{"total":120,"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":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"id":"2403.09636","title":"Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference","created":"2024-03-14","cited_by_count":116,"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":"2505.23416","title":"KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction","created":"2025-05-29","cited_by_count":95,"area":"inference"},{"id":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86,"area":"inference"},{"id":"2402.09398","title":"Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference","created":"2024-02-14","cited_by_count":75,"area":"inference"},{"id":"2510.00636","title":"Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution","created":"2025-10-01","cited_by_count":74,"area":"inference"},{"id":"2403.04797","title":"Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding","created":"2024-03-05","cited_by_count":72,"area":null},{"id":"2502.16002","title":"KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse","created":"2025-02-21","cited_by_count":66,"area":"inference"},{"id":"2503.12491","title":"CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences","created":"2025-03-16","cited_by_count":58,"area":"inference"},{"id":"2411.09688","title":"Squeezed Attention: Accelerating Long Context Length LLM Inference","created":"2024-11-14","cited_by_count":57,"area":null},{"id":"2504.15364","title":"KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments","created":"2025-04-21","cited_by_count":51,"area":"inference"},{"id":"2502.14866","title":"LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention","created":"2025-02-20","cited_by_count":41,"area":"inference"},{"id":"2405.15731","title":"Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks","created":"2024-05-24","cited_by_count":26,"area":null},{"id":"2404.09173","title":"TransformerFAM: Feedback attention is working memory","created":"2024-04-14","cited_by_count":22,"area":null},{"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":"2510.07293","title":"AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs","created":"2025-10-08","cited_by_count":22,"area":"inference"},{"id":"2604.04921","title":"TriAttention: Efficient Long Reasoning with Trigonometric KV Compression","created":"2026-04-06","cited_by_count":21,"area":"lr"},{"id":"2601.20499","title":"Efficient Autoregressive Video Diffusion with Dummy Head","created":"2026-01-28","cited_by_count":20,"area":"diffusion"},{"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":"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":"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":"2506.13059","title":"Multipole Attention for Efficient Long Context Reasoning","created":"2025-06-16","cited_by_count":14,"area":"lr"},{"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":"2602.10238","title":"Learning to Evict from Key-Value Cache","created":"2026-02-10","cited_by_count":14,"area":"inference"},{"id":"2409.13265","title":"Towards LifeSpan Cognitive Systems","created":"2024-09-20","cited_by_count":13,"area":null},{"id":"2410.12876","title":"In-context KV-Cache Eviction for LLMs via Attention-Gate","created":"2024-10-15","cited_by_count":13,"area":"inference"},{"id":"2504.14051","title":"CAOTE: KV Cache Selection for LLMs via Attention Output Error-Based Token Eviction","created":"2025-04-18","cited_by_count":13,"area":"inference"},{"id":"2511.01815","title":"KV Cache Transform Coding for Compact Storage in LLM Inference","created":"2025-11-03","cited_by_count":13,"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":"2410.20210","title":"Looking Beyond The Top-1: Transformers Determine Top Tokens In Order","created":"2024-10-26","cited_by_count":12,"area":null},{"id":"2603.28458","title":"HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention","created":"2026-03-30","cited_by_count":12,"area":null},{"id":"2504.00970","title":"SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching","created":"2025-04-01","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":"2603.10899","title":"LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation","created":"2026-03-11","cited_by_count":10,"area":"inference"},{"id":"2604.13226","title":"KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs","created":"2026-04-14","cited_by_count":10,"area":null},{"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":"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":"2605.08840","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":"2606.03928","title":"Value-Aware Stochastic KV Cache Eviction for Reasoning Models","created":"2026-06-02","cited_by_count":8,"area":"lr"},{"id":"2404.15949","title":"CORM: Cache Optimization with Recent Message for Large Language Model Inference","created":"2024-04-24","cited_by_count":7,"area":"inference"},{"id":"2406.06567","title":"DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion","created":"2024-06-03","cited_by_count":7,"area":null},{"id":"2501.02393","title":"Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers","created":"2025-01-04","cited_by_count":7,"area":null},{"id":"2506.05410","title":"Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs","created":"2025-06-04","cited_by_count":7,"area":"inference"},{"id":"2510.20797","title":"No Mean Feat: Simple, Strong Baselines for Context Compression","created":"2025-10-23","cited_by_count":7,"area":"inference"},{"id":"2602.07223","title":"Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention","created":"2026-02-06","cited_by_count":7,"area":"inference"},{"id":"2605.05971","title":"Training Transformers for KV Cache Compressibility","created":"2026-05-07","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":"2508.02751","title":"SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference","created":"2025-08-03","cited_by_count":6,"area":"inference"},{"id":"2510.09883","title":"DELTA: Dynamic Layer-Aware Token Attention for Efficient Long-Context Reasoning","created":"2025-10-10","cited_by_count":6,"area":"lr"},{"id":"2603.20586","title":"MKA: Memory-Keyed Attention for Efficient Long-Context Reasoning","created":"2026-03-21","cited_by_count":6,"area":"lr"},{"id":"2502.09647","title":"Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification","created":"2025-02-11","cited_by_count":5,"area":null},{"id":"2504.06949","title":"Adaptive Computation Pruning for the Forgetting Transformer","created":"2025-04-09","cited_by_count":5,"area":null},{"id":"2510.13797","title":"Breadcrumbs Reasoning: Memory-Efficient Reasoning with Compression Beacons","created":"2025-10-15","cited_by_count":5,"area":"lr"},{"id":"2603.06274","title":"Stem: Rethinking Causal Information Flow in Sparse Attention","created":"2026-03-06","cited_by_count":5,"area":"lr"},{"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":"2410.13166","title":"An Evolved Universal Transformer Memory","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2503.01330","title":"WeightedKV: Attention Scores Weighted Key-Value Cache Merging for Large Language Models","created":"2025-03-03","cited_by_count":4,"area":"inference"},{"id":"2508.09001","title":"Retrospective Sparse Attention for Efficient Long-Context Generation","created":"2025-08-12","cited_by_count":4,"area":"inference"},{"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":"2602.07397","title":"Scout Before You Attend: Sketch-and-Walk Sparse Attention for Efficient LLM Inference","created":"2026-02-07","cited_by_count":4,"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":"2501.04987","title":"TreeKV: Smooth Key-Value Cache Compression with Tree Structures","created":"2025-01-09","cited_by_count":3,"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":"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":"2509.05165","title":"KVCompose: Efficient Structured KV Cache Compression with Composite Tokens","created":"2025-09-05","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":"2602.08722","title":"QUOKA: Query-Oriented KV Selection For Efficient LLM Prefill","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2607.10582","title":"MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference","created":"2026-07-12","cited_by_count":3,"area":"agents"},{"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":"2408.00167","title":"Finch: Prompt-guided Key-Value Cache Compression","created":"2024-07-31","cited_by_count":2,"area":"rag"},{"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":"2510.07486","title":"AsyncSpade: Efficient Test-Time Scaling with Asynchronous Sparse Decoding","created":"2025-10-08","cited_by_count":2,"area":"lr"},{"id":"2510.25979","title":"AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache","created":"2025-10-29","cited_by_count":2,"area":null},{"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":"2602.18196","title":"RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference","created":"2026-02-20","cited_by_count":2,"area":"inference"},{"id":"2603.29494","title":"VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference","created":"2026-03-31","cited_by_count":2,"area":null},{"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":"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":"2607.21475","title":"Error Certificates for KV-Cache Eviction via Randomized Design","created":"2026-07-23","cited_by_count":2,"area":null},{"id":"2608.01672","title":"Learning What to Remember: Test-Time Training via Context Distillation","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.12435","title":"MARCH: Scaling Recurrent Memory with Content-Routed State Anchors","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2504.18929","title":"Revisiting Transformers through the Lens of Low Entropy and Dynamic Sparsity","created":"2025-04-26","cited_by_count":1,"area":null},{"id":"2508.15881","title":"TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference","created":"2025-08-21","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":"2604.11288","title":"Transactional Attention: Semantic Sponsorship for KV-Cache Retention","created":"2026-04-13","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":"2606.08302","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":"2606.15157","title":"Exploring a Layer-Wise Design Space for KV Cache Eviction","created":"2026-06-13","cited_by_count":1,"area":"inference"},{"id":"2608.25230","title":"Trust the Mass: Forced Weights in KV-Cache Eviction","created":"2026-08-25","cited_by_count":1,"area":"inference"},{"id":"2609.00092","title":"Safin-1: Safety from Within through Memory-Native State Evolution","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.35750","title":"KV-streams for Efficient Compaction in Agentic Reinforcement Learning","created":"2026-09-28","cited_by_count":1,"area":"agents"},{"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":"2410.12513","title":"FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2412.05693","title":"Batch-Max: Higher LLM Throughput using Larger Batch Sizes and KV Cache Compression","created":"2024-12-07","cited_by_count":0,"area":"inference"},{"id":"2502.15294","title":"Round Attention: A Novel Round-Level Attention Mechanism to Accelerate LLM Inference","created":"2025-02-21","cited_by_count":0,"area":"inference"},{"id":"2510.12051","title":"APCE: Adaptive Progressive Context Expansion for Long Context Processing","created":"2025-10-14","cited_by_count":0,"area":"inference"},{"id":"2511.00315","title":"Language Modeling With Factorization Memory","created":"2025-10-31","cited_by_count":0,"area":"ssm"}],"next_cursor":"100"}