{"total":89,"rows":[{"id":"2410.21465","title":"ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference","created":"2024-10-28","cited_by_count":134,"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":"2409.10516","title":"RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval","created":"2024-09-16","cited_by_count":116,"area":null},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"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":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68,"area":"lr"},{"id":"2502.14051","title":"RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression","created":"2025-02-19","cited_by_count":41,"area":"inference"},{"id":"2501.06425","title":"Tensor Product Attention Is All You Need","created":"2025-01-11","cited_by_count":31,"area":null},{"id":"2412.14468","title":"HashAttention: Semantic Sparsity for Faster Inference","created":"2024-12-19","cited_by_count":24,"area":null},{"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":"2504.05646","title":"Lattice: Learning to Efficiently Compress the Memory","created":"2025-04-08","cited_by_count":19,"area":null},{"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":"2601.21896","title":"Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video Diffusion","created":"2026-01-29","cited_by_count":16,"area":"diffusion"},{"id":"2602.10238","title":"Learning to Evict from Key-Value Cache","created":"2026-02-10","cited_by_count":14,"area":"inference"},{"id":"2512.12087","title":"BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding","created":"2025-12-12","cited_by_count":13,"area":null},{"id":"2505.23666","title":"LoLA: Low-Rank Linear Attention With Sparse Caching","created":"2025-05-29","cited_by_count":12,"area":null},{"id":"2510.24273","title":"SALS: Sparse Attention in Latent Space for KV cache Compression","created":"2025-10-28","cited_by_count":11,"area":"inference"},{"id":"2410.13184","title":"Router-Tuning: A Simple and Effective Approach for Enabling Dynamic-Depth in Transformers","created":"2024-10-17","cited_by_count":10,"area":null},{"id":"2505.21487","title":"Hardware-Efficient Attention for Fast Decoding","created":"2025-05-27","cited_by_count":10,"area":"inference"},{"id":"2512.05916","title":"KQ-SVD: Compressing the KV Cache with Provable Guarantees on Attention Fidelity","created":"2025-12-05","cited_by_count":10,"area":"inference"},{"id":"2512.16391","title":"Kascade: A Practical Sparse Attention Method for Long-Context LLM Inference","created":"2025-12-18","cited_by_count":10,"area":"lr"},{"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":"2602.03152","title":"FASA: Frequency-aware Sparse Attention","created":"2026-02-03","cited_by_count":8,"area":"inference"},{"id":"2606.03928","title":"Value-Aware Stochastic KV Cache Eviction for Reasoning Models","created":"2026-06-02","cited_by_count":8,"area":"lr"},{"id":"2502.12665","title":"A$^2$ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization","created":"2025-02-18","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":"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":"2502.15304","title":"SVDq: 1.25-bit and 410x Key Cache Compression for LLM Attention","created":"2025-02-21","cited_by_count":6,"area":"inference"},{"id":"2509.00388","title":"GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Eviction","created":"2025-08-30","cited_by_count":6,"area":"inference"},{"id":"2510.05688","title":"vAttention: Verified Sparse Attention","created":"2025-10-07","cited_by_count":6,"area":null},{"id":"2502.06766","title":"Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs","created":"2025-02-10","cited_by_count":5,"area":null},{"id":"2508.12969","title":"Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation","created":"2025-08-18","cited_by_count":5,"area":null},{"id":"2511.11907","title":"KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference","created":"2025-11-14","cited_by_count":5,"area":"inference"},{"id":"2512.23852","title":"Trellis: Learning to Compress Key-Value Memory in Attention Models","created":"2025-12-29","cited_by_count":5,"area":null},{"id":"2602.05929","title":"KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs","created":"2026-02-05","cited_by_count":5,"area":"inference"},{"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":"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":"2509.10798","title":"Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction","created":"2025-09-13","cited_by_count":4,"area":"inference"},{"id":"2510.13602","title":"NOSA: Native and Offloadable Sparse Attention","created":"2025-10-15","cited_by_count":4,"area":"inference"},{"id":"2510.23649","title":"Efficient Low Rank Attention for Long-Context Inference in Large Language Models","created":"2025-10-25","cited_by_count":4,"area":null},{"id":"2512.07647","title":"A Mathematical Theory of Top-$k$ Sparse Attention via Total Variation Distance","created":"2025-12-08","cited_by_count":4,"area":null},{"id":"2512.17452","title":"KV Admission: Learning What to Write for Efficient Long-Context LLM Inference","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2603.19664","title":"The Residual Stream Is All You Need: On the Redundancy of the KV Cache in Transformer Inference","created":"2026-03-20","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":"2506.01215","title":"Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers","created":"2025-06-01","cited_by_count":3,"area":"inference"},{"id":"2510.20787","title":"Alleviating Forgetfulness of Linear Attention by Hybrid Sparse Attention and Contextualized Learnable Token Eviction","created":"2025-10-23","cited_by_count":3,"area":"inference"},{"id":"2601.07667","title":"Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference","created":"2026-01-12","cited_by_count":3,"area":"inference"},{"id":"2602.06283","title":"SOCKET: SOft Collision Kernel EsTimator for Sparse Attention","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2602.08722","title":"QUOKA: Query-Oriented KV Selection For Efficient LLM Prefill","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2605.07719","title":"An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference","created":"2026-05-08","cited_by_count":3,"area":"inference"},{"id":"2511.14510","title":"LiteCache: A Query Similarity-Driven, GPU-Centric KVCache Subsystem for Efficient LLM Inference","created":"2025-11-18","cited_by_count":2,"area":"inference"},{"id":"2602.14209","title":"MAGE: All-[MASK] Block Already Knows Where to Look in Block Diffusion LLM","created":"2026-02-15","cited_by_count":2,"area":null},{"id":"2603.04427","title":"Thin Keys, Full Values: Reducing KV Cache via Low-Dimensional Attention Selection","created":"2026-02-16","cited_by_count":2,"area":"inference"},{"id":"2603.22300","title":"Scaling Attention via Feature Sparsity","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2604.01609","title":"Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression","created":"2026-04-02","cited_by_count":2,"area":"inference"},{"id":"2604.08584","title":"CSAttention: Centroid-Scoring Attention for Accelerating LLM Inference","created":"2026-03-30","cited_by_count":2,"area":"inference"},{"id":"2607.09052","title":"COBS: Cumulant Order Block Sparse Attention","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2506.05300","title":"Power Law Guided Dynamic Sifting for Efficient Attention","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2510.21956","title":"Transformer Based Linear Attention with Optimized GPU Kernel Implementation","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2511.18936","title":"SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression","created":"2025-11-24","cited_by_count":1,"area":"inference"},{"id":"2601.19178","title":"CollectiveKV: Decoupling and Sharing Collaborative Information in Sequential Recommendation","created":"2026-01-27","cited_by_count":1,"area":"inference"},{"id":"2603.12038","title":"Slow-Fast Inference: Training-Free Inference Acceleration via Within-Sentence Support Stability","created":"2026-03-12","cited_by_count":1,"area":"inference"},{"id":"2604.03260","title":"Why Attend to Everything? Focus is the Key","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.08426","title":"KV Cache Offloading for Context-Intensive Tasks","created":"2026-04-09","cited_by_count":1,"area":"inference"},{"id":"2604.09406","title":"OASIS: Online Activation Subspace Learning for Memory-Efficient Training","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2605.06763","title":"Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache","created":"2026-05-07","cited_by_count":1,"area":"inference"},{"id":"2606.06453","title":"Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents","created":"2026-06-04","cited_by_count":1,"area":"agents"},{"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":"2607.27692","title":"Recall Before You Rank: Similarity-Guided Top-$K$ Reuse for Efficient Long-Context Attention","created":"2026-07-30","cited_by_count":1,"area":"inference"},{"id":"2608.30295","title":"CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration","created":"2026-08-31","cited_by_count":1,"area":"inference"},{"id":"2609.26300","title":"CompKV: Compensation-Aware KV Selection for Long-Context LLM Inference","created":"2026-09-22","cited_by_count":1,"area":"inference"},{"id":"2503.01564","title":"Attention Condensation via Sparsity Induced Regularized Training","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2509.11155","title":"AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMs","created":"2025-09-14","cited_by_count":0,"area":"inference"},{"id":"2604.07857","title":"Networking-Aware Energy Efficiency in Agentic AI Inference: A Survey","created":"2026-04-09","cited_by_count":0,"area":"agents"},{"id":"2604.16864","title":"HieraSparse: Hierarchical Semi-Structured Sparse KV Attention","created":"2026-04-18","cited_by_count":0,"area":"inference"},{"id":"2604.24820","title":"Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.21649","title":"EntmaxKV: Support-Aware Decoding for Entmax Attention","created":"2026-05-20","cited_by_count":0,"area":"inference"},{"id":"2608.00528","title":"S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.06341","title":"Linear Algebra Foundations of Efficient Attention: A Phase Reversal in Rank Collapse Under SVD Compression","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.17652","title":"Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Caches","created":"2026-09-15","cited_by_count":0,"area":"inference"},{"id":"2609.24417","title":"ARM: Attention with Routed-Memory for Learnable Sparse Control","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.32579","title":"DimPO: Dimensionality Reduction for Attention using Preference Optimization","created":"2026-09-26","cited_by_count":0,"area":"alignment"},{"id":"2609.33746","title":"PQ-HSA: Reusing Product-Quantized Scores for Hybrid Sparse-Approximate Attention","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.01230","title":"HHR: Hierarchical Hash Retrieval for Efficient LLM Generation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04635","title":"LatentIndex: Cross-Layer Sharing with Layer-Specific Selection for Sparse Attention","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.11245","title":"Read What Matters: Query-Adaptive Quantization for KV Caches","created":"2026-10-08","cited_by_count":0,"area":"inference"},{"id":"2610.15384","title":"E8 Lattice Key Quantization for Low-Bit KV-Cache Compression","created":"2026-10-11","cited_by_count":0,"area":"inference"},{"id":"2610.19026","title":"Joint Subspace Sparse Attention for Efficient Long-Context Decoding","created":"2026-10-13","cited_by_count":0,"area":"inference"}],"next_cursor":null}