{"total":93,"rows":[{"id":"2407.00079","title":"Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving","created":"2024-06-24","cited_by_count":196,"area":"inference"},{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167,"area":null},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2407.08454","title":"Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks","created":"2024-07-11","cited_by_count":96,"area":"inference"},{"id":"2501.16383","title":"RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations","created":"2025-01-25","cited_by_count":46,"area":"inference"},{"id":"2410.08584","title":"ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification","created":"2024-10-11","cited_by_count":44,"area":"mllm"},{"id":"2410.23317","title":"VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration","created":"2024-10-29","cited_by_count":43,"area":"mllm"},{"id":"2502.04420","title":"KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference","created":"2025-02-06","cited_by_count":40,"area":"inference"},{"id":"2411.02886","title":"TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection","created":"2024-11-05","cited_by_count":39,"area":"inference"},{"id":"2412.14363","title":"ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals","created":"2024-12-18","cited_by_count":36,"area":null},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2412.03131","title":"DiffKV: Differentiated Memory Management for Large Language Models with Parallel KV Compaction","created":"2024-12-04","cited_by_count":26,"area":"inference"},{"id":"2501.19392","title":"Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models","created":"2025-01-31","cited_by_count":24,"area":"inference"},{"id":"2602.02958","title":"Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization","created":"2026-02-03","cited_by_count":23,"area":"diffusion"},{"id":"2505.19602","title":"Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression","created":"2025-05-26","cited_by_count":22,"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":"2412.08890","title":"Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries","created":"2024-12-12","cited_by_count":17,"area":"inference"},{"id":"2410.00428","title":"LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management","created":"2024-10-01","cited_by_count":16,"area":"inference"},{"id":"2504.09261","title":"Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling","created":"2025-04-12","cited_by_count":15,"area":"inference"},{"id":"2601.07891","title":"KVzap: Fast, Adaptive, and Faithful KV Cache Pruning","created":"2026-01-12","cited_by_count":15,"area":"inference"},{"id":"2502.20330","title":"RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding","created":"2025-02-27","cited_by_count":14,"area":"rag"},{"id":"2505.20334","title":"Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query","created":"2025-05-24","cited_by_count":14,"area":"inference"},{"id":"2503.16257","title":"Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models","created":"2025-03-20","cited_by_count":13,"area":"inference"},{"id":"2409.12963","title":"Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner","created":"2024-09-19","cited_by_count":11,"area":null},{"id":"2512.16822","title":"MEPIC: Memory Efficient Position Independent Caching for LLM Serving","created":"2025-12-18","cited_by_count":11,"area":"rag"},{"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":"2505.19586","title":"TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization","created":"2025-05-26","cited_by_count":10,"area":"inference"},{"id":"2508.15601","title":"LMDeploy Accelerates Mixed-Precision LLM Inference with TurboMind","created":"2025-08-21","cited_by_count":10,"area":"inference"},{"id":"2510.05373","title":"KVLinC : KV Cache Quantization with Hadamard Rotation and Linear Correction","created":"2025-10-06","cited_by_count":10,"area":"inference"},{"id":"2512.14946","title":"EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving","created":"2025-12-16","cited_by_count":10,"area":"inference"},{"id":"2503.16163","title":"SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs","created":"2025-03-20","cited_by_count":9,"area":"inference"},{"id":"2507.06517","title":"SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers","created":"2025-07-09","cited_by_count":9,"area":"inference"},{"id":"2602.08005","title":"ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference","created":"2026-02-08","cited_by_count":9,"area":"inference"},{"id":"2605.17757","title":"OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization","created":"2026-05-18","cited_by_count":9,"area":"inference"},{"id":"2503.24000","title":"Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving","created":"2025-03-31","cited_by_count":8,"area":"inference"},{"id":"2410.15252","title":"Lossless KV Cache Compression to 2%","created":"2024-10-20","cited_by_count":7,"area":"inference"},{"id":"2503.24358","title":"SQuat: Subspace-orthogonal KV Cache Quantization","created":"2025-03-31","cited_by_count":7,"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":"2505.22913","title":"Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference","created":"2025-05-28","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":"2604.04722","title":"Don't Waste Bits! Adaptive KV-Cache Quantization for Lightweight On-Device LLMs","created":"2026-04-06","cited_by_count":7,"area":"inference"},{"id":"2605.25475","title":"IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference","created":"2026-05-25","cited_by_count":7,"area":"inference"},{"id":"2505.22107","title":"Curse of High Dimensionality Issue in Transformer for Long-context Modeling","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2604.19157","title":"SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving","created":"2026-04-21","cited_by_count":5,"area":"inference"},{"id":"2605.19660","title":"OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond","created":"2026-05-19","cited_by_count":5,"area":"inference"},{"id":"2409.16546","title":"AlignedKV: Reducing Memory Access of KV-Cache with Precision-Aligned Quantization","created":"2024-09-25","cited_by_count":4,"area":"inference"},{"id":"2507.00605","title":"Quantize-Sample-and-Verify: LLM Acceleration via Adaptive Edge-Cloud Speculative Decoding","created":"2025-07-01","cited_by_count":4,"area":null},{"id":"2508.10395","title":"XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization","created":"2025-08-14","cited_by_count":4,"area":"inference"},{"id":"2510.06175","title":"VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization","created":"2025-10-07","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":"2607.08057","title":"Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization","created":"2026-07-09","cited_by_count":4,"area":"inference"},{"id":"2502.12085","title":"APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2504.18579","title":"Sparsity Forcing: Reinforcing Token Sparsity of MLLMs","created":"2025-04-23","cited_by_count":3,"area":"inference"},{"id":"2506.04390","title":"Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG","created":"2025-06-04","cited_by_count":3,"area":"rag"},{"id":"2507.19823","title":"HCAttention: Extreme KV Cache Compression via Heterogeneous Attention Computing for LLMs","created":"2025-07-26","cited_by_count":3,"area":"inference"},{"id":"2603.04592","title":"From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2605.12464","title":"Search Your Block Floating Point Scales!","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2605.17170","title":"TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks","created":"2026-05-16","cited_by_count":3,"area":"agents"},{"id":"2408.04107","title":"FDC: Fast KV Dimensionality Compression for Efficient LLM Inference","created":"2024-08-07","cited_by_count":2,"area":"inference"},{"id":"2604.18137","title":"AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization","created":"2026-04-20","cited_by_count":2,"area":null},{"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":"2607.28069","title":"SemPIC: Learning Semantic Position-Independent KV Caches","created":"2026-07-30","cited_by_count":2,"area":"agents"},{"id":"2608.05326","title":"QEvict: Recoverable Quantized KV Eviction for Attention-Drift-Robust Long-Context Decoding","created":"2026-08-05","cited_by_count":2,"area":null},{"id":"2507.19906","title":"CaliDrop: KV Cache Compression with Calibration","created":"2025-07-26","cited_by_count":1,"area":"inference"},{"id":"2605.03884","title":"QKVShare: Quantized KV-Cache Handoff for Multi-Agent On-Device LLMs","created":"2026-05-05","cited_by_count":1,"area":"agents"},{"id":"2606.07116","title":"OffQ: Taming Structured Outliers in LLM Quantization by Offsetting","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.08302","title":"HACK++: Towards More Effective Head-Aware Key-Value Compression for Efficient Visual Autoregressive Modeling","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2606.24033","title":"RoPE-Aware Bit Allocation for KV-Cache Quantization","created":"2026-06-23","cited_by_count":1,"area":"inference"},{"id":"2607.24555","title":"LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2608.13263","title":"vToken: Token-Level Virtualization for Reclaimable KV Caches","created":"2026-08-13","cited_by_count":1,"area":"inference"},{"id":"2610.00412","title":"EchoPress: Query-Agnostic KV Cache Pruning via Virtual Context Reconstruction","created":"2026-09-30","cited_by_count":1,"area":"inference"},{"id":"2510.05176","title":"PatternKV: Flattening KV Representation Expands Quantization Headroom","created":"2025-10-05","cited_by_count":0,"area":"lr"},{"id":"2602.08329","title":"Near-Oracle KV Selection via Pre-hoc Sparsity for Long-Context Inference","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2605.22337","title":"Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression","created":"2026-05-21","cited_by_count":0,"area":"inference"},{"id":"2607.01065","title":"GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache","created":"2026-07-01","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":"2607.05399","title":"Benchmarking KV-Cache Optimizations across Task Quality and System Performance for Long-Context Serving","created":"2026-05-03","cited_by_count":0,"area":"inference"},{"id":"2607.16213","title":"SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation","created":"2026-05-19","cited_by_count":0,"area":"inference"},{"id":"2608.07855","title":"CommitKV: Lifecycle-Aware KV Cache Compression via Commit Transitions for Multi-Turn Agents","created":"2026-08-08","cited_by_count":0,"area":"inference"},{"id":"2608.22237","title":"Read Less, Solve More: Token-Efficient Sparse Reading for AI Agents","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.23834","title":"Minima-KV: Retention-Preserving KV Cache Compression with Mixed-Format Paged Attention","created":"2026-08-24","cited_by_count":0,"area":"inference"},{"id":"2608.28911","title":"SemKV: Semantic Mixed-Precision KV Cache Quantization Guided by the Quality Cliff for Long-Context LLM Inference","created":"2026-08-28","cited_by_count":0,"area":"inference"},{"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":"2609.06940","title":"Unified AI Gateway: A Framework for Joint Model Routing and KV Cache Management","created":"2026-09-07","cited_by_count":0,"area":"inference"},{"id":"2609.07966","title":"MetaKV: Adaptive KV Cache Compression for Constrained LLM Inference","created":"2026-09-07","cited_by_count":0,"area":"inference"},{"id":"2609.33536","title":"Does Execution Require Target KV Fidelity? A Mixed-Fidelity KV Runtime for LLM Serving","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"id":"2610.05685","title":"Spend Bytes on Breadth: Precision-Count Trade-offs for Decode-Time KV Compression in Long Chain-of-Thought Reasoning","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.11245","title":"Read What Matters: Query-Adaptive Quantization for KV Caches","created":"2026-10-08","cited_by_count":0,"area":"inference"},{"id":"2610.12514","title":"CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches","created":"2026-10-07","cited_by_count":0,"area":"diffusion"},{"id":"2610.15324","title":"TempoKV: Predictive KV Cache Quantization for Autoregressive Video Generation","created":"2026-10-11","cited_by_count":0,"area":"diffusion"},{"id":"2610.15384","title":"E8 Lattice Key Quantization for Low-Bit KV-Cache Compression","created":"2026-10-11","cited_by_count":0,"area":"inference"},{"id":"2610.17966","title":"BELT : BEhavior-Aligned Low-Rank KV Cache Compression with Learned Top-k Rank Allocation","created":"2026-10-13","cited_by_count":0,"area":"inference"},{"id":"2610.18642","title":"MultiAlloc: Budget-Aware Precision Allocation for KV Cache Quantization","created":"2026-10-13","cited_by_count":0,"area":"inference"}],"next_cursor":null}