{"total":109,"rows":[{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141,"area":"rag"},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2402.17152","title":"Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations","created":"2024-02-27","cited_by_count":188,"area":null},{"id":"2101.00774","title":"Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering","created":"2021-01-04","cited_by_count":178,"area":null},{"id":"2110.15343","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","created":"2021-10-28","cited_by_count":130,"area":null},{"id":"2212.05221","title":"REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory","created":"2022-12-10","cited_by_count":123,"area":"mllm"},{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122,"area":null},{"id":"2302.11154","title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","created":"2023-02-22","cited_by_count":113,"area":null},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"id":"2110.00768","title":"TopiOCQA: Open-domain Conversational Question Answering with Topic Switching","created":"2021-10-02","cited_by_count":96,"area":null},{"id":"2101.00408","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","created":"2021-01-02","cited_by_count":75,"area":null},{"id":"2105.11269","title":"Neural Machine Translation with Monolingual Translation Memory","created":"2021-05-24","cited_by_count":61,"area":null},{"id":"2112.09924","title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus","created":"2021-12-18","cited_by_count":60,"area":null},{"id":"2306.15222","title":"Learning to Rank in Generative Retrieval","created":"2023-06-27","cited_by_count":46,"area":null},{"id":"2101.00117","title":"Multi-task Retrieval for Knowledge-Intensive Tasks","created":"2021-01-01","cited_by_count":44,"area":null},{"id":"2103.12279","title":"SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers","created":"2021-03-23","cited_by_count":44,"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":"2207.05836","title":"Contextual Bandits with Large Action Spaces: Made Practical","created":"2022-07-12","cited_by_count":33,"area":null},{"id":"2110.04622","title":"Does Preprocessing Help Training Over-parameterized Neural Networks?","created":"2021-10-09","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":"2211.14227","title":"Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing","created":"2022-11-25","cited_by_count":29,"area":null},{"id":"2104.05883","title":"Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval","created":"2021-04-13","cited_by_count":25,"area":null},{"id":"2106.08700","title":"Topology Distillation for Recommender System","created":"2021-06-16","cited_by_count":24,"area":"distill"},{"id":"2412.14468","title":"HashAttention: Semantic Sparsity for Faster Inference","created":"2024-12-19","cited_by_count":24,"area":null},{"id":"2105.06597","title":"RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling","created":"2021-05-14","cited_by_count":22,"area":"moe"},{"id":"2201.07745","title":"Improving Biomedical Information Retrieval with Neural Retrievers","created":"2022-01-19","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":"2111.15139","title":"Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures","created":"2021-11-30","cited_by_count":19,"area":null},{"id":"2405.14335","title":"Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning","created":"2024-05-23","cited_by_count":16,"area":null},{"id":"2105.08285","title":"Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing","created":"2021-05-18","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":"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":"2306.04039","title":"Revisiting Neural Retrieval on Accelerators","created":"2023-06-06","cited_by_count":14,"area":null},{"id":"2504.01403","title":"Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrieval","created":"2025-04-02","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":"2509.25519","title":"Flow Matching with Semidiscrete Couplings","created":"2025-09-29","cited_by_count":13,"area":"diffusion"},{"id":"2109.07812","title":"Transductive Learning for Unsupervised Text Style Transfer","created":"2021-09-16","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":"2402.12535","title":"Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics","created":"2024-02-19","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":"2101.04849","title":"Probabilistic Metric Learning with Adaptive Margin for Top-K Recommendation","created":"2021-01-13","cited_by_count":11,"area":null},{"id":"2107.06876","title":"Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More","created":"2021-07-14","cited_by_count":11,"area":null},{"id":"2108.02390","title":"Fuzzy Logic Based Logical Query Answering on Knowledge Graphs","created":"2021-08-05","cited_by_count":11,"area":null},{"id":"2310.14503","title":"Diversify Question Generation with Retrieval-Augmented Style Transfer","created":"2023-10-23","cited_by_count":10,"area":"rag"},{"id":"2402.17532","title":"Retrieval is Accurate Generation","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2103.02729","title":"Linear Bandit Algorithms with Sublinear Time Complexity","created":"2021-03-03","cited_by_count":9,"area":null},{"id":"2109.13087","title":"Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations","created":"2021-09-24","cited_by_count":9,"area":null},{"id":"2203.08517","title":"TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge","created":"2022-03-16","cited_by_count":9,"area":null},{"id":"2109.05773","title":"Fast Variational AutoEncoder with Inverted Multi-Index for Collaborative Filtering","created":"2021-09-13","cited_by_count":8,"area":null},{"id":"2208.06263","title":"Probabilistic Rank and Reward: A Scalable Model for Slate Recommendation","created":"2022-08-10","cited_by_count":8,"area":null},{"id":"2305.03276","title":"Expository Text Generation: Imitate, Retrieve, Paraphrase","created":"2023-05-05","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":"2109.10346","title":"Relation-Guided Pre-Training for Open-Domain Question Answering","created":"2021-09-21","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":"2302.00942","title":"Efficient Graph Field Integrators Meet Point Clouds","created":"2023-02-02","cited_by_count":7,"area":null},{"id":"2209.15469","title":"Zero-Shot Retrieval with Search Agents and Hybrid Environments","created":"2022-09-30","cited_by_count":6,"area":"agents"},{"id":"2305.18952","title":"Exploring the Practicality of Generative Retrieval on Dynamic Corpora","created":"2023-05-27","cited_by_count":6,"area":null},{"id":"2310.09516","title":"Efficient Link Prediction via GNN Layers Induced by Negative Sampling","created":"2023-10-14","cited_by_count":6,"area":null},{"id":"2502.15572","title":"DReSD: Dense Retrieval for Speculative Decoding","created":"2025-02-21","cited_by_count":6,"area":"inference"},{"id":"2110.04889","title":"Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation","created":"2021-10-10","cited_by_count":5,"area":null},{"id":"2210.12084","title":"Decoding a Neural Retriever's Latent Space for Query Suggestion","created":"2022-10-21","cited_by_count":5,"area":null},{"id":"2103.02537","title":"Weakly-Supervised Open-Retrieval Conversational Question Answering","created":"2021-03-03","cited_by_count":4,"area":null},{"id":"2205.06205","title":"kNN-Embed: Locally Smoothed Embedding Mixtures For Multi-interest Candidate Retrieval","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2104.08710","title":"Simple and Efficient ways to Improve REALM","created":"2021-04-18","cited_by_count":3,"area":null},{"id":"2110.00159","title":"Building an Efficient and Effective Retrieval-based Dialogue System via Mutual Learning","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2203.15959","title":"Entity-driven Fact-aware Abstractive Summarization of Biomedical Literature","created":"2022-03-30","cited_by_count":3,"area":null},{"id":"2208.01191","title":"Implicit Two-Tower Policies","created":"2022-08-02","cited_by_count":3,"area":null},{"id":"2212.07551","title":"Faster Maximum Inner Product Search in High Dimensions","created":"2022-12-14","cited_by_count":3,"area":null},{"id":"2308.01566","title":"Fast Slate Policy Optimization: Going Beyond Plackett-Luce","created":"2023-08-03","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":"2407.15462","title":"Retrieval with Learned Similarities","created":"2024-07-22","cited_by_count":3,"area":null},{"id":"2412.20574","title":"A Survey on Time-Series Distance Measures","created":"2024-12-29","cited_by_count":3,"area":null},{"id":"2106.00730","title":"Enabling Efficiency-Precision Trade-offs for Label Trees in Extreme Classification","created":"2021-06-01","cited_by_count":2,"area":null},{"id":"2112.02194","title":"ALX: Large Scale Matrix Factorization on TPUs","created":"2021-12-03","cited_by_count":2,"area":null},{"id":"2112.12433","title":"Sparse-softmax: A Simpler and Faster Alternative Softmax Transformation","created":"2021-12-23","cited_by_count":2,"area":null},{"id":"2204.10936","title":"Counterfactual Learning To Rank for Utility-Maximizing Query Autocompletion","created":"2022-04-22","cited_by_count":2,"area":null},{"id":"2306.17675","title":"Multimodal Prompt Retrieval for Generative Visual Question Answering","created":"2023-06-30","cited_by_count":2,"area":"mllm"},{"id":"2402.10769","title":"Distillation Enhanced Generative Retrieval","created":"2024-02-16","cited_by_count":2,"area":null},{"id":"2402.12291","title":"KARL: Knowledge-Aware Retrieval and Representations aid Retention and Learning in Students","created":"2024-02-19","cited_by_count":2,"area":null},{"id":"2407.13952","title":"Knowledge Distillation Approaches for Accurate and Efficient Recommender System","created":"2024-07-19","cited_by_count":2,"area":"distill"},{"id":"2205.16005","title":"Neural Retriever and Go Beyond: A Thesis Proposal","created":"2022-05-31","cited_by_count":1,"area":null},{"id":"2211.12751","title":"SAH: Shifting-aware Asymmetric Hashing for Reverse $k$-Maximum Inner Product Search","created":"2022-11-23","cited_by_count":1,"area":null},{"id":"2306.02563","title":"Large-Scale Distributed Learning via Private On-Device Locality-Sensitive Hashing","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2312.02532","title":"DRAFT: Dense Retrieval Augmented Few-shot Topic classifier Framework","created":"2023-12-05","cited_by_count":1,"area":"rag"},{"id":"2411.04013","title":"$k$NN Attention Demystified: A Theoretical Exploration for Scalable Transformers","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2602.00586","title":"RAG-GNN: Integrating Retrieved Knowledge with Graph Neural Networks for Precision Medicine","created":"2026-01-31","cited_by_count":1,"area":"rag"},{"id":"2603.08001","title":"Amortized Maximum Inner Product Search with Learned Support Functions","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2605.17285","title":"UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2606.06453","title":"Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents","created":"2026-06-04","cited_by_count":1,"area":"agents"},{"id":"2102.04770","title":"COLOGNE: Coordinated Local Graph Neighborhood Sampling","created":"2021-02-09","cited_by_count":0,"area":null},{"id":"2202.13616","title":"WSLRec: Weakly Supervised Learning for Neural Sequential Recommendation Models","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2301.13606","title":"Multi-video Moment Ranking with Multimodal Clue","created":"2023-01-29","cited_by_count":0,"area":null},{"id":"2305.14949","title":"Cross-lingual Data Augmentation for Document-grounded Dialog Systems in Low Resource Languages","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2306.09293","title":"[Experiments & Analysis] Evaluating the Feasibility of Sampling-Based Techniques for Training Multilayer Perceptrons","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2309.15479","title":"Fast Locality Sensitive Hashing with Theoretical Guarantee","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2310.14486","title":"Text Fact Transfer","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2311.11429","title":"Fast Heavy Inner Product Identification Between Weights and Inputs in Neural Network Training","created":"2023-11-19","cited_by_count":0,"area":null},{"id":"2508.05206","title":"Bidding-Aware Retrieval for Multi-Stage Consistency in Online Advertising","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2509.25919","title":"Accelerating LLM Inference with Precomputed Query Storage","created":"2025-09-30","cited_by_count":0,"area":null}],"next_cursor":"100"}