{"total":106,"rows":[{"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":"2401.07851","title":"Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding","created":"2024-01-15","cited_by_count":269,"area":"inference"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"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":"2503.00540","title":"Streaming Video Question-Answering with In-context Video KV-Cache Retrieval","created":"2025-03-01","cited_by_count":117,"area":"inference"},{"id":"2408.11049","title":"MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding","created":"2024-08-20","cited_by_count":91,"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":"2409.01227","title":"Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference","created":"2024-09-02","cited_by_count":53,"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":"2408.05499","title":"LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale","created":"2024-08-10","cited_by_count":31,"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":"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":"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":"2410.03960","title":"SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation","created":"2024-10-04","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":"2404.07979","title":"LLoCO: Learning Long Contexts Offline","created":"2024-04-11","cited_by_count":16,"area":"inference"},{"id":"2409.13761","title":"Do Large Language Models Need a Content Delivery Network?","created":"2024-09-16","cited_by_count":16,"area":"inference"},{"id":"2412.15803","title":"WebLLM: A High-Performance In-Browser LLM Inference Engine","created":"2024-12-20","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":"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":"2502.00085","title":"Efficient Beam Search for Large Language Models Using Trie-Based Decoding","created":"2025-01-31","cited_by_count":10,"area":"inference"},{"id":"2501.08192","title":"PRESERVE: Prefetching Model Weights and KV-Cache in Distributed LLM Serving","created":"2025-01-14","cited_by_count":9,"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":"2505.18231","title":"NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache","created":"2025-05-23","cited_by_count":7,"area":"inference"},{"id":"2507.11942","title":"DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression","created":"2025-07-16","cited_by_count":7,"area":"inference"},{"id":"2509.17396","title":"EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments","created":"2025-09-22","cited_by_count":7,"area":"inference"},{"id":"2605.05971","title":"Training Transformers for KV Cache Compressibility","created":"2026-05-07","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":"2607.07847","title":"When Does Continual Learning Require Learning","created":"2026-07-08","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":"2504.11004","title":"Dynamic Compressing Prompts for Efficient Inference of Large Language Models","created":"2025-04-15","cited_by_count":6,"area":"inference"},{"id":"2505.15347","title":"FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management","created":"2025-05-21","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":"2509.02121","title":"Batch Query Processing and Optimization for Agentic Workflows","created":"2025-09-02","cited_by_count":6,"area":"inference"},{"id":"2510.07915","title":"MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding","created":"2025-10-09","cited_by_count":6,"area":"inference"},{"id":"2606.04557","title":"Cartridges at Scale: Training Modular KV Caches over Large Document Collections","created":"2026-06-03","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":"2503.07956","title":"EFPC: Towards Efficient and Flexible Prompt Compression","created":"2025-03-11","cited_by_count":5,"area":"inference"},{"id":"2503.11816","title":"Key, Value, Compress: A Systematic Exploration of KV Cache Compression Techniques","created":"2025-03-14","cited_by_count":5,"area":"inference"},{"id":"2503.23294","title":"Cocktail: Chunk-Adaptive Mixed-Precision Quantization for Long-Context LLM Inference","created":"2025-03-30","cited_by_count":5,"area":"inference"},{"id":"2509.16495","title":"Shift Parallelism: Low-Latency, High-Throughput LLM Inference for Dynamic Workloads","created":"2025-09-20","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":"2409.15012","title":"Inference-Friendly Models With MixAttention","created":"2024-09-23","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":"2605.08317","title":"RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache","created":"2026-05-08","cited_by_count":4,"area":"inference"},{"id":"2605.23258","title":"A Simple Plug-in for Improving Eviction-Based KV Cache Compression","created":"2026-05-22","cited_by_count":4,"area":"inference"},{"id":"2607.28979","title":"KV Cache Translation across Heterogeneous Large Language Models","created":"2026-07-31","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":"2603.05663","title":"Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding","created":"2026-03-05","cited_by_count":3,"area":"inference"},{"id":"2603.16514","title":"FleetOpt: Analytical Fleet Provisioning for LLM Inference with Compress-and-Route as Implementation Mechanism","created":"2026-03-17","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":"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":"2605.24022","title":"Adaptive KV Cache Reuse for Fast Long-Context LLM Serving","created":"2026-05-20","cited_by_count":3,"area":"inference"},{"id":"2608.11231","title":"LinearKV: One Cached State Suffices for Position-Independent Caching in Hybrid LLMs","created":"2026-07-31","cited_by_count":3,"area":"inference"},{"id":"2411.05894","title":"SSSD: Simply-Scalable Speculative Decoding","created":"2024-11-08","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":"2603.02188","title":"Multi-Head Low-Rank Attention","created":"2026-03-02","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":"2605.04426","title":"Telegraph English: Semantic Prompt Compression via Structured Symbolic Rewriting","created":"2026-05-06","cited_by_count":2,"area":"inference"},{"id":"2605.06225","title":"Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs","created":"2026-05-07","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":"2606.05698","title":"Rethinking LoRA Memory Through the Lens of KV Cache Compression","created":"2026-06-04","cited_by_count":2,"area":"inference"},{"id":"2606.09061","title":"Fairness-Aware and Latency-Controllable Scheduling for Chunked-Prefill LLM Serving","created":"2026-06-08","cited_by_count":2,"area":"inference"},{"id":"2607.10987","title":"[AAFLOW+] Stateful Operator Abstraction with Zero-Copy Distributed KV Cache Orchestration for Multi-Agent Workflows","created":"2026-07-13","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":"2609.35621","title":"Cartridges++: KV Cache Compression without Off-Context Derailment","created":"2026-09-28","cited_by_count":2,"area":"inference"},{"id":"2511.21862","title":"OOCO: Latency-disaggregated Architecture for Online-Offline Co-locate LLM Serving","created":"2025-11-26","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":"2606.00021","title":"SENSE: Semantic Embedding Navigation with Soft-gated Evaluation for Retrieval-based Speculative Decoding","created":"2026-04-14","cited_by_count":1,"area":"inference"},{"id":"2606.09877","title":"Streaming Knowledge Compilation: Proactive Materiality-Scored Pinning for Time-Evolving LLM Wikis","created":"2026-06-03","cited_by_count":1,"area":"inference"},{"id":"2606.15157","title":"Exploring a Layer-Wise Design Space for KV Cache Eviction","created":"2026-06-13","cited_by_count":1,"area":"inference"},{"id":"2608.30310","title":"Tail-Replay: Escaping the Curse of Linear Attention in Prefix Caching for Hybrid LLMs","created":"2026-08-31","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":"2608.30811","title":"TopoCompress: Long Context Compression via Graph-Wired Semantic Trajectories","created":"2026-08-31","cited_by_count":1,"area":"inference"},{"id":"2609.11192","title":"FlexComp: One Model for Every Ratio in Context Compression","created":"2026-09-10","cited_by_count":1,"area":"inference"},{"id":"2609.16161","title":"LLM Inference in a Flash!","created":"2026-09-14","cited_by_count":1,"area":"inference"},{"id":"2409.00855","title":"LanguaShrink: Reducing Token Overhead with Psycholinguistics","created":"2024-09-01","cited_by_count":0,"area":"inference"},{"id":"2502.13374","title":"Task-agnostic Prompt Compression with Context-aware Sentence Embedding and Reward-guided Task Descriptor","created":"2025-02-19","cited_by_count":0,"area":"inference"},{"id":"2503.19950","title":"LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation","created":"2025-03-25","cited_by_count":0,"area":"inference"},{"id":"2604.16395","title":"Stream2LLM: Overlap Context Streaming and Prefill for Reduced Time-to-First-Token (TTFT)","created":"2026-03-29","cited_by_count":0,"area":"inference"},{"id":"2604.16864","title":"HieraSparse: Hierarchical Semi-Structured Sparse KV Attention","created":"2026-04-18","cited_by_count":0,"area":"inference"},{"id":"2605.06046","title":"Requests of a Feather Must Flock Together: Batch Size vs. Prefix Homogeneity in LLM Inference","created":"2026-05-07","cited_by_count":0,"area":"inference"},{"id":"2606.03739","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","created":"2026-06-02","cited_by_count":0,"area":"inference"},{"id":"2606.14779","title":"Unified KV Pooling to Accelerate Long-Context LLM Serving","created":"2026-06-10","cited_by_count":0,"area":"inference"},{"id":"2607.02574","title":"From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving","created":"2026-06-30","cited_by_count":0,"area":"inference"},{"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":"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":"2608.15584","title":"GraniKV: Asymmetric Granularity KV-Cache Paging for Multi-Agent Systems with Long Shared Prefix","created":"2026-08-16","cited_by_count":0,"area":"inference"},{"id":"2608.17336","title":"TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference Acceleration","created":"2026-08-18","cited_by_count":0,"area":"inference"}],"next_cursor":"100"}