{"total":63,"rows":[{"id":"2502.16002","title":"KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse","created":"2025-02-21","cited_by_count":66,"area":"inference"},{"id":"2412.15605","title":"Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks","created":"2024-12-20","cited_by_count":38,"area":"rag"},{"id":"2412.16545","title":"Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models","created":"2024-12-21","cited_by_count":26,"area":null},{"id":"2510.10129","title":"CacheClip: Accelerating RAG with Effective KV Cache Reuse","created":"2025-10-11","cited_by_count":16,"area":"rag"},{"id":"2503.08640","title":"Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention","created":"2025-03-11","cited_by_count":12,"area":null},{"id":"2412.18069","title":"Improving Factuality with Explicit Working Memory","created":"2024-12-24","cited_by_count":10,"area":null},{"id":"2512.16391","title":"Kascade: A Practical Sparse Attention Method for Long-Context LLM Inference","created":"2025-12-18","cited_by_count":10,"area":"lr"},{"id":"2502.20969","title":"TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval","created":"2025-02-28","cited_by_count":9,"area":"rag"},{"id":"2511.03475","title":"ContextPilot: Fast Long-Context Inference via Context Reuse","created":"2025-11-05","cited_by_count":8,"area":"inference"},{"id":"2607.01299","title":"HYPIC: Accelerating Hybrid-Attention LLM Serving with Position-Independent Caching","created":"2026-07-01","cited_by_count":7,"area":"rag"},{"id":"2505.12731","title":"Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval Overlaps","created":"2025-05-19","cited_by_count":6,"area":"rag"},{"id":"2602.01519","title":"You Need an Encoder for Native Position-Independent Caching","created":"2026-02-02","cited_by_count":6,"area":null},{"id":"2505.12065","title":"Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents","created":"2025-05-17","cited_by_count":5,"area":"agents"},{"id":"2506.02279","title":"ImpRAG: Retrieval-Augmented Generation with Implicit Queries","created":"2025-06-02","cited_by_count":5,"area":"rag"},{"id":"2601.12904","title":"From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation","created":"2026-01-19","cited_by_count":5,"area":"rag"},{"id":"2603.20218","title":"An experimental study of KV cache reuse strategies in chunk-level caching systems","created":"2026-03-03","cited_by_count":5,"area":"rag"},{"id":"2504.07109","title":"OSCAR: Online Soft Compression And Reranking","created":"2025-03-17","cited_by_count":4,"area":"rag"},{"id":"2505.14398","title":"Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation","created":"2025-05-20","cited_by_count":4,"area":"lr"},{"id":"2603.23049","title":"PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving","created":"2026-03-24","cited_by_count":4,"area":"rag"},{"id":"2607.17715","title":"C$^2$KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference","created":"2026-07-20","cited_by_count":4,"area":"rag"},{"id":"2607.28979","title":"KV Cache Translation across Heterogeneous Large Language Models","created":"2026-07-31","cited_by_count":4,"area":"inference"},{"id":"2412.15529","title":"XRAG: eXamining the Core -- Benchmarking Foundational Components in Advanced Retrieval-Augmented Generation","created":"2024-12-20","cited_by_count":3,"area":"rag"},{"id":"2504.11765","title":"Shared Disk KV Cache Management for Efficient Multi-Instance Inference in RAG-Powered LLMs","created":"2025-04-16","cited_by_count":3,"area":"inference"},{"id":"2603.05353","title":"InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context","created":"2026-03-05","cited_by_count":3,"area":"rag"},{"id":"2606.02245","title":"When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation","created":"2026-06-01","cited_by_count":3,"area":"rag"},{"id":"2511.12979","title":"RAGPulse: An Open-Source RAG Workload Trace to Optimize RAG Serving Systems","created":"2025-11-17","cited_by_count":2,"area":"rag"},{"id":"2512.22195","title":"MatKV: Trading Compute for Flash Storage in LLM Inference","created":"2025-12-20","cited_by_count":2,"area":"rag"},{"id":"2601.02522","title":"On the Effectiveness of Proposed Techniques to Reduce Energy Consumption in RAG Systems: A Controlled Experiment","created":"2026-01-05","cited_by_count":2,"area":"rag"},{"id":"2601.08343","title":"When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges","created":"2026-01-13","cited_by_count":2,"area":"agents"},{"id":"2601.08743","title":"TableCache: Primary Foreign Key Guided KV Cache Precomputation for Low Latency Text-to-SQL","created":"2026-01-13","cited_by_count":2,"area":"inference"},{"id":"2604.08584","title":"CSAttention: Centroid-Scoring Attention for Accelerating LLM Inference","created":"2026-03-30","cited_by_count":2,"area":"inference"},{"id":"2606.04302","title":"LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding","created":"2026-06-03","cited_by_count":2,"area":"rag"},{"id":"2607.28069","title":"SemPIC: Learning Semantic Position-Independent KV Caches","created":"2026-07-30","cited_by_count":2,"area":"agents"},{"id":"2505.10951","title":"SubGCache: Accelerating Graph-based RAG with Subgraph-level KV Cache","created":"2025-05-16","cited_by_count":1,"area":"rag"},{"id":"2506.19651","title":"PEVLM: Parallel Encoding for Vision-Language Models","created":"2025-06-24","cited_by_count":1,"area":"mllm"},{"id":"2601.08670","title":"Parallel Context-of-Experts Decoding for Retrieval Augmented Generation","created":"2026-01-13","cited_by_count":1,"area":"rag"},{"id":"2603.09222","title":"EnComp: Lightweight Encoder-Only Context Compression for Retrieval-Augmented Question Answering","created":"2026-03-10","cited_by_count":1,"area":"rag"},{"id":"2605.08581","title":"PRISM: Fast Online LLM Serving via Scheduling-Memory Co-design","created":"2026-05-09","cited_by_count":1,"area":"rag"},{"id":"2605.27494","title":"Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?","created":"2026-05-26","cited_by_count":1,"area":"rag"},{"id":"2606.09441","title":"SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance","created":"2026-06-08","cited_by_count":1,"area":"rag"},{"id":"2606.19667","title":"CacheWeaver: Cache-Aware Evidence Ordering for Efficient Grounded RAG Inference","created":"2026-06-18","cited_by_count":1,"area":"rag"},{"id":"2607.28263","title":"CoMem: Reusing Transformer Depth across Queries with Persistent Intermediate Residuals","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2609.10266","title":"KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints","created":"2026-09-09","cited_by_count":1,"area":"inference"},{"id":"2609.17983","title":"Contiguity, Not Importance: Budgeted Repair of Stale KV Caches After Document Edits","created":"2026-09-16","cited_by_count":1,"area":"rag"},{"id":"2505.08261","title":"Enhancing Cache-Augmented Generation (CAG) with Adaptive Contextual Compression for Scalable Knowledge Integration","created":"2025-05-13","cited_by_count":0,"area":"rag"},{"id":"2509.25919","title":"Accelerating LLM Inference with Precomputed Query Storage","created":"2025-09-30","cited_by_count":0,"area":null},{"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":"2511.20662","title":"Democratizing LLM Efficiency: From Hyperscale Optimizations to Universal Deployability","created":"2025-11-03","cited_by_count":0,"area":"rag"},{"id":"2512.23049","title":"Accelerating Language Model Workflows with Prompt Choreography","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2604.20452","title":"HaS: Accelerating RAG through Homology-Aware Speculative Retrieval","created":"2026-04-22","cited_by_count":0,"area":"rag"},{"id":"2606.13097","title":"Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents","created":"2026-06-11","cited_by_count":0,"area":"agents"},{"id":"2607.24260","title":"KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems","created":"2026-07-27","cited_by_count":0,"area":"inference"},{"id":"2608.07458","title":"CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG","created":"2026-08-07","cited_by_count":0,"area":"rag"},{"id":"2608.30996","title":"Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generation","created":"2026-08-31","cited_by_count":0,"area":"rag"},{"id":"2609.09768","title":"Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?","created":"2026-09-09","cited_by_count":0,"area":"rag"},{"id":"2609.29245","title":"No More Free Lunch: Corpus Task Complexity Matters as Corpora Grow","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.31415","title":"Evaluating the accuracy of KV cache reuse techniques","created":"2026-09-25","cited_by_count":0,"area":"inference"},{"id":"2609.35139","title":"CacheRepair: Learning to Repair Cross-Chunk Context in RAG for KV Cache Fusion","created":"2026-09-28","cited_by_count":0,"area":"rag"},{"id":"2609.36722","title":"ATTUNER: Recomputation-Free KV Cache Reuse via Query-Side Adaptation","created":"2026-09-29","cited_by_count":0,"area":"inference"},{"id":"2610.12133","title":"Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13060","title":"KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse","created":"2026-10-09","cited_by_count":0,"area":"inference"},{"id":"2610.15186","title":"SAFE-KV: Causal Suffix Repair for Behavior-Preserving Non-Prefix KV Cache Reuse in RAG","created":"2026-10-10","cited_by_count":0,"area":"rag"},{"id":"2610.19247","title":"Copy-Paste Language Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}