{"total":861,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297,"area":"rag"},{"id":"2401.08281","title":"The Faiss library","created":"2024-01-16","cited_by_count":376,"area":null},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354,"area":"rag"},{"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":"2303.01229","title":"Almanac: Retrieval-Augmented Language Models for Clinical Medicine","created":"2023-03-01","cited_by_count":123,"area":"rag"},{"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":"2202.11233","title":"Retrieval Augmented Classification for Long-Tail Visual Recognition","created":"2022-02-22","cited_by_count":106,"area":"rag"},{"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":"2404.12457","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":"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":"2404.10981","title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","created":"2024-04-17","cited_by_count":77,"area":"rag"},{"id":"2407.13193","title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","created":"2024-07-18","cited_by_count":71,"area":"rag"},{"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":"2304.06762","title":"Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study","created":"2023-04-13","cited_by_count":63,"area":"rag"},{"id":"2105.11269","title":"Neural Machine Translation with Monolingual Translation Memory","created":"2021-05-24","cited_by_count":61,"area":null},{"id":"2301.07094","title":"Learning Customized Visual Models with Retrieval-Augmented Knowledge","created":"2023-01-17","cited_by_count":58,"area":"rag"},{"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":"2310.07713","title":"InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining","created":"2023-10-11","cited_by_count":53,"area":"rag"},{"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":"2303.12733","title":"On the De-duplication of LAION-2B","created":"2023-03-17","cited_by_count":47,"area":"diffusion"},{"id":"2402.05131","title":"Financial Report Chunking for Effective Retrieval Augmented Generation","created":"2024-02-05","cited_by_count":46,"area":"rag"},{"id":"2503.04338","title":"In-depth Analysis of Graph-based RAG in a Unified Framework","created":"2025-03-06","cited_by_count":46,"area":"rag"},{"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":"2405.16420","title":"M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions","created":"2024-05-26","cited_by_count":38,"area":"rag"},{"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":"2210.16773","title":"An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks","created":"2022-10-30","cited_by_count":36,"area":"rag"},{"id":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"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":"2410.21943","title":"Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications","created":"2024-10-29","cited_by_count":31,"area":"rag"},{"id":"2507.18910","title":"A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions","created":"2025-07-25","cited_by_count":31,"area":"rag"},{"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":"2403.05676","title":"PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design","created":"2024-03-08","cited_by_count":28,"area":"rag"},{"id":"2410.11303","title":"TSDS: Data Selection for Task-Specific Model Finetuning","created":"2024-10-15","cited_by_count":28,"area":null},{"id":"2502.09891","title":"ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation","created":"2025-02-14","cited_by_count":28,"area":"rag"},{"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":"2504.11544","title":"NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes","created":"2025-04-15","cited_by_count":26,"area":"rag"},{"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":"2602.05665","title":"Graph-based Agent Memory: Taxonomy, Techniques, and Applications","created":"2026-02-05","cited_by_count":25,"area":"agents"},{"id":"2108.13934","title":"Robust Retrieval Augmented Generation for Zero-shot Slot Filling","created":"2021-08-31","cited_by_count":24,"area":"rag"},{"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":"2503.01478","title":"SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction","created":"2025-03-03","cited_by_count":24,"area":"rag"},{"id":"2205.11728","title":"ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest","created":"2022-05-24","cited_by_count":23,"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":"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":"2410.08876","title":"RoRA-VLM: Robust Retrieval-Augmented Vision Language Models","created":"2024-10-11","cited_by_count":23,"area":"mllm"},{"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":"2402.10196","title":"A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents","created":"2024-02-15","cited_by_count":22,"area":"agents"},{"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":"2401.14021","title":"Accelerating Retrieval-Augmented Language Model Serving with Speculation","created":"2024-01-25","cited_by_count":20,"area":"rag"},{"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":"2503.14649","title":"RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving","created":"2025-03-18","cited_by_count":19,"area":"rag"},{"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":"2402.07179","title":"Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models","created":"2024-02-11","cited_by_count":18,"area":"rag"},{"id":"2602.01801","title":"Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention","created":"2026-02-02","cited_by_count":18,"area":"wm"},{"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":"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":"2407.18553","title":"REAPER: Reasoning based Retrieval Planning for Complex RAG Systems","created":"2024-07-26","cited_by_count":16,"area":"lr"},{"id":"2501.09186","title":"Guiding Retrieval using LLM-based Listwise Rankers","created":"2025-01-15","cited_by_count":16,"area":null},{"id":"2511.12997","title":"WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance","created":"2025-11-17","cited_by_count":16,"area":"agents"},{"id":"2606.03056","title":"SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale","created":"2026-06-02","cited_by_count":16,"area":"agents"},{"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}],"next_cursor":"100"}