{"total":58,"rows":[{"id":"2410.10819","title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads","created":"2024-10-14","cited_by_count":288,"area":"inference"},{"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":"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":"2506.15745","title":"InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding","created":"2025-06-18","cited_by_count":58,"area":"inference"},{"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":"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":"2409.04992","title":"InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference","created":"2024-09-08","cited_by_count":19,"area":"inference"},{"id":"2507.08143","title":"Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores","created":"2025-07-10","cited_by_count":17,"area":"inference"},{"id":"2505.13109","title":"FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference","created":"2025-05-19","cited_by_count":14,"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":"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":"2410.01485","title":"A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts","created":"2024-10-02","cited_by_count":9,"area":"inference"},{"id":"2502.12574","title":"HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading","created":"2025-02-18","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":"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":"2506.11418","title":"CentroidKV: Efficient Long-Context LLM Inference via KV Cache Clustering","created":"2025-06-13","cited_by_count":8,"area":"inference"},{"id":"2507.03865","title":"OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference","created":"2025-07-05","cited_by_count":8,"area":"inference"},{"id":"2504.04704","title":"LagKV: Lag-Relative Information of the KV Cache Tells Which Tokens Are Important","created":"2025-04-07","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":"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":"2508.15212","title":"SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning","created":"2025-08-21","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":"2502.15955","title":"Compression Barriers for Autoregressive Transformers","created":"2025-02-21","cited_by_count":5,"area":"inference"},{"id":"2503.22196","title":"EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices","created":"2025-03-28","cited_by_count":5,"area":"inference"},{"id":"2602.04541","title":"LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding","created":"2026-02-04","cited_by_count":5,"area":"inference"},{"id":"2602.05191","title":"Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs","created":"2026-02-05","cited_by_count":5,"area":"inference"},{"id":"2605.08234","title":"When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression","created":"2026-05-07","cited_by_count":5,"area":"inference"},{"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":"2605.16928","title":"Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps","created":"2026-05-16","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":"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":"2608.01247","title":"RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction","created":"2026-08-02","cited_by_count":3,"area":"inference"},{"id":"2606.06302","title":"Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving","created":"2026-06-04","cited_by_count":2,"area":"inference"},{"id":"2606.24467","title":"CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference","created":"2026-06-23","cited_by_count":2,"area":"inference"},{"id":"2606.28831","title":"HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression","created":"2026-06-27","cited_by_count":2,"area":"inference"},{"id":"2502.17501","title":"CoKV: Optimizing KV Cache Allocation via Cooperative Game","created":"2025-02-21","cited_by_count":1,"area":"inference"},{"id":"2512.03608","title":"KVNAND: Efficient On-Device Large Language Model Inference Using DRAM-Free In-Flash Computing","created":"2025-12-03","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":"2606.09508","title":"From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs","created":"2026-06-08","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":"2608.06849","title":"Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry","created":"2026-08-07","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":"2609.39329","title":"PatchKV: Weight-Space Compensation of KV Cache","created":"2026-09-30","cited_by_count":1,"area":"inference"},{"id":"2412.04788","title":"GUIDE: A Global Unified Inference Engine for Deploying Large Language Models in Heterogeneous Environments","created":"2024-12-06","cited_by_count":0,"area":"inference"},{"id":"2603.20616","title":"Beyond Token Eviction: Mixed-Dimension Budget Allocation for Efficient KV Cache Compression","created":"2026-03-21","cited_by_count":0,"area":"inference"},{"id":"2603.21576","title":"PRISM: Breaking the O(n) Memory Wall in Long-Context LLM Inference via O(1) Photonic Block Selection","created":"2026-03-23","cited_by_count":0,"area":"inference"},{"id":"2604.05942","title":"BOSCH: Black-Box Binary Optimization for Short-Context Attention-Head Selection in LLMs","created":"2026-04-07","cited_by_count":0,"area":"inference"},{"id":"2606.21848","title":"Keyless Attention: Value-Space Routing and Value-Only Caching for Efficient Transformers","created":"2026-06-20","cited_by_count":0,"area":"inference"},{"id":"2606.31145","title":"SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference","created":"2026-06-30","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":"2609.03235","title":"SGD-KV: Summarization Guided KV Cache Compression","created":"2026-09-03","cited_by_count":0,"area":"inference"},{"id":"2609.16617","title":"Divergence Timing and Cumulative Disagreement under KV-Cache Eviction","created":"2026-09-15","cited_by_count":0,"area":"inference"},{"id":"2609.34555","title":"PulseInfer: I/O-Centric Sparse KV Cache Offloading for Efficient Long-Context LLM Decoding","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2609.36322","title":"Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2610.02713","title":"WakeKV: Reactive, Reversible KV Residency for Heads That Change Their Minds","created":"2026-10-02","cited_by_count":0,"area":"inference"}],"next_cursor":null}