{"total":124,"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":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2407.11550","title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","created":"2024-07-16","cited_by_count":235,"area":"inference"},{"id":"2410.10781","title":"When Attention Sink Emerges in Language Models: An Empirical View","created":"2024-10-14","cited_by_count":208,"area":"inference"},{"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":"2405.00200","title":"In-Context Learning with Long-Context Models: An In-Depth Exploration","created":"2024-04-30","cited_by_count":128,"area":null},{"id":"2502.20766","title":"FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference","created":"2025-02-28","cited_by_count":123,"area":null},{"id":"2409.10516","title":"RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval","created":"2024-09-16","cited_by_count":116,"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":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99,"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":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2502.05173","title":"VideoRoPE: What Makes for Good Video Rotary Position Embedding?","created":"2025-02-07","cited_by_count":65,"area":null},{"id":"2410.18745","title":"Why Does the Effective Context Length of LLMs Fall Short?","created":"2024-10-24","cited_by_count":63,"area":null},{"id":"2407.09450","title":"Human-inspired Episodic Memory for Infinite Context LLMs","created":"2024-07-12","cited_by_count":62,"area":null},{"id":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60,"area":"inference"},{"id":"2502.00299","title":"ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference","created":"2025-02-01","cited_by_count":60,"area":"inference"},{"id":"2501.01986","title":"FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models","created":"2024-12-30","cited_by_count":54,"area":"mllm"},{"id":"2406.16747","title":"Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers","created":"2024-06-24","cited_by_count":52,"area":null},{"id":"2602.12684","title":"Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution","created":"2026-02-13","cited_by_count":45,"area":"vla"},{"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":"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":"2312.08901","title":"Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning","created":"2023-12-14","cited_by_count":26,"area":"lr"},{"id":"2411.17116","title":"Star Attention: Efficient LLM Inference over Long Sequences","created":"2024-11-26","cited_by_count":25,"area":"inference"},{"id":"2409.00509","title":"LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models","created":"2024-08-31","cited_by_count":23,"area":null},{"id":"2408.06318","title":"Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example","created":"2024-08-12","cited_by_count":22,"area":"agents"},{"id":"2510.05069","title":"SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs","created":"2025-10-06","cited_by_count":22,"area":"lr"},{"id":"2407.16695","title":"Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack","created":"2024-07-23","cited_by_count":19,"area":null},{"id":"2504.08719","title":"SWAN-GPT: An Efficient and Scalable Approach for Long-Context Language Modeling","created":"2025-04-11","cited_by_count":19,"area":null},{"id":"2512.03324","title":"Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs","created":"2025-12-03","cited_by_count":19,"area":"inference"},{"id":"2509.19633","title":"Mamba Modulation: On the Length Generalization of Mamba","created":"2025-09-23","cited_by_count":16,"area":"ssm"},{"id":"2506.03131","title":"Native-Resolution Image Synthesis","created":"2025-06-03","cited_by_count":15,"area":null},{"id":"2407.21443","title":"Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistency","created":"2024-07-31","cited_by_count":14,"area":"lr"},{"id":"2502.14317","title":"ParallelComp: Parallel Long-Context Compressor for Length Extrapolation","created":"2025-02-20","cited_by_count":14,"area":"inference"},{"id":"2409.06679","title":"E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning","created":"2024-09-10","cited_by_count":13,"area":"lr"},{"id":"2409.13265","title":"Towards LifeSpan Cognitive Systems","created":"2024-09-20","cited_by_count":13,"area":null},{"id":"2503.18150","title":"LongDiff: Training-Free Long Video Generation in One Go","created":"2025-03-23","cited_by_count":13,"area":"diffusion"},{"id":"2505.07775","title":"Must Read: A Comprehensive Survey of Computational Persuasion","created":"2025-05-12","cited_by_count":13,"area":null},{"id":"2503.21817","title":"Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping","created":"2025-03-26","cited_by_count":12,"area":"mllm"},{"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":"2605.09649","title":"Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction","created":"2026-05-10","cited_by_count":11,"area":"inference"},{"id":"2605.18601","title":"Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models","created":"2026-05-18","cited_by_count":10,"area":"wm"},{"id":"2503.03588","title":"PowerAttention: Exponentially Scaling of Receptive Fields for Effective Sparse Attention","created":"2025-03-05","cited_by_count":9,"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":"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":"2510.16670","title":"All You Need is One: Capsule Prompt Tuning with a Single Vector","created":"2025-10-19","cited_by_count":8,"area":null},{"id":"2512.19206","title":"MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning","created":"2025-12-22","cited_by_count":8,"area":"lr"},{"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":"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":"2505.00570","title":"FreqKV: Key-Value Compression in Frequency Domain for Context Window Extension","created":"2025-05-01","cited_by_count":7,"area":"inference"},{"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":"2410.06577","title":"Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2502.07183","title":"Space-Aware Instruction Tuning: Dataset and Benchmark for Guide Dog Robots Assisting the Visually Impaired","created":"2025-02-11","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":"2510.20941","title":"Do LLMs Truly Understand When a Precedent Is Overruled?","created":"2025-10-23","cited_by_count":6,"area":null},{"id":"2503.09819","title":"Attention Reveals More Than Tokens: Training-Free Long-Context Reasoning with Attention-guided Retrieval","created":"2025-03-12","cited_by_count":5,"area":"lr"},{"id":"2504.06949","title":"Adaptive Computation Pruning for the Forgetting Transformer","created":"2025-04-09","cited_by_count":5,"area":null},{"id":"2505.17083","title":"Scale-invariant Attention","created":"2025-05-20","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":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2501.01805","title":"End-to-End Long Document Summarization using Gradient Caching","created":"2025-01-03","cited_by_count":4,"area":null},{"id":"2501.08570","title":"Information Entropy Invariance: Enhancing Length Extrapolation in Attention Mechanisms","created":"2025-01-15","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":"2504.10854","title":"LVLM_CSP: Accelerating Large Vision Language Models via Clustering, Scattering, and Pruning for Reasoning Segmentation","created":"2025-04-15","cited_by_count":4,"area":"lr"},{"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":"2510.13602","title":"NOSA: Native and Offloadable Sparse Attention","created":"2025-10-15","cited_by_count":4,"area":"inference"},{"id":"2602.02108","title":"Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts","created":"2026-02-02","cited_by_count":4,"area":"inference"},{"id":"2605.10544","title":"Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancing","created":"2026-05-11","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":"2501.04987","title":"TreeKV: Smooth Key-Value Cache Compression with Tree Structures","created":"2025-01-09","cited_by_count":3,"area":"inference"},{"id":"2503.06868","title":"Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation","created":"2025-03-10","cited_by_count":3,"area":"synth"},{"id":"2505.16928","title":"Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning","created":"2025-05-22","cited_by_count":3,"area":"lr"},{"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":"2510.12251","title":"DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering","created":"2025-10-14","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":"2511.06222","title":"SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization","created":"2025-11-09","cited_by_count":3,"area":"alignment"},{"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":"2603.06591","title":"What Makes Position Zero Special? A Mechanistic Study of Position Zero Attention Sinks in LLMs","created":"2026-02-04","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":"2603.18017","title":"Frayed RoPE and Long Inputs: A Geometric Perspective","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2603.25209","title":"Free-Lunch Long Video Generation via Layer-Adaptive O.O.D Correction","created":"2026-03-26","cited_by_count":3,"area":"diffusion"},{"id":"2605.13511","title":"Many-Shot CoT-ICL: Making In-Context Learning Truly Learn","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2408.00167","title":"Finch: Prompt-guided Key-Value Cache Compression","created":"2024-07-31","cited_by_count":2,"area":"rag"},{"id":"2503.07680","title":"Hierarchical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM","created":"2025-03-10","cited_by_count":2,"area":null},{"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":"2602.20981","title":"Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2605.01858","title":"Decouple and Cache: KV Cache Construction for Streaming Video Understanding","created":"2026-05-03","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":"2606.29563","title":"Coverage-Driven KV Cache Eviction for Efficient and Improved Inference of LLM","created":"2026-06-28","cited_by_count":2,"area":"inference"},{"id":"2408.09434","title":"HySem: A context length optimized LLM pipeline for unstructured tabular extraction","created":"2024-08-18","cited_by_count":1,"area":null},{"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":"2505.03745","title":"AccLLM: Accelerating Long-Context LLM Inference Via Algorithm-Hardware Co-Design","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2506.01986","title":"SpecMemo: Speculative Decoding is in Your Pocket","created":"2025-05-16","cited_by_count":1,"area":"inference"},{"id":"2509.12635","title":"Positional Encoding via Token-Aware Phase Attention","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2511.00576","title":"FlashEVA: Accelerating LLM inference via Efficient Attention","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2511.02647","title":"Federated Attention: A Distributed Paradigm for Collaborative LLM Inference over Edge Networks","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2604.14339","title":"Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation","created":"2026-04-15","cited_by_count":1,"area":"rag"},{"id":"2605.05066","title":"The Impossibility Triangle of Long-Context Modeling","created":"2026-05-06","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}],"next_cursor":"100"}