{"total":97,"rows":[{"id":"2502.11089","title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","created":"2025-02-16","cited_by_count":407,"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":"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":"2508.15717","title":"StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding","created":"2025-08-21","cited_by_count":58,"area":"mllm"},{"id":"2505.24133","title":"R-KV: Redundancy-aware KV Cache Compression for Reasoning Models","created":"2025-05-30","cited_by_count":54,"area":"lr"},{"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":"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":"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":"2510.01290","title":"ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models","created":"2025-10-01","cited_by_count":21,"area":"lr"},{"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":"2505.13866","title":"Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning","created":"2025-05-20","cited_by_count":17,"area":"lr"},{"id":"2505.24357","title":"ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration","created":"2025-05-30","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":"2504.09261","title":"Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling","created":"2025-04-12","cited_by_count":15,"area":"inference"},{"id":"2502.01068","title":"FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration","created":"2025-02-03","cited_by_count":14,"area":"inference"},{"id":"2510.13334","title":"Taming the Fragility of KV Cache Eviction in LLM Inference","created":"2025-10-15","cited_by_count":14,"area":"inference"},{"id":"2510.20707","title":"Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models","created":"2025-10-23","cited_by_count":14,"area":"mllm"},{"id":"2502.07861","title":"Streaming Attention Approximation via Discrepancy Theory","created":"2025-02-11","cited_by_count":11,"area":null},{"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":"2510.07651","title":"OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference","created":"2025-10-09","cited_by_count":10,"area":"inference"},{"id":"2510.08525","title":"Which Heads Matter for Reasoning? RL-Guided KV Cache Compression","created":"2025-10-09","cited_by_count":10,"area":"lr"},{"id":"2502.12574","title":"HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading","created":"2025-02-18","cited_by_count":9,"area":"inference"},{"id":"2504.09936","title":"KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference","created":"2025-04-14","cited_by_count":9,"area":"inference"},{"id":"2509.15763","title":"UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression","created":"2025-09-19","cited_by_count":9,"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":"2512.00504","title":"G-KV: Decoding-Time KV Cache Eviction with Global Attention","created":"2025-11-29","cited_by_count":7,"area":"lr"},{"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":"2602.08585","title":"Predicting Future Utility: Global Combinatorial Optimization for Task-Agnostic KV Cache Eviction","created":"2026-02-09","cited_by_count":6,"area":"inference"},{"id":"2605.22269","title":"MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering","created":"2026-05-21","cited_by_count":6,"area":"lr"},{"id":"2504.06949","title":"Adaptive Computation Pruning for the Forgetting Transformer","created":"2025-04-09","cited_by_count":5,"area":null},{"id":"2505.07293","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","created":"2025-05-12","cited_by_count":5,"area":"lr"},{"id":"2506.08373","title":"Draft-based Approximate Inference for LLMs","created":"2025-06-10","cited_by_count":5,"area":"inference"},{"id":"2601.12904","title":"From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation","created":"2026-01-19","cited_by_count":5,"area":"rag"},{"id":"2604.13349","title":"When Less Latent Leads to Better Relay: Information-Preserving Compression for Latent Multi-Agent LLM Collaboration","created":"2026-04-14","cited_by_count":5,"area":"agents"},{"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":"2503.04973","title":"Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning","created":"2025-03-06","cited_by_count":4,"area":"lr"},{"id":"2504.10804","title":"Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability","created":"2025-04-15","cited_by_count":4,"area":null},{"id":"2505.23520","title":"AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity","created":"2025-05-29","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":"2605.05602","title":"Nearly Optimal Attention Coresets","created":"2026-05-07","cited_by_count":4,"area":null},{"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":"2605.31105","title":"GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs","created":"2026-05-29","cited_by_count":4,"area":"inference"},{"id":"2508.17892","title":"ILRe: Intermediate Layer Retrieval for Context Compression in Causal Language Models","created":"2025-08-25","cited_by_count":3,"area":"inference"},{"id":"2509.17486","title":"AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation","created":"2025-09-22","cited_by_count":3,"area":"rag"},{"id":"2512.13279","title":"AIR: Post-training Data Selection for Reasoning via Attention Head Influence","created":"2025-12-15","cited_by_count":3,"area":"lr"},{"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":"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":"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":"2505.18799","title":"ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models","created":"2025-05-24","cited_by_count":2,"area":"alignment"},{"id":"2508.15806","title":"REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV Cache Compression","created":"2025-08-14","cited_by_count":2,"area":"lr"},{"id":"2510.00078","title":"Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey","created":"2025-09-30","cited_by_count":2,"area":"lr"},{"id":"2510.03283","title":"MACE: A Hybrid LLM Serving System with Colocated SLO-aware Continuous Retraining Alignment","created":"2025-09-28","cited_by_count":2,"area":"inference"},{"id":"2512.04857","title":"Autoregressive Image Generation Needs Only a Few Lines of Cached Tokens","created":"2025-12-04","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":"2602.08686","title":"CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2602.11162","title":"Retrieval Heads are Dynamic","created":"2026-01-07","cited_by_count":2,"area":null},{"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":"2606.29563","title":"Coverage-Driven KV Cache Eviction for Efficient and Improved Inference of LLM","created":"2026-06-28","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":"2502.17501","title":"CoKV: Optimizing KV Cache Allocation via Cooperative Game","created":"2025-02-21","cited_by_count":1,"area":"inference"},{"id":"2504.08202","title":"Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2507.19906","title":"CaliDrop: KV Cache Compression with Calibration","created":"2025-07-26","cited_by_count":1,"area":"inference"},{"id":"2511.03728","title":"Efficient On-Device Agents via Adaptive Context Management","created":"2025-09-24","cited_by_count":1,"area":"inference"},{"id":"2602.03216","title":"Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.16839","title":"Training Large Reasoning Models Efficiently via Progressive Thought Encoding","created":"2026-02-18","cited_by_count":1,"area":"lr"},{"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":"2605.07234","title":"Reformulating KV Cache Eviction Problem for Long-Context LLM Inference","created":"2026-05-08","cited_by_count":1,"area":"inference"},{"id":"2605.23200","title":"Adaptive Mass-Segmented KV Compression for Long-Context Reasoning","created":"2026-05-22","cited_by_count":1,"area":"lr"},{"id":"2606.14782","title":"Last But Not Least: Boundary Attention CalibratiON for Multimodal KV Cache Compression","created":"2026-06-10","cited_by_count":1,"area":"lr"},{"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":"2607.13205","title":"Adaptive Filtering of the KV Cache: Diagnosing and Correcting Structural-Role Bias in LLM Inference","created":"2026-07-14","cited_by_count":1,"area":"inference"},{"id":"2608.09412","title":"KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models","created":"2026-08-10","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":"2609.16722","title":"VideoMM: Adaptive Macro-Micro Inference for Efficient Video MLLMs","created":"2026-09-15","cited_by_count":1,"area":"mllm"},{"id":"2502.15804","title":"FairKV: Balancing Per-Head KV Cache for Fast Multi-GPU Inference","created":"2025-02-19","cited_by_count":0,"area":"inference"},{"id":"2602.22453","title":"Identifying Crucial Attention Heads for Multilingual Language Models: Retrieval and Retrieval-Transition Heads","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.00907","title":"KVSlimmer: Theoretical Insights and Practical Optimizations for Asymmetric KV Merging","created":"2026-03-01","cited_by_count":0,"area":null},{"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":"2604.16864","title":"HieraSparse: Hierarchical Semi-Structured Sparse KV Attention","created":"2026-04-18","cited_by_count":0,"area":"inference"},{"id":"2605.20600","title":"Head-Aware Key-Value Compression for Efficient Autoregressive Image Generation","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2607.01002","title":"Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.22704","title":"WnW: Waxing-and-Waning KV Cache for Long-Form Speech LLMs","created":"2026-08-24","cited_by_count":0,"area":"inference"},{"id":"2608.27875","title":"HyQuant: Hybrid-Precision Quantization for LLM Attention","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.02029","title":"HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models","created":"2026-09-02","cited_by_count":0,"area":null},{"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":"2609.33334","title":"When to Evict, Not What to Keep: Draft-Guided Eviction for Training-Free KV-Cache Compression","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"id":"2609.34653","title":"OmniTide: Co-Designing Algorithms and Systems for Efficient On-Device Omni-LLM Streaming","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2609.35800","title":"HeadGuard: Selective Head Protection for Low-Bit VLM KV-Cache Quantization","created":"2026-09-18","cited_by_count":0,"area":"mllm"},{"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"},{"id":"2610.03007","title":"AvoKV-E: Payload-Aware KV Cache Eviction for Long Reasoning","created":"2026-10-02","cited_by_count":0,"area":"inference"},{"id":"2610.04313","title":"MOIRA: Mass-Oriented Indexing with Ragged Attention for Long-Context Decoding","created":"2026-10-03","cited_by_count":0,"area":"inference"},{"id":"2610.14754","title":"GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.18026","title":"ChampionKV: Head-Wise Adaptive Budget Allocation for KV Cache Compression","created":"2026-10-13","cited_by_count":0,"area":"inference"}],"next_cursor":null}