{"total":126,"rows":[{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383,"area":null},{"id":"2407.00079","title":"Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving","created":"2024-06-24","cited_by_count":196,"area":"inference"},{"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":"2404.09526","title":"LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism","created":"2024-04-15","cited_by_count":112,"area":"inference"},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"id":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97,"area":"inference"},{"id":"2407.12820","title":"PQCache: Product Quantization-based KVCache for Long Context LLM Inference","created":"2024-07-01","cited_by_count":95,"area":"inference"},{"id":"2408.05646","title":"Eigen Attention: Attention in Low-Rank Space for KV Cache Compression","created":"2024-08-10","cited_by_count":72,"area":"lr"},{"id":"2407.14057","title":"LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference","created":"2024-07-19","cited_by_count":70,"area":"inference"},{"id":"2412.03213","title":"ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression","created":"2024-12-04","cited_by_count":65,"area":"lr"},{"id":"2405.10637","title":"Layer-Condensed KV Cache for Efficient Inference of Large Language Models","created":"2024-05-17","cited_by_count":59,"area":"inference"},{"id":"2407.12391","title":"LLM Inference Serving: Survey of Recent Advances and Opportunities","created":"2024-07-17","cited_by_count":46,"area":null},{"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":"2506.04301","title":"The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective","created":"2025-06-04","cited_by_count":39,"area":"lr"},{"id":"2406.06467","title":"How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad","created":"2024-06-10","cited_by_count":36,"area":null},{"id":"2502.15734","title":"Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation","created":"2025-02-05","cited_by_count":36,"area":"rag"},{"id":"2405.14722","title":"DAPE: Data-Adaptive Positional Encoding for Length Extrapolation","created":"2024-05-23","cited_by_count":31,"area":null},{"id":"2501.06425","title":"Tensor Product Attention Is All You Need","created":"2025-01-11","cited_by_count":31,"area":null},{"id":"2506.08889","title":"SeerAttention-R: Sparse Attention Adaptation for Long Reasoning","created":"2025-06-10","cited_by_count":30,"area":"lr"},{"id":"2504.02441","title":"Cognitive Memory in Large Language Models","created":"2025-04-03","cited_by_count":29,"area":null},{"id":"2412.09616","title":"V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding","created":"2024-12-12","cited_by_count":28,"area":"mllm"},{"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":"2502.03805","title":"CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective","created":"2025-02-06","cited_by_count":26,"area":"inference"},{"id":"2503.18292","title":"Jenga: Effective Memory Management for Serving LLM with Heterogeneity","created":"2025-03-24","cited_by_count":25,"area":"inference"},{"id":"2503.00979","title":"Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLMs","created":"2025-03-02","cited_by_count":20,"area":"inference"},{"id":"2502.01941","title":"Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression","created":"2025-02-04","cited_by_count":16,"area":"lr"},{"id":"2502.18755","title":"M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type","created":"2025-02-26","cited_by_count":16,"area":null},{"id":"2503.18893","title":"xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction","created":"2025-03-24","cited_by_count":16,"area":"inference"},{"id":"2506.15969","title":"LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning","created":"2025-06-19","cited_by_count":16,"area":"lr"},{"id":"2502.12632","title":"MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation","created":"2025-02-18","cited_by_count":14,"area":"diffusion"},{"id":"2602.10238","title":"Learning to Evict from Key-Value Cache","created":"2026-02-10","cited_by_count":14,"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":"2412.04652","title":"Cross-Self KV Cache Pruning for Efficient Vision-Language Inference","created":"2024-12-05","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":"2508.06297","title":"KV Cache Compression for Inference Efficiency in LLMs: A Review","created":"2025-08-08","cited_by_count":12,"area":"inference"},{"id":"2409.19315","title":"Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models","created":"2024-09-28","cited_by_count":11,"area":null},{"id":"2411.05787","title":"RefreshKV: Updating Small KV Cache During Long-form Generation","created":"2024-11-08","cited_by_count":11,"area":"inference"},{"id":"2510.07318","title":"Artificial Hippocampus Networks for Efficient Long-Context Modeling","created":"2025-10-08","cited_by_count":11,"area":null},{"id":"2511.20172","title":"Beluga: A CXL-Based Memory Architecture for Scalable and Efficient LLM KVCache Management","created":"2025-11-25","cited_by_count":11,"area":"inference"},{"id":"2410.04798","title":"DAPE V2: Process Attention Score as Feature Map for Length Extrapolation","created":"2024-10-07","cited_by_count":10,"area":null},{"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":"2507.14204","title":"LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models","created":"2025-07-14","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":"2407.20485","title":"A2SF: Accumulative Attention Scoring with Forgetting Factor for Token Pruning in Transformer Decoder","created":"2024-07-30","cited_by_count":8,"area":"inference"},{"id":"2501.06709","title":"Mell: Memory-Efficient Large Language Model Serving via Multi-GPU KV Cache Management","created":"2025-01-12","cited_by_count":8,"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":"2411.12593","title":"AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction","created":"2024-11-19","cited_by_count":7,"area":null},{"id":"2412.20677","title":"Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA","created":"2024-12-30","cited_by_count":7,"area":null},{"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":"2506.02572","title":"HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference","created":"2025-06-03","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":"2505.14884","title":"Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity","created":"2025-05-20","cited_by_count":6,"area":null},{"id":"2507.09025","title":"Lizard: An Efficient Linearization Framework for Large Language Models","created":"2025-07-11","cited_by_count":6,"area":null},{"id":"2512.03870","title":"Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers","created":"2025-12-03","cited_by_count":6,"area":"inference"},{"id":"2408.01890","title":"Cross-layer Attention Sharing for Pre-trained Large Language Models","created":"2024-08-04","cited_by_count":5,"area":"inference"},{"id":"2506.15155","title":"eLLM: Elastic Memory Management Framework for Efficient LLM Serving","created":"2025-06-18","cited_by_count":5,"area":"inference"},{"id":"2509.07379","title":"DuoServe-MoE: Dual-Phase Expert Prefetch and Caching for LLM Inference QoS Assurance","created":"2025-09-09","cited_by_count":5,"area":"moe"},{"id":"2601.22037","title":"Optimizing Agentic Workflows using Meta-tools","created":"2026-01-29","cited_by_count":5,"area":"agents"},{"id":"2605.17613","title":"VeriCache: Turning Lossy KV Cache into Lossless LLM Inference","created":"2026-05-17","cited_by_count":5,"area":"inference"},{"id":"2405.18400","title":"Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass","created":"2024-05-28","cited_by_count":4,"area":null},{"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":"2506.11104","title":"DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration","created":"2025-06-06","cited_by_count":4,"area":"inference"},{"id":"2507.03153","title":"HGCA: Hybrid GPU-CPU Attention for Long Context LLM Inference","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2507.07694","title":"SAS: Simulated Attention Score","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2508.09001","title":"Retrospective Sparse Attention for Efficient Long-Context Generation","created":"2025-08-12","cited_by_count":4,"area":"inference"},{"id":"2510.18245","title":"Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2511.00321","title":"Scalable Processing-Near-Memory for 1M-Token LLM Inference: CXL-Enabled KV-Cache Management Beyond GPU Limits","created":"2025-10-31","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":"2605.12825","title":"Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion","created":"2026-05-12","cited_by_count":4,"area":"diffusion"},{"id":"2607.01520","title":"The risk of KV cache compression","created":"2026-07-01","cited_by_count":4,"area":"inference"},{"id":"2607.08032","title":"What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents","created":"2026-07-09","cited_by_count":4,"area":"agents"},{"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":"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":"2504.03661","title":"MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Quantization","created":"2025-03-12","cited_by_count":3,"area":"inference"},{"id":"2505.17331","title":"ECHO-LLaMA: Efficient Caching for High-Performance LLaMA Training","created":"2025-05-22","cited_by_count":3,"area":null},{"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":"2510.18250","title":"ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2511.16786","title":"Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach","created":"2025-11-20","cited_by_count":3,"area":"mllm"},{"id":"2602.05305","title":"FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion","created":"2026-02-05","cited_by_count":3,"area":"diffusion"},{"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":"2607.29591","title":"ResKV: Reconstructing Omitted Attention Contributions for Fixed-Budget KV Cache Compression","created":"2026-07-31","cited_by_count":3,"area":"inference"},{"id":"2408.04107","title":"FDC: Fast KV Dimensionality Compression for Efficient LLM Inference","created":"2024-08-07","cited_by_count":2,"area":"inference"},{"id":"2409.11650","title":"Art and Science of Quantizing Large-Scale Models: A Comprehensive Overview","created":"2024-09-18","cited_by_count":2,"area":null},{"id":"2502.13542","title":"Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2507.13681","title":"LoopServe: An Adaptive Dual-phase LLM Inference Acceleration System for Multi-Turn Dialogues","created":"2025-07-18","cited_by_count":2,"area":"inference"},{"id":"2508.08446","title":"OverFill: Two-Stage Models for Efficient Language Model Decoding","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2508.19740","title":"Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval","created":"2025-08-27","cited_by_count":2,"area":"inference"},{"id":"2602.07721","title":"ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs","created":"2026-02-07","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":"2604.18529","title":"HybridGen: Efficient LLM Generative Inference via CPU-GPU Hybrid Computing","created":"2026-04-20","cited_by_count":2,"area":"inference"},{"id":"2605.14037","title":"Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility","created":"2026-05-13","cited_by_count":2,"area":"lr"},{"id":"2606.16135","title":"SwiftCache: Efficient LLM Serving for Multi-turn Conversations with Heterogeneous KV Cache Sharing","created":"2026-06-15","cited_by_count":2,"area":"inference"},{"id":"2608.07001","title":"Every Cache Entry Earns Its Place: Global Allocation of Resolution and Coverage for KV Cache Compression","created":"2026-08-07","cited_by_count":2,"area":"inference"},{"id":"2502.13251","title":"Neural Attention Search","created":"2025-02-18","cited_by_count":1,"area":"inference"},{"id":"2504.17069","title":"Distilling Specialized Orders for Visual Generation","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2507.00797","title":"VEDA: Efficient LLM Generation Through Voting-based KV Cache Eviction and Dataflow-flexible Accelerator","created":"2025-07-01","cited_by_count":1,"area":"inference"},{"id":"2507.08045","title":"Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing","created":"2025-07-10","cited_by_count":1,"area":"inference"},{"id":"2602.00874","title":"Sublinear Time Quantum Algorithm for Attention Approximation","created":"2026-01-31","cited_by_count":1,"area":null}],"next_cursor":"100"}