{"total":106,"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":"2406.10774","title":"Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference","created":"2024-06-16","cited_by_count":501,"area":"inference"},{"id":"2406.02069","title":"PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling","created":"2024-06-04","cited_by_count":432,"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":"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":"2406.17565","title":"MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool","created":"2024-06-25","cited_by_count":68,"area":"inference"},{"id":"2410.12388","title":"Prompt Compression for Large Language Models: A Survey","created":"2024-10-16","cited_by_count":67,"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":"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":"2408.03675","title":"NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time","created":"2024-08-07","cited_by_count":43,"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":"2105.11618","title":"TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference","created":"2021-05-25","cited_by_count":40,"area":"inference"},{"id":"2402.01869","title":"InferCept: Efficient Intercept Support for Augmented Large Language Model Inference","created":"2024-02-02","cited_by_count":33,"area":"inference"},{"id":"2502.03805","title":"CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective","created":"2025-02-06","cited_by_count":26,"area":"inference"},{"id":"2405.19325","title":"Nearest Neighbor Speculative Decoding for LLM Generation and Attribution","created":"2024-05-29","cited_by_count":25,"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":"2502.12216","title":"Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs","created":"2025-02-17","cited_by_count":24,"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":"2407.08892","title":"Characterizing Prompt Compression Methods for Long Context Inference","created":"2024-07-11","cited_by_count":18,"area":"inference"},{"id":"2404.07979","title":"LLoCO: Learning Long Contexts Offline","created":"2024-04-11","cited_by_count":16,"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":"2510.08907","title":"Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors","created":"2025-10-10","cited_by_count":14,"area":"inference"},{"id":"2510.13334","title":"Taming the Fragility of KV Cache Eviction in LLM Inference","created":"2025-10-15","cited_by_count":14,"area":"inference"},{"id":"2506.07851","title":"Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning","created":"2025-06-09","cited_by_count":13,"area":"inference"},{"id":"2508.06447","title":"SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning","created":"2025-08-08","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":"2501.12959","title":"Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference","created":"2025-01-22","cited_by_count":12,"area":"inference"},{"id":"2412.12706","title":"More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression","created":"2024-12-17","cited_by_count":10,"area":"inference"},{"id":"2505.13204","title":"Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification","created":"2025-05-19","cited_by_count":10,"area":"inference"},{"id":"2507.11953","title":"IAM: Efficient Inference through Attention Mapping between Different-scale LLMs","created":"2025-07-16","cited_by_count":10,"area":"inference"},{"id":"2509.08315","title":"EvolKV: Evolutionary KV Cache Compression for LLM Inference","created":"2025-09-10","cited_by_count":10,"area":"inference"},{"id":"2409.14364","title":"Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models","created":"2024-09-22","cited_by_count":9,"area":"inference"},{"id":"2410.14042","title":"Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles","created":"2024-10-17","cited_by_count":9,"area":"inference"},{"id":"2404.15949","title":"CORM: Cache Optimization with Recent Message for Large Language Model Inference","created":"2024-04-24","cited_by_count":7,"area":"inference"},{"id":"2503.00392","title":"Progressive Sparse Attention: Algorithm and System Co-design for Efficient Attention in LLM Serving","created":"2025-03-01","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":"2506.05410","title":"Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs","created":"2025-06-04","cited_by_count":7,"area":"inference"},{"id":"2509.04377","title":"PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference","created":"2025-09-04","cited_by_count":7,"area":"inference"},{"id":"2510.20797","title":"No Mean Feat: Simple, Strong Baselines for Context Compression","created":"2025-10-23","cited_by_count":7,"area":"inference"},{"id":"2512.02337","title":"SpecPV: Improving Self-Speculative Decoding for Long-Context Generation via Partial Verification","created":"2025-12-02","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":"2409.15395","title":"Parse Trees Guided LLM Prompt Compression","created":"2024-09-23","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":"2602.08585","title":"Predicting Future Utility: Global Combinatorial Optimization for Task-Agnostic KV Cache Eviction","created":"2026-02-09","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":"2501.15113","title":"Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads","created":"2025-01-25","cited_by_count":5,"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":"2408.10497","title":"QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory","created":"2024-08-20","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":"2512.01953","title":"KV Pareto: Systems-Level Optimization of KV Cache and Model Compression for Long Context Inference","created":"2025-12-01","cited_by_count":4,"area":"inference"},{"id":"2604.05417","title":"Multi-Drafter Speculative Decoding with Alignment Feedback","created":"2026-04-07","cited_by_count":4,"area":"inference"},{"id":"2605.31105","title":"GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs","created":"2026-05-29","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":"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":"2505.05772","title":"Sparse Attention Remapping with Clustering for Efficient LLM Decoding on PIM","created":"2025-05-09","cited_by_count":3,"area":"inference"},{"id":"2506.01215","title":"Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers","created":"2025-06-01","cited_by_count":3,"area":"inference"},{"id":"2506.04642","title":"TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering","created":"2025-06-05","cited_by_count":3,"area":"inference"},{"id":"2506.18728","title":"PARALLELPROMPT: Extracting Parallelism from Large Language Model Queries","created":"2025-06-23","cited_by_count":3,"area":"inference"},{"id":"2603.19733","title":"PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction","created":"2026-03-20","cited_by_count":3,"area":"inference"},{"id":"2604.24647","title":"DepthKV: Layer-Dependent KV Cache Pruning for Long-Context LLM Inference","created":"2026-04-27","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":"2605.24022","title":"Adaptive KV Cache Reuse for Fast Long-Context LLM Serving","created":"2026-05-20","cited_by_count":3,"area":"inference"},{"id":"2504.21228","title":"CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing","created":"2025-04-29","cited_by_count":2,"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":"2509.01083","title":"DSDE: Dynamic Speculative Decoding with KLD Stability for Real-World Serving","created":"2025-09-01","cited_by_count":2,"area":"inference"},{"id":"2604.03270","title":"Knowledge Packs: Zero-Token Knowledge Delivery via KV Cache Injection","created":"2026-03-22","cited_by_count":2,"area":"inference"},{"id":"2605.18856","title":"SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference","created":"2026-05-13","cited_by_count":2,"area":"inference"},{"id":"2606.29563","title":"Coverage-Driven KV Cache Eviction for Efficient and Improved Inference of LLM","created":"2026-06-28","cited_by_count":2,"area":"inference"},{"id":"2607.19957","title":"HijackKV: New Threat in Position-Independent KV Cache Reuse","created":"2026-07-22","cited_by_count":2,"area":"inference"},{"id":"2607.23693","title":"Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV","created":"2026-07-26","cited_by_count":2,"area":"inference"},{"id":"2502.13251","title":"Neural Attention Search","created":"2025-02-18","cited_by_count":1,"area":"inference"},{"id":"2601.23180","title":"TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification","created":"2026-01-30","cited_by_count":1,"area":"inference"},{"id":"2602.00885","title":"Reliability-Aware Determinantal Point Processes for Robust Informative Data Selection in Large Language Models","created":"2026-01-31","cited_by_count":1,"area":"inference"},{"id":"2604.07815","title":"AsyncTLS: Efficient Generative LLM Inference with Asynchronous Two-level Sparse Attention","created":"2026-04-09","cited_by_count":1,"area":"inference"},{"id":"2604.21231","title":"SparKV: Overhead-Aware KV Cache Loading for Efficient On-Device LLM Inference","created":"2026-04-23","cited_by_count":1,"area":"inference"},{"id":"2605.01910","title":"Stochastic Sparse Attention for Memory-Bound Inference","created":"2026-05-03","cited_by_count":1,"area":"inference"},{"id":"2605.07234","title":"Reformulating KV Cache Eviction Problem for Long-Context LLM Inference","created":"2026-05-08","cited_by_count":1,"area":"inference"},{"id":"2606.14875","title":"Context Compression Is Not One Thing: Readable Symbolic Re-expression vs. Coherent Summary at Matched Budget","created":"2026-06-12","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":"2609.05707","title":"Intra-Prompt Parallel Decoding for Common-Context Question Answering","created":"2026-09-04","cited_by_count":1,"area":"inference"},{"id":"2609.24298","title":"KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation","created":"2026-09-21","cited_by_count":1,"area":"inference"},{"id":"2609.25537","title":"Compressing Long Context into Answer-Aligned Memory Embeddings for LLM Inference","created":"2026-09-22","cited_by_count":1,"area":"inference"},{"id":"2609.36835","title":"ARC-KV: Amortizing Anchor Search for Reconstruction-Based KV Cache Compaction","created":"2026-09-29","cited_by_count":1,"area":"inference"},{"id":"2609.39329","title":"PatchKV: Weight-Space Compensation of KV Cache","created":"2026-09-30","cited_by_count":1,"area":"inference"},{"id":"2603.25926","title":"Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio","created":"2026-03-26","cited_by_count":0,"area":"inference"},{"id":"2605.09735","title":"KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving","created":"2026-05-10","cited_by_count":0,"area":"inference"},{"id":"2605.16637","title":"HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling","created":"2026-05-15","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":"2606.18056","title":"ConSA: Controllable Sparsity in Hybrid Attention via Learnable Allocation","created":"2026-06-16","cited_by_count":0,"area":"inference"},{"id":"2607.17486","title":"SALT: Salience-Aware Lexical Trie for Long-Context Compression","created":"2026-07-20","cited_by_count":0,"area":"inference"},{"id":"2607.25335","title":"Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors","created":"2026-07-28","cited_by_count":0,"area":"inference"},{"id":"2608.04569","title":"Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression","created":"2026-08-05","cited_by_count":0,"area":"inference"},{"id":"2608.11218","title":"MaSRead: Content-Addressed Reading of Replicated Latent Stores","created":"2026-07-21","cited_by_count":0,"area":"inference"},{"id":"2609.30884","title":"CacheReforge: Bounded Recovery for Stale KV Caches under Evolving Adapters","created":"2026-09-25","cited_by_count":0,"area":"inference"},{"id":"2609.32474","title":"PC-SubMax: Efficient Prompt Compression via Regularized Submodular Maximization","created":"2026-09-26","cited_by_count":0,"area":"inference"},{"id":"2609.33334","title":"When to Evict, Not What to Keep: Draft-Guided Eviction for Training-Free KV-Cache Compression","created":"2026-09-27","cited_by_count":0,"area":"inference"}],"next_cursor":"100"}