SIGMOD] Vexless: A Serverless Vector Data Management System Using Cloud Functions [Serverless]

• [SIGMOD] FreshDiskANN: The DiskANN Library for Fast, Fresh, and Filtered Vector Search [Streaming] [Filter] [Graph] [code]

• [SOSP] SPFresh: Incremental In-Place Update for Billion-Scale Vector Search [Streaming]

• [ICDE] MUST: An Effective and Scalable Framework for Multimodal Search of Target Modality [Multimodal] [code]

• [MM] Relative NN-Descent: A Fast Index Construction for Graph-Based Approximate Nearest Neighbor Search [Graph] [code]

• [VLDB] Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models [Hardware] [code]

• [ICDE] CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs [Hardware] [Graph] [code]

• [arXiv] CAPS: A Practical Partition Index for Filtered Similarity Search [Filter] [code]

• [NeurIPS] XTR: Rethinking the Role of Token Retrieval in Multi-Vector Retrieval [Multi Vector]

• [SIGIR] SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes [Multi Vector] [Sparse]

• [NeurIPS] DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries [Multi Vector]

• [NeurIPS] An Efficient and Robust Framework for Approximate Nearest Neighbor Search with Attribute Constraint [Filter]

• [WWW] Filtered-DiskANN: Graph Algorithms for Approximate Nearest Neighbor Search with Filters [Filter]

• [ATC] CXL-ANNS: Software-Hardware Collaborative Memory Disaggregation and Computation for Billion-Scale Approximate Nearest Neighbor Search [Hardware] [Distributed]

• [OSDI] VBASE: Unifying Online Vector Similarity Search and Relational Queries via Relaxed Monotonicity [Filter] [code]