{"total":114,"rows":[{"id":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880,"area":"inference"},{"id":"2310.06839","title":"LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression","created":"2023-10-10","cited_by_count":453,"area":"inference"},{"id":"2403.12968","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","created":"2024-03-19","cited_by_count":348,"area":"inference"},{"id":"2407.11550","title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","created":"2024-07-16","cited_by_count":235,"area":"inference"},{"id":"2405.16444","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","created":"2024-05-26","cited_by_count":223,"area":"inference"},{"id":"2310.07240","title":"CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving","created":"2023-10-11","cited_by_count":203,"area":"inference"},{"id":"2307.06945","title":"In-context Autoencoder for Context Compression in a Large Language Model","created":"2023-07-13","cited_by_count":199,"area":"inference"},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2404.11912","title":"TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding","created":"2024-04-18","cited_by_count":102,"area":"inference"},{"id":"2406.11430","title":"A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression","created":"2024-06-17","cited_by_count":86,"area":"inference"},{"id":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86,"area":"inference"},{"id":"2402.15220","title":"ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition","created":"2024-02-23","cited_by_count":82,"area":"inference"},{"id":"2510.00636","title":"Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution","created":"2025-10-01","cited_by_count":74,"area":"inference"},{"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":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60,"area":"inference"},{"id":"2502.00299","title":"ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference","created":"2025-02-01","cited_by_count":60,"area":"inference"},{"id":"2503.12491","title":"CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences","created":"2025-03-16","cited_by_count":58,"area":"inference"},{"id":"2504.15364","title":"KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments","created":"2025-04-21","cited_by_count":51,"area":"inference"},{"id":"2412.14838","title":"DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs","created":"2024-12-19","cited_by_count":42,"area":"inference"},{"id":"2402.06262","title":"On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference","created":"2024-02-09","cited_by_count":32,"area":"inference"},{"id":"2511.07278","title":"StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression","created":"2025-11-10","cited_by_count":26,"area":"inference"},{"id":"2406.02376","title":"Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs","created":"2024-06-04","cited_by_count":24,"area":"inference"},{"id":"2409.19272","title":"Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios","created":"2024-09-28","cited_by_count":23,"area":"inference"},{"id":"2505.12215","title":"GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment","created":"2025-05-18","cited_by_count":21,"area":"inference"},{"id":"2412.13649","title":"SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation","created":"2024-12-18","cited_by_count":20,"area":"inference"},{"id":"2406.05317","title":"LoCoCo: Dropping In Convolutions for Long Context Compression","created":"2024-06-08","cited_by_count":19,"area":"inference"},{"id":"2407.15504","title":"Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models","created":"2024-07-22","cited_by_count":19,"area":"inference"},{"id":"2503.10337","title":"KV-Distill: Nearly Lossless Learnable Context Compression for LLMs","created":"2025-03-13","cited_by_count":19,"area":"inference"},{"id":"2404.00489","title":"Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression","created":"2024-03-30","cited_by_count":18,"area":"inference"},{"id":"2407.08892","title":"Characterizing Prompt Compression Methods for Long Context Inference","created":"2024-07-11","cited_by_count":18,"area":"inference"},{"id":"2505.10938","title":"Accurate KV Cache Quantization with Outlier Tokens Tracing","created":"2025-05-16","cited_by_count":18,"area":"inference"},{"id":"2509.09754","title":"LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation","created":"2025-09-11","cited_by_count":16,"area":"inference"},{"id":"2410.03090","title":"UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective","created":"2024-10-04","cited_by_count":15,"area":"inference"},{"id":"2503.19114","title":"Understanding and Improving Information Preservation in Prompt Compression for LLMs","created":"2025-03-24","cited_by_count":15,"area":"inference"},{"id":"2502.14317","title":"ParallelComp: Parallel Long-Context Compressor for Length Extrapolation","created":"2025-02-20","cited_by_count":14,"area":"inference"},{"id":"2510.08907","title":"Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors","created":"2025-10-10","cited_by_count":14,"area":"inference"},{"id":"2504.08934","title":"Long Context In-Context Compression by Getting to the Gist of Gisting","created":"2025-04-11","cited_by_count":13,"area":"inference"},{"id":"2504.14051","title":"CAOTE: KV Cache Selection for LLMs via Attention Output Error-Based Token Eviction","created":"2025-04-18","cited_by_count":13,"area":"inference"},{"id":"2511.01815","title":"KV Cache Transform Coding for Compact Storage in LLM Inference","created":"2025-11-03","cited_by_count":13,"area":"inference"},{"id":"2602.01719","title":"COMI: Coarse-to-fine Context Compression via Marginal Information Gain","created":"2026-02-02","cited_by_count":13,"area":"inference"},{"id":"2404.15420","title":"XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference","created":"2024-04-23","cited_by_count":12,"area":"inference"},{"id":"2507.20030","title":"FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compression","created":"2025-07-26","cited_by_count":11,"area":"inference"},{"id":"2605.09649","title":"Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction","created":"2026-05-10","cited_by_count":11,"area":"inference"},{"id":"2502.00527","title":"PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration","created":"2025-02-01","cited_by_count":10,"area":"inference"},{"id":"2410.23079","title":"BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM Inference","created":"2024-10-30","cited_by_count":9,"area":"inference"},{"id":"2509.12211","title":"TinyServe: Query-Aware Cache Selection for Efficient LLM Serving","created":"2025-08-28","cited_by_count":9,"area":"inference"},{"id":"2603.00155","title":"EfficientPosterGen: Semantic-aware Efficient Poster Generation via Token Compression and Accurate Violation Detection","created":"2026-02-25","cited_by_count":9,"area":"inference"},{"id":"2605.08840","title":"ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing","created":"2026-05-09","cited_by_count":9,"area":"inference"},{"id":"2503.10714","title":"ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs","created":"2025-03-13","cited_by_count":8,"area":"inference"},{"id":"2505.00019","title":"An Empirical Study on Prompt Compression for Large Language Models","created":"2025-04-24","cited_by_count":8,"area":"inference"},{"id":"2512.04550","title":"AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees","created":"2025-12-04","cited_by_count":8,"area":"inference"},{"id":"2410.04139","title":"From Reading to Compressing: Exploring the Multi-document Reader for Prompt Compression","created":"2024-10-05","cited_by_count":7,"area":"inference"},{"id":"2505.15774","title":"Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention","created":"2025-05-21","cited_by_count":7,"area":"inference"},{"id":"2606.06256","title":"RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention","created":"2026-06-04","cited_by_count":7,"area":"inference"},{"id":"2411.18077","title":"MiniKV: Pushing the Limits of LLM Inference via 2-Bit Layer-Discriminative KV Cache","created":"2024-11-27","cited_by_count":6,"area":"inference"},{"id":"2506.07334","title":"Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models","created":"2025-06-09","cited_by_count":6,"area":"inference"},{"id":"2508.02053","title":"ProCut: LLM Prompt Compression via Attribution Estimation","created":"2025-08-04","cited_by_count":6,"area":"inference"},{"id":"2509.24832","title":"SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching","created":"2025-09-29","cited_by_count":6,"area":"inference"},{"id":"2606.17034","title":"KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing","created":"2026-06-15","cited_by_count":6,"area":"inference"},{"id":"2506.08373","title":"Draft-based Approximate Inference for LLMs","created":"2025-06-10","cited_by_count":5,"area":"inference"},{"id":"2509.19228","title":"CompLLM: Compression for Long Context Q&A","created":"2025-09-23","cited_by_count":5,"area":"inference"},{"id":"2603.14224","title":"Self-Indexing KVCache: Predicting Sparse Attention from Compressed Keys","created":"2026-03-15","cited_by_count":5,"area":"inference"},{"id":"2406.07528","title":"QuickLLaMA: Query-aware Inference Acceleration for Large Language Models","created":"2024-06-11","cited_by_count":4,"area":"inference"},{"id":"2412.08521","title":"EMS: Adaptive Evict-then-Merge Strategy for Head-wise KV Cache Compression Based on Global-Local Importance","created":"2024-12-11","cited_by_count":4,"area":"inference"},{"id":"2502.01025","title":"Knowing When to Stop: Efficient Context Processing via Latent Sufficiency Signals","created":"2025-02-03","cited_by_count":4,"area":"inference"},{"id":"2605.06676","title":"LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction","created":"2026-04-22","cited_by_count":4,"area":"inference"},{"id":"2605.07068","title":"WiCER: Wiki-memory Compile, Evaluate, Refine Iterative Knowledge Compilation for LLM Wiki Systems","created":"2026-05-08","cited_by_count":4,"area":"inference"},{"id":"2606.09659","title":"End-to-End Context Compression at Scale","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"id":"2405.11299","title":"The CAP Principle for LLM Serving: A Survey of Long-Context Large Language Model Serving","created":"2024-05-18","cited_by_count":3,"area":"inference"},{"id":"2412.05896","title":"XKV: Personalized KV Cache Memory Reduction for Long-Context LLM Inference","created":"2024-12-08","cited_by_count":3,"area":"inference"},{"id":"2605.09463","title":"Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven","created":"2026-05-10","cited_by_count":3,"area":"inference"},{"id":"2605.17304","title":"Compress the Context, Keep the Commitments: A Formal Framework for Verifiable LLM Context Compression","created":"2026-05-17","cited_by_count":3,"area":"inference"},{"id":"2605.18053","title":"Protection Is (Nearly) All You Need: Structural Protection Dominates Scoring in Globally Capped KV Eviction","created":"2026-05-18","cited_by_count":3,"area":"inference"},{"id":"2505.18092","title":"QwenLong-CPRS: Towards $\\infty$-LLMs with Dynamic Context Optimization","created":"2025-05-23","cited_by_count":2,"area":"inference"},{"id":"2603.12646","title":"98$\\times$ Faster LLM Routing Without a Dedicated GPU: Flash Attention, Prompt Compression, and Near-Streaming for the vLLM Semantic Router","created":"2026-03-13","cited_by_count":2,"area":"inference"},{"id":"2603.19635","title":"BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection","created":"2026-03-20","cited_by_count":2,"area":"inference"},{"id":"2604.09611","title":"Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows","created":"2026-03-12","cited_by_count":2,"area":"inference"},{"id":"2604.10044","title":"LoopGuard: Breaking Self-Reinforcing Attention Loops via Dynamic KV Cache Intervention","created":"2026-04-11","cited_by_count":2,"area":"inference"},{"id":"2605.13784","title":"Attention Once Is All You Need: Efficient Streaming Inference with Stateful Transformers","created":"2026-05-13","cited_by_count":2,"area":"inference"},{"id":"2605.21226","title":"OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization","created":"2026-05-20","cited_by_count":2,"area":"inference"},{"id":"2606.05698","title":"Rethinking LoRA Memory Through the Lens of KV Cache Compression","created":"2026-06-04","cited_by_count":2,"area":"inference"},{"id":"2609.04434","title":"What Attention Recalls and Recurrence Controls in Hybrid Language Models","created":"2026-09-03","cited_by_count":2,"area":"inference"},{"id":"2403.17411","title":"PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models","created":"2024-03-26","cited_by_count":1,"area":"inference"},{"id":"2507.19906","title":"CaliDrop: KV Cache Compression with Calibration","created":"2025-07-26","cited_by_count":1,"area":"inference"},{"id":"2511.03728","title":"Efficient On-Device Agents via Adaptive Context Management","created":"2025-09-24","cited_by_count":1,"area":"inference"},{"id":"2512.09238","title":"Training-free Context-adaptive Attention for Efficient Long Context Modeling","created":"2025-12-10","cited_by_count":1,"area":"inference"},{"id":"2602.01778","title":"Data Distribution Matters: A Data-Centric Perspective on Context Compression for Large Language Model","created":"2026-02-02","cited_by_count":1,"area":"inference"},{"id":"2602.20732","title":"CHESS: Context-aware Hierarchical Efficient Semantic Selection for Long-Context LLM Inference","created":"2026-02-24","cited_by_count":1,"area":"inference"},{"id":"2603.06642","title":"SR-TTT Does Not Learn Retrieval: A Correction and Mechanistic Post-Mortem of Surprisal-Aware Residual Test-Time Training","created":"2026-02-26","cited_by_count":1,"area":"inference"},{"id":"2604.23277","title":"From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors","created":"2026-04-25","cited_by_count":1,"area":"inference"},{"id":"2606.18406","title":"CoreMem: Riemannian Retrieval and Fisher-Guided Distillation for Long-Term Memory in Dialogue Agents","created":"2026-06-16","cited_by_count":1,"area":"inference"},{"id":"2607.01241","title":"Mapping Text to Multiplex Graph: Prompt Compression as L\\'evy Walk-Guided Graph Pruning","created":"2026-05-04","cited_by_count":1,"area":"inference"},{"id":"2608.09412","title":"KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models","created":"2026-08-10","cited_by_count":1,"area":"inference"},{"id":"2608.30647","title":"What It Costs to Compose, Rebuild, and Correct Precomputed Memory","created":"2026-08-31","cited_by_count":1,"area":"inference"},{"id":"2610.03198","title":"KV$^2$: A Self-Refining KV Cache","created":"2026-10-02","cited_by_count":1,"area":"inference"},{"id":"2603.29193","title":"Developing Adaptive Context Compression Techniques for Large Language Models (LLMs) in Long-Running Interactions","created":"2026-03-31","cited_by_count":0,"area":"inference"},{"id":"2604.15732","title":"Accuracy Is Speed: Towards Long-Context-Aware Routing for Distributed LLM Serving","created":"2026-04-17","cited_by_count":0,"area":"inference"},{"id":"2605.30574","title":"Probing the Prompt KV Cache: Where It Becomes Dispensable","created":"2026-05-28","cited_by_count":0,"area":"inference"},{"id":"2606.01336","title":"LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning","created":"2026-05-31","cited_by_count":0,"area":"inference"},{"id":"2606.01483","title":"MURMUR: An Efficient Inference System for Long-Form ASR","created":"2026-05-31","cited_by_count":0,"area":"inference"}],"next_cursor":"100"}