{"total":17,"rows":[{"id":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125,"area":"rag"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2503.23895","title":"Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement","created":"2025-03-31","cited_by_count":25,"area":"rag"},{"id":"2501.16075","title":"PISCO: Pretty Simple Compression for Retrieval-Augmented Generation","created":"2025-01-27","cited_by_count":20,"area":"rag"},{"id":"2507.05633","title":"SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression","created":"2025-07-08","cited_by_count":10,"area":"rag"},{"id":"2604.02985","title":"Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference","created":"2026-04-03","cited_by_count":9,"area":"rag"},{"id":"2401.07793","title":"Flexibly Scaling Large Language Models Contexts Through Extensible Tokenization","created":"2024-01-15","cited_by_count":7,"area":"rag"},{"id":"2504.07109","title":"OSCAR: Online Soft Compression And Reranking","created":"2025-03-17","cited_by_count":4,"area":"rag"},{"id":"2408.00167","title":"Finch: Prompt-guided Key-Value Cache Compression","created":"2024-07-31","cited_by_count":2,"area":"rag"},{"id":"2601.05038","title":"ArcAligner: Adaptive Recursive Aligner for Compressed Context Embeddings in RAG","created":"2026-01-08","cited_by_count":1,"area":"rag"},{"id":"2604.17866","title":"Latent Abstraction for Retrieval-Augmented Generation","created":"2026-04-20","cited_by_count":1,"area":"rag"},{"id":"2605.00505","title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","created":"2026-05-01","cited_by_count":1,"area":"rag"},{"id":"2606.21807","title":"Fixed RAG Compression Collapses Measured Reader Scaling","created":"2026-06-20","cited_by_count":1,"area":"rag"},{"id":"2604.14403","title":"A Unified Model and Document Representation for On-Device Retrieval-Augmented Generation","created":"2026-04-15","cited_by_count":0,"area":"rag"},{"id":"2606.28361","title":"ConCise: Training-Free Conclusion-Chain State Compression for Cost-Efficient Multi-Step RAG Services","created":"2026-06-13","cited_by_count":0,"area":"rag"},{"id":"2609.05152","title":"Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG","created":"2026-09-04","cited_by_count":0,"area":"rag"},{"id":"2609.27380","title":"MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression","created":"2026-09-23","cited_by_count":0,"area":"rag"}],"next_cursor":null}