{"total":104,"rows":[{"id":"2401.08281","title":"The Faiss library","created":"2024-01-16","cited_by_count":376,"area":null},{"id":"2404.12457","title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation","created":"2024-04-18","cited_by_count":98,"area":"rag"},{"id":"2407.12820","title":"PQCache: Product Quantization-based KVCache for Long Context LLM Inference","created":"2024-07-01","cited_by_count":95,"area":"inference"},{"id":"2305.04359","title":"ParlayANN: Scalable and Deterministic Parallel Graph-Based Approximate Nearest Neighbor Search Algorithms","created":"2023-05-07","cited_by_count":24,"area":null},{"id":"2310.09949","title":"Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models","created":"2023-10-15","cited_by_count":23,"area":"rag"},{"id":"2308.15136","title":"CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs","created":"2023-08-29","cited_by_count":22,"area":null},{"id":"2304.04759","title":"Similarity search in the blink of an eye with compressed indices","created":"2023-04-07","cited_by_count":21,"area":null},{"id":"2310.19126","title":"Worst-case Performance of Popular Approximate Nearest Neighbor Search Implementations: Guarantees and Limitations","created":"2023-10-29","cited_by_count":20,"area":null},{"id":"2503.14649","title":"RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving","created":"2025-03-18","cited_by_count":19,"area":"rag"},{"id":"2202.06212","title":"Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search","created":"2022-02-13","cited_by_count":17,"area":"distill"},{"id":"2211.12850","title":"OOD-DiskANN: Efficient and Scalable Graph ANNS for Out-of-Distribution Queries","created":"2022-10-22","cited_by_count":15,"area":null},{"id":"2112.15202","title":"Visual and Object Geo-localization: A Comprehensive Survey","created":"2021-12-30","cited_by_count":13,"area":null},{"id":"2505.02922","title":"RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference","created":"2025-05-05","cited_by_count":13,"area":"inference"},{"id":"2408.08933","title":"RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search","created":"2024-08-16","cited_by_count":12,"area":null},{"id":"2308.02752","title":"DeDrift: Robust Similarity Search under Content Drift","created":"2023-08-05","cited_by_count":11,"area":null},{"id":"2402.02044","title":"Locally-Adaptive Quantization for Streaming Vector Search","created":"2024-02-03","cited_by_count":11,"area":null},{"id":"2502.08246","title":"Inference-time sparse attention with asymmetric indexing","created":"2025-02-12","cited_by_count":11,"area":null},{"id":"2303.06210","title":"A Theoretical Analysis Of Nearest Neighbor Search On Approximate Near Neighbor Graph","created":"2023-03-10","cited_by_count":10,"area":null},{"id":"2105.01823","title":"TransHash: Transformer-based Hamming Hashing for Efficient Image Retrieval","created":"2021-05-05","cited_by_count":8,"area":null},{"id":"2312.05417","title":"ESPN: Memory-Efficient Multi-Vector Information Retrieval","created":"2023-12-09","cited_by_count":8,"area":null},{"id":"2408.05141","title":"A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning","created":"2024-08-09","cited_by_count":8,"area":"lr"},{"id":"2503.04422","title":"PDX: A Data Layout for Vector Similarity Search","created":"2025-03-06","cited_by_count":8,"area":null},{"id":"2201.05409","title":"Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval","created":"2022-01-14","cited_by_count":7,"area":null},{"id":"2203.13601","title":"Navigable Proximity Graph-Driven Native Hybrid Queries with Structured and Unstructured Constraints","created":"2022-03-25","cited_by_count":7,"area":null},{"id":"2209.10100","title":"Flashlight: Scalable Link Prediction with Effective Decoders","created":"2022-09-17","cited_by_count":7,"area":null},{"id":"2301.01702","title":"Automating Nearest Neighbor Search Configuration with Constrained Optimization","created":"2023-01-04","cited_by_count":7,"area":null},{"id":"2405.18680","title":"Navigable Graphs for High-Dimensional Nearest Neighbor Search: Constructions and Limits","created":"2024-05-29","cited_by_count":7,"area":null},{"id":"2411.00970","title":"Incremental IVF Index Maintenance for Streaming Vector Search","created":"2024-11-01","cited_by_count":7,"area":null},{"id":"2110.14007","title":"TOD: GPU-accelerated Outlier Detection via Tensor Operations","created":"2021-10-26","cited_by_count":6,"area":null},{"id":"2302.08714","title":"Binary Embedding-based Retrieval at Tencent","created":"2023-02-17","cited_by_count":6,"area":null},{"id":"2306.11182","title":"Co-design Hardware and Algorithm for Vector Search","created":"2023-06-19","cited_by_count":6,"area":null},{"id":"2504.05573","title":"MicroNN: An On-device Disk-resident Updatable Vector Database","created":"2025-04-08","cited_by_count":6,"area":"rag"},{"id":"2505.17810","title":"VIBE: Vector Index Benchmark for Embeddings","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2312.16335","title":"LeanVec: Searching vectors faster by making them fit","created":"2023-12-26","cited_by_count":5,"area":null},{"id":"2206.11408","title":"FINGER: Fast Inference for Graph-based Approximate Nearest Neighbor Search","created":"2022-06-22","cited_by_count":4,"area":null},{"id":"2406.19651","title":"CANDY: A Benchmark for Continuous Approximate Nearest Neighbor Search with Dynamic Data Ingestion","created":"2024-06-28","cited_by_count":4,"area":null},{"id":"2505.17152","title":"LSM-VEC: A Large-Scale Disk-Based System for Dynamic Vector Search","created":"2025-05-22","cited_by_count":4,"area":"rag"},{"id":"2506.08276","title":"LEANN: A Low-Storage Vector Index","created":"2025-06-09","cited_by_count":4,"area":"rag"},{"id":"2506.16444","title":"REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing","created":"2025-06-19","cited_by_count":4,"area":null},{"id":"2508.01405","title":"Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Search","created":"2025-08-02","cited_by_count":4,"area":"rag"},{"id":"2303.06586","title":"Proactive Prioritization of App Issues via Contrastive Learning","created":"2023-03-12","cited_by_count":3,"area":null},{"id":"2309.00472","title":"General and Practical Tuning Method for Off-the-Shelf Graph-Based Index: SISAP Indexing Challenge Report by Team UTokyo","created":"2023-09-01","cited_by_count":3,"area":null},{"id":"2401.07119","title":"Curator: Efficient Indexing for Multi-Tenant Vector Databases","created":"2024-01-13","cited_by_count":3,"area":null},{"id":"2402.11354","title":"Probabilistic Routing for Graph-Based Approximate Nearest Neighbor Search","created":"2024-02-17","cited_by_count":3,"area":null},{"id":"2406.02891","title":"A Bi-metric Framework for Fast Similarity Search","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2502.01528","title":"SQUASH: Serverless and Distributed Quantization-based Attributed Vector Similarity Search","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2504.10326","title":"AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference","created":"2025-04-14","cited_by_count":3,"area":"inference"},{"id":"2505.01538","title":"HONEYBEE: Efficient Role-based Access Control for Vector Databases via Dynamic Partitioning[Technical Report]","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2511.14748","title":"Cloud-Native Vector Search: A Comprehensive Performance Analysis","created":"2025-11-18","cited_by_count":3,"area":"rag"},{"id":"2211.14982","title":"Two Is Better Than One: Dual Embeddings for Complementary Product Recommendations","created":"2022-11-28","cited_by_count":2,"area":null},{"id":"2306.07607","title":"Practice with Graph-based ANN Algorithms on Sparse Data: Chi-square Two-tower model, HNSW, Sign Cauchy Projections","created":"2023-06-13","cited_by_count":2,"area":null},{"id":"2505.12524","title":"HAKES: Scalable Vector Database for Embedding Search Service","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2505.20274","title":"Probabilistic Kernel Function for Fast Angle Testing","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2509.03228","title":"NeurStore: Efficient In-database Deep Learning Model Management System","created":"2025-09-03","cited_by_count":2,"area":null},{"id":"2509.25487","title":"Scalable Disk-Based Approximate Nearest Neighbor Search with Page-Aligned Graph","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2602.02057","title":"QVCache: A Query-Aware Vector Cache","created":"2026-02-02","cited_by_count":2,"area":"rag"},{"id":"2201.07917","title":"Similarity search on neighbor's graphs with automatic Pareto optimal performance and minimum expected quality setups based on hyperparameter optimization","created":"2022-01-19","cited_by_count":1,"area":null},{"id":"2203.02505","title":"ARM 4-BIT PQ: SIMD-based Acceleration for Approximate Nearest Neighbor Search on ARM","created":"2022-03-03","cited_by_count":1,"area":null},{"id":"2206.08091","title":"Unsupervised Space Partitioning for Nearest Neighbor Search","created":"2022-06-16","cited_by_count":1,"area":null},{"id":"2209.08759","title":"Tree-based Text-Vision BERT for Video Search in Baidu Video Advertising","created":"2022-09-19","cited_by_count":1,"area":null},{"id":"2210.04288","title":"CoopHash: Cooperative Learning of Multipurpose Descriptor and Contrastive Pair Generator via Variational MCMC Teaching for Supervised Image Hashing","created":"2022-10-09","cited_by_count":1,"area":null},{"id":"2501.10479","title":"Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search","created":"2025-01-16","cited_by_count":1,"area":null},{"id":"2506.04790","title":"LotusFilter: Fast Diverse Nearest Neighbor Search via a Learned Cutoff Table","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2508.05369","title":"Cross-View Localization via Redundant Sliced Observations and A-Contrario Validation","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2602.16719","title":"GPU-Accelerated Algorithms for Graph Vector Search: Taxonomy, Empirical Study, and Research Directions","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2603.20336","title":"GEM: A Native Graph-based Index for Multi-Vector Retrieval","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2102.06525","title":"Leveraging Reinforcement Learning for evaluating Robustness of KNN Search Algorithms","created":"2021-02-10","cited_by_count":0,"area":null},{"id":"2311.02573","title":"Group Testing for Accurate and Efficient Range-Based Near Neighbor Search for Plagiarism Detection","created":"2023-11-05","cited_by_count":0,"area":null},{"id":"2405.04435","title":"Fast Exact Retrieval for Nearest-neighbor Lookup (FERN)","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2410.22347","title":"GleanVec: Accelerating vector search with minimalist nonlinear dimensionality reduction","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2502.06163","title":"Scalable k-Means Clustering for Large k via Seeded Approximate Nearest-Neighbor Search","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2504.20018","title":"MINT: Multi-Vector Search Index Tuning","created":"2025-04-28","cited_by_count":0,"area":null},{"id":"2505.15636","title":"Distance Adaptive Beam Search for Provably Accurate Graph-Based Nearest Neighbor Search","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2505.17844","title":"Locality-Sensitive Hashing for Efficient Hard Negative Sampling in Contrastive Learning","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2505.24608","title":"GARLIC: GAussian Representation LearnIng for spaCe partitioning","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2506.20584","title":"The kernel of graph indices for vector search","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2508.02091","title":"CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search","created":"2025-08-04","cited_by_count":0,"area":"lr"},{"id":"2509.18471","title":"Individualized non-uniform quantization for vector search","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2510.22479","title":"Contextual Tokenization for Graph Inverted Indices","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2510.27243","title":"Approximate Diverse $k$-nearest Neighbor Search in Vector Database","created":"2025-10-31","cited_by_count":0,"area":"rag"},{"id":"2511.00855","title":"All-in-one Graph-based Indexing for Hybrid Search on GPUs","created":"2025-11-02","cited_by_count":0,"area":"rag"},{"id":"2512.09695","title":"Exqutor: Extended Query Optimizer for Vector-augmented Analytical Queries","created":"2025-12-10","cited_by_count":0,"area":"rag"},{"id":"2512.12938","title":"SPAR: Session-based Pipeline for Adaptive Retrieval on Legacy File Systems","created":"2025-12-15","cited_by_count":0,"area":"rag"},{"id":"2512.18060","title":"Graph-based Nearest Neighbors with Dynamic Updates via Random Walks","created":"2025-12-19","cited_by_count":0,"area":"rag"},{"id":"2601.01930","title":"MCGI: Manifold-Consistent Graph Indexing for Billion-Scale Disk-Resident Vector Search","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2602.06633","title":"Graph-Based Nearest-Neighbor Search without the Spread","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.22214","title":"Adaptive Prefiltering for High-Dimensional Similarity Search: A Frequency-Aware Approach","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2603.06159","title":"Efficient K-generalizable Learned Search","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.06660","title":"Approximate Nearest Neighbor Search for Modern AI: A Projection-Augmented Graph Approach","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2603.09347","title":"The Virtuous Cycle: AI-Powered Vector Search and Vector Search-Augmented AI","created":"2026-03-10","cited_by_count":0,"area":"rag"},{"id":"2603.21710","title":"FGIM: a Fast Graph-based Indexes Merging Framework for Approximate Nearest Neighbor Search","created":"2026-03-23","cited_by_count":0,"area":"rag"},{"id":"2604.06616","title":"CubeGraph: Efficient Retrieval-Augmented Generation for Spatial and Temporal Data","created":"2026-04-08","cited_by_count":0,"area":"rag"},{"id":"2604.11274","title":"Mycelium-Index: A Streaming Approximate Nearest Neighbor Index with Myelial Edge Decay, Traffic-Driven Reinforcement, and Adaptive Living Hierarchy","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.17104","title":"TensorDex: A Compact, Tensor-Centric Storage System for Modern AI Models","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.17415","title":"IVF-TQ: Calibration-Free Streaming Vector Search via a Codebook-Free Residual Layer","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.21952","title":"NasZip: Software and Hardware Co-Design to Accelerate Approximate Nearest Neighbor Search with DIMM-Based Near-Data Processing","created":"2026-05-21","cited_by_count":0,"area":"rag"},{"id":"2606.04522","title":"ANN Search: Recall What Matters","created":"2026-06-03","cited_by_count":0,"area":"rag"},{"id":"2607.02338","title":"HNSW with Accuracy Guarantees Using Graph Spanners","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.04630","title":"Exploiting Structural Properties for Efficient Constraint-Aware HNSW Hyperparameter Tuning","created":"2026-07-06","cited_by_count":0,"area":"rag"},{"id":"2607.17582","title":"ANNLib: A Development Framework for Efficient Approximate Nearest Neighbor Search","created":"2026-07-20","cited_by_count":0,"area":null}],"next_cursor":"100"}