{"total":16,"rows":[{"id":"2410.07590","title":"TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text","created":"2024-10-10","cited_by_count":63,"area":"rag"},{"id":"2409.15355","title":"Block-Attention for Efficient Prefilling","created":"2024-09-14","cited_by_count":37,"area":"rag"},{"id":"2506.00054","title":"Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers","created":"2025-05-28","cited_by_count":27,"area":"rag"},{"id":"2407.09252","title":"Context Embeddings for Efficient Answer Generation in RAG","created":"2024-07-12","cited_by_count":26,"area":"rag"},{"id":"2503.10720","title":"AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation","created":"2025-03-13","cited_by_count":19,"area":"rag"},{"id":"2412.11854","title":"Towards Understanding Systems Trade-offs in Retrieval-Augmented Generation Model Inference","created":"2024-12-16","cited_by_count":15,"area":"rag"},{"id":"2412.15246","title":"Accelerating Retrieval-Augmented Generation","created":"2024-12-14","cited_by_count":14,"area":"rag"},{"id":"2509.21359","title":"Influence Guided Context Selection for Effective Retrieval-Augmented Generation","created":"2025-09-21","cited_by_count":7,"area":"rag"},{"id":"2602.04711","title":"Addressing Corpus Knowledge Poisoning Attacks on RAG Using Sparse Attention","created":"2026-02-04","cited_by_count":3,"area":"rag"},{"id":"2504.15302","title":"RAGDoll: Efficient Offloading-based Online RAG System on a Single GPU","created":"2025-04-17","cited_by_count":2,"area":"rag"},{"id":"2504.08386","title":"PCA-RAG: Principal Component Analysis for Efficient Retrieval-Augmented Generation","created":"2025-04-11","cited_by_count":1,"area":"rag"},{"id":"2601.11553","title":"PerCache: Predictive Hierarchical Cache for RAG Applications on Mobile Devices","created":"2025-12-10","cited_by_count":1,"area":"rag"},{"id":"2502.11101","title":"CacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented Generation","created":"2025-02-16","cited_by_count":0,"area":"rag"},{"id":"2505.19847","title":"DGRAG: Distributed Graph-based Retrieval-Augmented Generation in Edge-Cloud Systems","created":"2025-05-26","cited_by_count":0,"area":"rag"},{"id":"2510.20878","title":"HA-RAG: Hotness-Aware RAG Acceleration via Mixed Precision and Data Placement","created":"2025-10-23","cited_by_count":0,"area":"rag"},{"id":"2604.20452","title":"HaS: Accelerating RAG through Homology-Aware Speculative Retrieval","created":"2026-04-22","cited_by_count":0,"area":"rag"}],"next_cursor":null}