{"total":197,"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":"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":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2410.02367","title":"SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration","created":"2024-10-03","cited_by_count":160,"area":"inference"},{"id":"2503.16428","title":"XAttention: Block Sparse Attention with Antidiagonal Scoring","created":"2025-03-20","cited_by_count":137,"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":"2502.18137","title":"SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference","created":"2025-02-25","cited_by_count":120,"area":null},{"id":"2503.00540","title":"Streaming Video Question-Answering with In-context Video KV-Cache Retrieval","created":"2025-03-01","cited_by_count":117,"area":"inference"},{"id":"2409.10516","title":"RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval","created":"2024-09-16","cited_by_count":116,"area":null},{"id":"2411.10958","title":"SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization","created":"2024-11-17","cited_by_count":114,"area":null},{"id":"2505.18875","title":"Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation","created":"2025-05-24","cited_by_count":106,"area":"diffusion"},{"id":"2505.11594","title":"SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training","created":"2025-05-16","cited_by_count":66,"area":null},{"id":"2509.24006","title":"SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention","created":"2025-09-28","cited_by_count":58,"area":"diffusion"},{"id":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52,"area":null},{"id":"2606.13392","title":"MiniMax Sparse Attention","created":"2026-06-11","cited_by_count":44,"area":"lr"},{"id":"2512.22087","title":"Context as a Tool: Context Management for Long-Horizon SWE-Agents","created":"2025-12-26","cited_by_count":43,"area":"agents"},{"id":"2412.12094","title":"SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator","created":"2024-12-16","cited_by_count":41,"area":null},{"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":"2502.06975","title":"Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents","created":"2025-02-10","cited_by_count":36,"area":"agents"},{"id":"2509.24663","title":"InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation","created":"2025-09-29","cited_by_count":32,"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":"2504.17768","title":"The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs","created":"2025-04-24","cited_by_count":29,"area":null},{"id":"2410.23041","title":"Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrieval","created":"2024-10-30","cited_by_count":26,"area":"rag"},{"id":"2411.17116","title":"Star Attention: Efficient LLM Inference over Long Sequences","created":"2024-11-26","cited_by_count":25,"area":"inference"},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2505.21136","title":"SageAttention2++: A More Efficient Implementation of SageAttention2","created":"2025-05-27","cited_by_count":22,"area":null},{"id":"2605.06716","title":"From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms","created":"2026-05-07","cited_by_count":21,"area":"agents"},{"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":"2503.08879","title":"LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference","created":"2025-03-11","cited_by_count":20,"area":"inference"},{"id":"2410.09342","title":"LLM$\\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models","created":"2024-10-12","cited_by_count":17,"area":null},{"id":"2506.16054","title":"PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models","created":"2025-06-19","cited_by_count":17,"area":null},{"id":"2502.14317","title":"ParallelComp: Parallel Long-Context Compressor for Length Extrapolation","created":"2025-02-20","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":"2410.08703","title":"On the token distance modeling ability of higher RoPE attention dimension","created":"2024-10-11","cited_by_count":13,"area":null},{"id":"2505.02922","title":"RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference","created":"2025-05-05","cited_by_count":13,"area":"inference"},{"id":"2508.06447","title":"SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning","created":"2025-08-08","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":"2501.02336","title":"AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference","created":"2025-01-04","cited_by_count":12,"area":null},{"id":"2411.06899","title":"LongSafety: Enhance Safety for Long-Context LLMs","created":"2024-11-11","cited_by_count":11,"area":"safety"},{"id":"2502.08246","title":"Inference-time sparse attention with asymmetric indexing","created":"2025-02-12","cited_by_count":11,"area":null},{"id":"2510.07318","title":"Artificial Hippocampus Networks for Efficient Long-Context Modeling","created":"2025-10-08","cited_by_count":11,"area":null},{"id":"2604.21221","title":"Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation","created":"2026-04-23","cited_by_count":11,"area":"diffusion"},{"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":"2505.19586","title":"TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization","created":"2025-05-26","cited_by_count":10,"area":"inference"},{"id":"2506.04108","title":"Rectified Sparse Attention","created":"2025-06-04","cited_by_count":10,"area":"inference"},{"id":"2512.01278","title":"Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding","created":"2025-12-01","cited_by_count":10,"area":"lr"},{"id":"2502.16684","title":"WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2506.09420","title":"A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy","created":"2025-06-11","cited_by_count":9,"area":"agents"},{"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":"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":"2502.02095","title":"LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information","created":"2025-02-04","cited_by_count":8,"area":null},{"id":"2503.10714","title":"ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs","created":"2025-03-13","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":"2509.11860","title":"MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialogues","created":"2025-09-15","cited_by_count":8,"area":null},{"id":"2602.08382","title":"Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning","created":"2026-02-09","cited_by_count":8,"area":"lr"},{"id":"2502.04077","title":"AttentionPredictor: Temporal Patterns Matter for KV Cache Compression","created":"2025-02-06","cited_by_count":7,"area":"inference"},{"id":"2502.08910","title":"InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU","created":"2025-02-13","cited_by_count":7,"area":"inference"},{"id":"2502.12962","title":"Infinite Retrieval: Attention Enhanced LLMs in Long-Context Processing","created":"2025-02-18","cited_by_count":7,"area":"lr"},{"id":"2505.00570","title":"FreqKV: Key-Value Compression in Frequency Domain for Context Window Extension","created":"2025-05-01","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":"2506.18226","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","created":"2025-06-23","cited_by_count":7,"area":"inference"},{"id":"2508.18224","title":"FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel","created":"2025-08-25","cited_by_count":7,"area":null},{"id":"2602.02159","title":"Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing","created":"2026-02-02","cited_by_count":7,"area":null},{"id":"2602.07223","title":"Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention","created":"2026-02-06","cited_by_count":7,"area":"inference"},{"id":"2604.04503","title":"Memory Intelligence Agent","created":"2026-04-06","cited_by_count":7,"area":"lr"},{"id":"2605.07363","title":"MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference","created":"2026-05-08","cited_by_count":7,"area":null},{"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":"2508.02124","title":"Trainable Dynamic Mask Sparse Attention","created":"2025-08-04","cited_by_count":6,"area":null},{"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":"2511.20102","title":"SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2504.06949","title":"Adaptive Computation Pruning for the Forgetting Transformer","created":"2025-04-09","cited_by_count":5,"area":null},{"id":"2505.19293","title":"100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability?","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2507.19608","title":"DeltaLLM: Delta-Key Sparse Attention for Edge LLMs","created":"2025-07-25","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":"2602.11761","title":"MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2603.14224","title":"Self-Indexing KVCache: Predicting Sparse Attention from Compressed Keys","created":"2026-03-15","cited_by_count":5,"area":"inference"},{"id":"2606.22874","title":"SpotAttention: Plug-In Block-Sparse Routing for Pretrained Long-Context Transformers","created":"2026-06-22","cited_by_count":5,"area":"inference"},{"id":"2505.21471","title":"Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration","created":"2025-05-27","cited_by_count":4,"area":"agents"},{"id":"2508.09001","title":"Retrospective Sparse Attention for Efficient Long-Context Generation","created":"2025-08-12","cited_by_count":4,"area":"inference"},{"id":"2510.06175","title":"VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization","created":"2025-10-07","cited_by_count":4,"area":"inference"},{"id":"2510.11292","title":"LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences","created":"2025-10-13","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":"2510.18413","title":"Adamas: Hadamard Sparse Attention for Efficient Long-Context Inference","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":"2511.07427","title":"DynaKV: Enabling Accurate and Efficient Long-Sequence LLM Decoding on Smartphones","created":"2025-10-20","cited_by_count":4,"area":"inference"},{"id":"2512.04025","title":"PSA: Pyramid Sparse Attention for Efficient Video Understanding and Generation","created":"2025-12-03","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":"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":"2605.18753","title":"DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention","created":"2026-05-18","cited_by_count":4,"area":null},{"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":"2609.00097","title":"Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding","created":"2026-08-31","cited_by_count":4,"area":null},{"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":"2504.10326","title":"AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference","created":"2025-04-14","cited_by_count":3,"area":"inference"},{"id":"2504.21239","title":"Memorization and Knowledge Injection in Gated LLMs","created":"2025-04-30","cited_by_count":3,"area":null},{"id":"2506.00773","title":"Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models","created":"2025-06-01","cited_by_count":3,"area":null},{"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":"2601.22379","title":"SPLA: Block Sparse Plus Linear Attention for Long Context Modeling","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2602.06283","title":"SOCKET: SOft Collision Kernel EsTimator for Sparse Attention","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2603.17484","title":"Learning When to Attend: Conditional Memory Access for Long-Context LLMs","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2604.14922","title":"LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning","created":"2026-04-16","cited_by_count":3,"area":"lr"}],"next_cursor":"100"}