{"total":22,"rows":[{"id":"2410.04343","title":"Inference Scaling for Long-Context Retrieval Augmented Generation","created":"2024-10-06","cited_by_count":65,"area":"rag"},{"id":"2411.08249","title":"Retrieval Augmented Time Series Forecasting","created":"2024-11-12","cited_by_count":46,"area":"rag"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2405.16178","title":"Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection","created":"2024-05-25","cited_by_count":25,"area":"rag"},{"id":"2410.07071","title":"Retrieval-Augmented Decision Transformer: External Memory for In-context RL","created":"2024-10-09","cited_by_count":21,"area":"rag"},{"id":"2410.02719","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","created":"2024-10-03","cited_by_count":16,"area":"rag"},{"id":"2410.15262","title":"HyQE: Ranking Contexts with Hypothetical Query Embeddings","created":"2024-10-20","cited_by_count":6,"area":"rag"},{"id":"2408.02854","title":"Creating a Taxonomy for Retrieval Augmented Generation Applications","created":"2024-08-05","cited_by_count":3,"area":"rag"},{"id":"2511.12043","title":"BudgetLeak: Membership Inference Attacks on RAG Systems via the Generation Budget Side Channel","created":"2025-11-15","cited_by_count":3,"area":"rag"},{"id":"2412.06078","title":"Mixture-of-PageRanks: Replacing Long-Context with Real-Time, Sparse GraphRAG","created":"2024-12-08","cited_by_count":2,"area":"rag"},{"id":"2510.01363","title":"Retrieval-Augmented Framework for LLM-Based Clinical Decision Support","created":"2025-10-01","cited_by_count":2,"area":"rag"},{"id":"2605.05806","title":"Retrieval from Within: An Intrinsic Capability of Attention-Based Models","created":"2026-05-07","cited_by_count":2,"area":"rag"},{"id":"2601.22203","title":"Beyond Conditional Computation: Retrieval-Augmented Genomic Foundation Models with Gengram","created":"2026-01-29","cited_by_count":1,"area":"rag"},{"id":"2605.25716","title":"An Efficient and Privacy-Preserving Architecture for Cross-Institutional Collaborative RAG","created":"2026-05-25","cited_by_count":1,"area":"rag"},{"id":"2312.12430","title":"Efficient Title Reranker for Fast and Improved Knowledge-Intense NLP","created":"2023-12-19","cited_by_count":0,"area":"rag"},{"id":"2505.07833","title":"Harmonia: End-to-End RAG Serving Optimization","created":"2025-05-01","cited_by_count":0,"area":"rag"},{"id":"2601.07861","title":"EmbeddingRWKV: State-Centric Retrieval with Reusable States","created":"2026-01-10","cited_by_count":0,"area":"rag"},{"id":"2603.29002","title":"Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference","created":"2026-03-30","cited_by_count":0,"area":"rag"},{"id":"2605.12335","title":"EHR-RAGp: Retrieval-Augmented Prototype-Guided Foundation Model for Electronic Health Records","created":"2026-05-12","cited_by_count":0,"area":"rag"},{"id":"2607.07740","title":"Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE","created":"2026-07-08","cited_by_count":0,"area":"rag"},{"id":"2608.02560","title":"Structured Memory for Edge Language Models: Persistent Context and Corpus Retrieval via O(1) SSM State Injection","created":"2026-08-03","cited_by_count":0,"area":"rag"},{"id":"2610.08463","title":"UNREAL: Unifying Retrieval and Long-Context with a Single Model","created":"2026-10-06","cited_by_count":0,"area":"rag"}],"next_cursor":null}