{"total":617,"rows":[{"id":"2401.08281","title":"The Faiss library","created":"2024-01-16","cited_by_count":376,"area":null},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282,"area":null},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252,"area":null},{"id":"2102.07033","title":"PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them","created":"2021-02-13","cited_by_count":200,"area":null},{"id":"2205.12035","title":"RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder","created":"2022-05-24","cited_by_count":118,"area":null},{"id":"2409.10516","title":"RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval","created":"2024-09-16","cited_by_count":116,"area":null},{"id":"2207.06300","title":"Re2G: Retrieve, Rerank, Generate","created":"2022-07-13","cited_by_count":102,"area":null},{"id":"2205.09707","title":"PLAID: An Efficient Engine for Late Interaction Retrieval","created":"2022-05-19","cited_by_count":101,"area":null},{"id":"2404.14851","title":"From Matching to Generation: A Survey on Generative Information Retrieval","created":"2024-04-23","cited_by_count":89,"area":null},{"id":"2204.03444","title":"Deep Visual Geo-localization Benchmark","created":"2022-04-07","cited_by_count":84,"area":null},{"id":"2110.00685","title":"Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification","created":"2021-10-01","cited_by_count":67,"area":null},{"id":"2105.11269","title":"Neural Machine Translation with Monolingual Translation Memory","created":"2021-05-24","cited_by_count":61,"area":null},{"id":"2111.09360","title":"Personalized Federated Learning through Local Memorization","created":"2021-11-17","cited_by_count":57,"area":null},{"id":"2205.04507","title":"PinnerFormer: Sequence Modeling for User Representation at Pinterest","created":"2022-05-09","cited_by_count":57,"area":null},{"id":"2310.11703","title":"A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge","created":"2023-10-18","cited_by_count":55,"area":null},{"id":"2106.00882","title":"Efficient Passage Retrieval with Hashing for Open-domain Question Answering","created":"2021-06-02","cited_by_count":53,"area":null},{"id":"2502.14913","title":"OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment","created":"2025-02-19","cited_by_count":53,"area":null},{"id":"2203.05765","title":"Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval","created":"2022-03-11","cited_by_count":47,"area":null},{"id":"2205.03763","title":"Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search","created":"2022-05-08","cited_by_count":45,"area":null},{"id":"2404.06542","title":"Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation","created":"2024-04-09","cited_by_count":44,"area":null},{"id":"2402.01763","title":"When Large Language Models Meet Vector Databases: A Survey","created":"2024-01-30","cited_by_count":39,"area":null},{"id":"2111.06685","title":"DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents","created":"2021-11-12","cited_by_count":37,"area":null},{"id":"2202.03101","title":"Nonparametric Uncertainty Quantification for Single Deterministic Neural Network","created":"2022-02-07","cited_by_count":36,"area":null},{"id":"2111.08566","title":"SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search","created":"2021-11-05","cited_by_count":35,"area":null},{"id":"2404.11672","title":"MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory","created":"2024-04-17","cited_by_count":35,"area":null},{"id":"2207.04452","title":"NGAME: Negative Mining-aware Mini-batching for Extreme Classification","created":"2022-07-10","cited_by_count":32,"area":null},{"id":"2304.01982","title":"Rethinking the Role of Token Retrieval in Multi-Vector Retrieval","created":"2023-04-04","cited_by_count":31,"area":null},{"id":"2403.13310","title":"A Semantic Search Engine for Mathlib4","created":"2024-03-20","cited_by_count":31,"area":null},{"id":"2305.09253","title":"Online Continual Learning Without the Storage Constraint","created":"2023-05-16","cited_by_count":29,"area":null},{"id":"2106.12657","title":"Extreme Multi-label Learning for Semantic Matching in Product Search","created":"2021-06-23","cited_by_count":28,"area":null},{"id":"2410.11303","title":"TSDS: Data Selection for Task-Specific Model Finetuning","created":"2024-10-15","cited_by_count":28,"area":null},{"id":"2207.03834","title":"An Efficiency Study for SPLADE Models","created":"2022-07-08","cited_by_count":26,"area":null},{"id":"2212.00196","title":"Data-Efficient Finetuning Using Cross-Task Nearest Neighbors","created":"2022-12-01","cited_by_count":26,"area":null},{"id":"2203.09127","title":"ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps","created":"2022-03-17","cited_by_count":25,"area":null},{"id":"2207.03868","title":"Learning Sequential Descriptors for Sequence-based Visual Place Recognition","created":"2022-07-08","cited_by_count":25,"area":null},{"id":"2401.14732","title":"Residual Quantization with Implicit Neural Codebooks","created":"2024-01-26","cited_by_count":25,"area":null},{"id":"2409.14683","title":"Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling","created":"2024-09-23","cited_by_count":25,"area":null},{"id":"2110.01529","title":"A Proposed Conceptual Framework for a Representational Approach to Information Retrieval","created":"2021-10-04","cited_by_count":24,"area":null},{"id":"2210.05758","title":"Decoupled Context Processing for Context Augmented Language Modeling","created":"2022-10-11","cited_by_count":24,"area":null},{"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":"2403.13805","title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","created":"2024-03-20","cited_by_count":24,"area":null},{"id":"2205.11728","title":"ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest","created":"2022-05-24","cited_by_count":23,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"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":"2409.17424","title":"Results of the Big ANN: NeurIPS'23 competition","created":"2024-09-25","cited_by_count":22,"area":null},{"id":"2411.05276","title":"GPT Semantic Cache: Reducing LLM Costs and Latency via Semantic Embedding Caching","created":"2024-11-08","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":"2412.04653","title":"Hidden in the Noise: Two-Stage Robust Watermarking for Images","created":"2024-12-05","cited_by_count":21,"area":null},{"id":"2204.09314","title":"NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results","created":"2022-04-20","cited_by_count":20,"area":null},{"id":"2208.11184","title":"AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results","created":"2022-08-23","cited_by_count":20,"area":null},{"id":"2211.07886","title":"A Survey for Efficient Open Domain Question Answering","created":"2022-11-15","cited_by_count":20,"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":"2311.04335","title":"Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations","created":"2023-11-07","cited_by_count":20,"area":null},{"id":"2203.08543","title":"Integrating Language Guidance into Vision-based Deep Metric Learning","created":"2022-03-16","cited_by_count":19,"area":null},{"id":"2304.01926","title":"High-Throughput Vector Similarity Search in Knowledge Graphs","created":"2023-04-04","cited_by_count":19,"area":null},{"id":"2102.09268","title":"Training Large-Scale News Recommenders with Pretrained Language Models in the Loop","created":"2021-02-18","cited_by_count":18,"area":null},{"id":"2206.14286","title":"TPU-KNN: K Nearest Neighbor Search at Peak FLOP/s","created":"2022-06-28","cited_by_count":18,"area":null},{"id":"2303.10126","title":"IRGen: Generative Modeling for Image Retrieval","created":"2023-03-17","cited_by_count":18,"area":null},{"id":"2502.03771","title":"vCache: Verified Semantic Prompt Caching","created":"2025-02-06","cited_by_count":17,"area":null},{"id":"2505.11545","title":"TARGET: Benchmarking Table Retrieval for Generative Tasks","created":"2025-05-14","cited_by_count":17,"area":null},{"id":"2102.03716","title":"SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation","created":"2021-02-07","cited_by_count":16,"area":null},{"id":"2501.09186","title":"Guiding Retrieval using LLM-based Listwise Rankers","created":"2025-01-15","cited_by_count":16,"area":null},{"id":"2110.06777","title":"Incremental Ensemble Gaussian Processes","created":"2021-10-13","cited_by_count":15,"area":null},{"id":"2112.08652","title":"Extreme Zero-Shot Learning for Extreme Text Classification","created":"2021-12-16","cited_by_count":15,"area":null},{"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":"2212.07588","title":"DeepJoin: Joinable Table Discovery with Pre-trained Language Models","created":"2022-12-15","cited_by_count":15,"area":null},{"id":"2304.11943","title":"Constructing Tree-based Index for Efficient and Effective Dense Retrieval","created":"2023-04-24","cited_by_count":15,"area":null},{"id":"2305.17080","title":"Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2407.21523","title":"Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI","created":"2024-07-31","cited_by_count":15,"area":null},{"id":"2412.16100","title":"Logical Consistency of Large Language Models in Fact-checking","created":"2024-12-20","cited_by_count":15,"area":null},{"id":"2106.12671","title":"What makes visual place recognition easy or hard?","created":"2021-06-23","cited_by_count":14,"area":null},{"id":"2201.12741","title":"GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks","created":"2022-01-30","cited_by_count":14,"area":null},{"id":"2202.10226","title":"Approximate Nearest Neighbor Search under Neural Similarity Metric for Large-Scale Recommendation","created":"2022-02-14","cited_by_count":14,"area":null},{"id":"2203.12997","title":"Hierarchical Nearest Neighbor Graph Embedding for Efficient Dimensionality Reduction","created":"2022-03-24","cited_by_count":14,"area":null},{"id":"2210.08410","title":"ELIAS: End-to-End Learning to Index and Search in Large Output Spaces","created":"2022-10-16","cited_by_count":14,"area":null},{"id":"2306.17373","title":"HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image","created":"2023-06-30","cited_by_count":14,"area":null},{"id":"2409.03708","title":"RAG based Question-Answering for Contextual Response Prediction System","created":"2024-09-05","cited_by_count":14,"area":null},{"id":"2510.12474","title":"SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression","created":"2025-10-14","cited_by_count":14,"area":null},{"id":"2106.10458","title":"Place recognition survey: An update on deep learning approaches","created":"2021-06-19","cited_by_count":13,"area":null},{"id":"2304.12329","title":"Pre-trained Embeddings for Entity Resolution: An Experimental Analysis [Experiment, Analysis & Benchmark]","created":"2023-04-24","cited_by_count":13,"area":null},{"id":"2311.18213","title":"Beyond Two-Tower Matching: Learning Sparse Retrievable Cross-Interactions for Recommendation","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2205.15540","title":"MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation","created":"2022-05-31","cited_by_count":12,"area":null},{"id":"2301.12874","title":"Extremal Domain Translation with Neural Optimal Transport","created":"2023-01-30","cited_by_count":12,"area":null},{"id":"2302.03505","title":"OPORP: One Permutation + One Random Projection","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2311.15578","title":"Experimental Analysis of Large-scale Learnable Vector Storage Compression","created":"2023-11-27","cited_by_count":12,"area":null},{"id":"2404.00774","title":"SOAR: Improved Indexing for Approximate Nearest Neighbor Search","created":"2024-03-31","cited_by_count":12,"area":null},{"id":"2409.16763","title":"Statewide Visual Geolocalization in the Wild","created":"2024-09-25","cited_by_count":12,"area":null},{"id":"2411.00489","title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2503.08640","title":"Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention","created":"2025-03-11","cited_by_count":12,"area":null},{"id":"2604.01707","title":"Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework","created":"2026-04-02","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":"2402.00943","title":"Approximate Nearest Neighbor Search with Window Filters","created":"2024-02-01","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":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2409.17687","title":"Graph Edit Distance with General Costs Using Neural Set Divergence","created":"2024-09-26","cited_by_count":11,"area":null},{"id":"2412.01826","title":"RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations","created":"2024-12-02","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":"2509.00640","title":"NMR-Solver: Automated Structure Elucidation via Large-Scale Spectral Matching and Physics-Guided Fragment Optimization","created":"2025-08-30","cited_by_count":11,"area":null},{"id":"2108.04526","title":"A Survey on Deep Reinforcement Learning for Data Processing and Analytics","created":"2021-08-10","cited_by_count":10,"area":null},{"id":"2112.07771","title":"Boosted Dense Retriever","created":"2021-12-14","cited_by_count":10,"area":null}],"next_cursor":"100"}