{"total":28,"rows":[{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"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":"2402.07844","title":"Mercury: A Code Efficiency Benchmark for Code Large Language Models","created":"2024-02-12","cited_by_count":35,"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":"2401.14542","title":"Exploring Musical Roots: Applying Audio Embeddings to Empower Influence Attribution for a Generative Music Model","created":"2024-01-25","cited_by_count":13,"area":null},{"id":"2412.18241","title":"An Automatic Graph Construction Framework based on Large Language Models for Recommendation","created":"2024-12-24","cited_by_count":9,"area":null},{"id":"2503.04422","title":"PDX: A Data Layout for Vector Similarity Search","created":"2025-03-06","cited_by_count":8,"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":"2304.02296","title":"Data Leakage Detection and De-duplication in Large Scale Geospatial Image Datasets","created":"2023-04-05","cited_by_count":4,"area":null},{"id":"2601.23088","title":"From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2311.04207","title":"Deep Hashing via Householder Quantization","created":"2023-11-07","cited_by_count":2,"area":null},{"id":"2404.00816","title":"HeteroMILE: a Multi-Level Graph Representation Learning Framework for Heterogeneous Graphs","created":"2024-03-31","cited_by_count":2,"area":null},{"id":"2511.15557","title":"B+ANN: A Fast Billion-Scale Disk-based Nearest-Neighbor Index","created":"2025-11-19","cited_by_count":2,"area":null},{"id":"2603.20009","title":"A Super Fast K-means for Indexing Vector Embeddings","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2502.13171","title":"Web Phishing Net (WPN): A scalable machine learning approach for real-time phishing campaign detection","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2505.07621","title":"Bang for the Buck: Vector Search on Cloud CPUs","created":"2025-05-12","cited_by_count":1,"area":null},{"id":"2109.10824","title":"Learning by Examples Based on Multi-level Optimization","created":"2021-09-22","cited_by_count":0,"area":null},{"id":"2112.11478","title":"LSH methods for data deduplication in a Wikipedia artificial dataset","created":"2021-12-10","cited_by_count":0,"area":null},{"id":"2211.09093","title":"Experimental Analysis of Machine Learning Techniques for Finding Search Radius in Locality Sensitive Hashing","created":"2022-11-16","cited_by_count":0,"area":null},{"id":"2405.13386","title":"360Zhinao Technical Report","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2410.04462","title":"Tensor-Train Point Cloud Compression and Efficient Approximate Nearest-Neighbor Search","created":"2024-10-06","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":"2502.20293","title":"Scalable Graph Attention-based Instance Selection via Mini-Batch Sampling and Hierarchical Hashing","created":"2025-02-27","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":"2509.18471","title":"Individualized non-uniform quantization for vector search","created":"2025-09-22","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}],"next_cursor":null}