{"total":104,"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":"2503.16428","title":"XAttention: Block Sparse Attention with Antidiagonal Scoring","created":"2025-03-20","cited_by_count":137,"area":null},{"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":"2502.02770","title":"Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning","created":"2025-02-04","cited_by_count":49,"area":null},{"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":"2511.01805","title":"Accumulating Context Changes the Beliefs of Language Models","created":"2025-11-03","cited_by_count":28,"area":null},{"id":"2603.05498","title":"The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks","created":"2026-03-05","cited_by_count":27,"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":"2501.18107","title":"Scaling Inference-Efficient Language Models","created":"2025-01-30","cited_by_count":16,"area":null},{"id":"2502.02789","title":"Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation","created":"2025-02-05","cited_by_count":14,"area":null},{"id":"2512.12087","title":"BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding","created":"2025-12-12","cited_by_count":13,"area":null},{"id":"2503.08640","title":"Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention","created":"2025-03-11","cited_by_count":12,"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":"2506.17121","title":"Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?","created":"2025-06-20","cited_by_count":10,"area":null},{"id":"2509.24745","title":"ProxyAttn: Guided Sparse Attention via Representative Heads","created":"2025-09-29","cited_by_count":9,"area":null},{"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":"2510.22548","title":"LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?","created":"2025-10-26","cited_by_count":8,"area":null},{"id":"2508.02215","title":"LeanK: Learnable K Cache Channel Pruning for Efficient Decoding","created":"2025-08-04","cited_by_count":7,"area":null},{"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":"2510.24606","title":"Long-Context Modeling with Dynamic Hierarchical Sparse Attention for Memory-Constrained LLM Inference","created":"2025-10-28","cited_by_count":7,"area":null},{"id":"2512.23966","title":"Efficient Context Scaling with LongCat ZigZag Attention","created":"2025-12-30","cited_by_count":6,"area":null},{"id":"2502.09647","title":"Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification","created":"2025-02-11","cited_by_count":5,"area":null},{"id":"2502.11276","title":"The Rotary Position Embedding May Cause Dimension Inefficiency in Attention Heads for Long-Distance Retrieval","created":"2025-02-16","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":"2507.21526","title":"Accelerating Prefilling via Decoding-time Contribution Sparsity","created":"2025-07-29","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":"2510.05862","title":"Revisiting Long-context Modeling from Context Denoising Perspective","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2601.17367","title":"Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers","created":"2026-01-24","cited_by_count":5,"area":null},{"id":"2602.00398","title":"MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2606.04511","title":"SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference","created":"2026-06-03","cited_by_count":5,"area":null},{"id":"2505.10063","title":"CAFE: Retrieval Head-based Coarse-to-Fine Information Seeking to Enhance Multi-Document QA Capability","created":"2025-05-15","cited_by_count":4,"area":null},{"id":"2508.16703","title":"ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2510.18245","title":"Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2510.18413","title":"Adamas: Hadamard Sparse Attention for Efficient Long-Context Inference","created":"2025-10-21","cited_by_count":4,"area":null},{"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":"2512.17452","title":"KV Admission: Learning What to Write for Efficient Long-Context LLM Inference","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2512.21859","title":"TimeBill: Time-Budgeted Inference for Large Language Models","created":"2025-12-26","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":"2605.18753","title":"DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention","created":"2026-05-18","cited_by_count":4,"area":null},{"id":"2505.24179","title":"SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2601.00919","title":"Attention Needs to Focus: A Unified Perspective on Attention Allocation","created":"2026-01-01","cited_by_count":3,"area":null},{"id":"2601.03043","title":"Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage","created":"2026-01-06","cited_by_count":3,"area":null},{"id":"2602.03681","title":"Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models","created":"2026-02-03","cited_by_count":3,"area":null},{"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":"2607.24593","title":"PIVOT: Efficient Query-Group Indexing for Token-Level Sparse Attention","created":"2026-07-27","cited_by_count":3,"area":null},{"id":"2609.02986","title":"Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design","created":"2026-09-02","cited_by_count":3,"area":null},{"id":"2412.02819","title":"CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels","created":"2024-12-03","cited_by_count":2,"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":"2512.07525","title":"Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2602.08686","title":"CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2602.22175","title":"DySCO: Dynamic Attention-Scaling Decoding for Long-Context Language Models","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2605.17887","title":"Attention Sinks and Outliers in Attention Residuals","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2606.03979","title":"Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.30562","title":"Morphing into Hybrid Attention Models","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2608.01662","title":"LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2609.13141","title":"SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking","created":"2026-09-11","cited_by_count":2,"area":null},{"id":"2410.14268","title":"MoDification: Mixture of Depths Made Easy","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2411.01030","title":"Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2506.15704","title":"Learn from the Past: Fast Sparse Indexing for Large Language Model Decoding","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2506.15954","title":"One Period to Rule Them All: Identifying Critical Learning Periods in Deep Networks","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2510.03678","title":"Towards Sampling Data Structures for Tensor Products in Turnstile Streams","created":"2025-10-04","cited_by_count":1,"area":null},{"id":"2510.23052","title":"Knocking-Heads Attention","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2601.17702","title":"S$^3$-Attention:Attention-Aligned Endogenous Retrieval for Memory-Bounded Long-Context Inference","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2604.06393","title":"ART: Attention Replacement Technique to Improve Factuality in LLMs","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.06105","title":"Shallow Prefill, Deep Decoding: Efficient Long-Context Inference via Layer-Asymmetric KV Visibility","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.06611","title":"The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.11744","title":"Training-Inference Consistent Segmented Execution for Long-Context LLMs","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.15508","title":"STS: Efficient Sparse Attention with Speculative Token Sparsity","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2606.07703","title":"How Much Dense Attention is Necessary? Oracle-Guided Sparse Prefill for Full/GQA Layers in Hybrid Long-Context Models","created":"2026-06-05","cited_by_count":1,"area":null},{"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":"2607.03612","title":"SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers","created":"2026-07-03","cited_by_count":1,"area":null},{"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":"2607.25291","title":"CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2505.11040","title":"Efficient Attention via Pre-Scoring: Prioritizing Informative Keys in Transformers","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2507.03220","title":"Symbiosis: Multi-Adapter Inference and Fine-Tuning","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2508.00285","title":"Enhancing Trustworthy Clinical Diagnosis Decision-Making in Large Language Models via Etiology-Aware Attention Supervision","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2602.06317","title":"Attention-Mass Condensation for Sparse Decoding","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.08329","title":"Near-Oracle KV Selection via Pre-hoc Sparsity for Long-Context Inference","created":"2026-02-09","cited_by_count":0,"area":null},{"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":"2604.07394","title":"Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference","created":"2026-04-08","cited_by_count":0,"area":null},{"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":"2606.03712","title":"When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.21249","title":"Does RoPE Prevent or Degrade Retrieval Heads? A Mechanistic Analysis Across Model Families","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.29844","title":"MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers","created":"2026-06-29","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":"2607.22720","title":"CausalGate: Causal Importance Distillation for Transformer Module Pruning","created":"2026-07-21","cited_by_count":0,"area":null},{"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":"2608.19920","title":"Learning how to Forget: Fine-tuning for Long-Context Sparse Attention","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.20427","title":"BF1: A Causal Dyadic Sparse-Attention Retrofit for Efficient Long-Context Transformers","created":"2026-08-19","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":"2609.07282","title":"Separating Stream Stability from Long-Term Recall in Language Models","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.07306","title":"RouteRelay: Event-Triggered Cross-Layer Route Reuse for Efficient Dynamic Sparse Attention","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.09085","title":"It's Not RoPE that Creates Sinks: The Role of Self-Concentration and Value-Non-Mixing in Attention","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.17888","title":"Long-Context Demonstration Selection Using State Space Models","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.27590","title":"MWE-ECL: Recoverable Long-Range Context Does Not Always Override Local Lexical Priors","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.32704","title":"CoWindow Attention: Full Causal Coverage Is a Collective Property","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32712","title":"MassAlloc Attention: Let Attention Allocate Its Own Compute","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34650","title":"When Can Attention Heads Be Statically Defined?","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35629","title":"SANTA++: Sampling Attention through Representative Keys","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.39661","title":"The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":"100"}