{"total":432,"rows":[{"id":"2512.13564","title":"Memory in the Age of AI Agents","created":"2025-12-15","cited_by_count":303,"area":"agents"},{"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":"2410.21465","title":"ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference","created":"2024-10-28","cited_by_count":134,"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":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128,"area":null},{"id":"2504.19874","title":"TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate","created":"2025-04-28","cited_by_count":125,"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":"2502.15589","title":"LightThinker: Thinking Step-by-Step Compression","created":"2025-02-21","cited_by_count":104,"area":"lr"},{"id":"2407.12820","title":"PQCache: Product Quantization-based KVCache for Long Context LLM Inference","created":"2024-07-01","cited_by_count":95,"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":"2505.21467","title":"FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion","created":"2025-05-27","cited_by_count":77,"area":"diffusion"},{"id":"2504.06263","title":"OmniSVG: A Unified Scalable Vector Graphics Generation Model","created":"2025-04-08","cited_by_count":74,"area":null},{"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":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68,"area":"lr"},{"id":"2410.01699","title":"Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding","created":"2024-10-02","cited_by_count":66,"area":"inference"},{"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":"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":"2412.00876","title":"Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification","created":"2024-12-01","cited_by_count":59,"area":"mllm"},{"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":"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":"2505.24133","title":"R-KV: Redundancy-aware KV Cache Compression for Reasoning Models","created":"2025-05-30","cited_by_count":54,"area":"lr"},{"id":"2410.03111","title":"LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy","created":"2024-10-04","cited_by_count":51,"area":"inference"},{"id":"2502.02770","title":"Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning","created":"2025-02-04","cited_by_count":49,"area":null},{"id":"2501.18795","title":"Rope to Nope and Back Again: A New Hybrid Attention Strategy","created":"2025-01-30","cited_by_count":47,"area":null},{"id":"2406.14909","title":"Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths","created":"2024-06-21","cited_by_count":44,"area":null},{"id":"2602.06052","title":"A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents","created":"2026-01-14","cited_by_count":44,"area":"agents"},{"id":"2410.23317","title":"VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration","created":"2024-10-29","cited_by_count":43,"area":"mllm"},{"id":"2412.14838","title":"DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs","created":"2024-12-19","cited_by_count":42,"area":"inference"},{"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":"2506.02634","title":"KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider","created":"2025-06-03","cited_by_count":41,"area":"inference"},{"id":"2506.19225","title":"Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification","created":"2025-06-24","cited_by_count":37,"area":"mllm"},{"id":"2406.13035","title":"D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models","created":"2024-06-18","cited_by_count":31,"area":"inference"},{"id":"2501.06425","title":"Tensor Product Attention Is All You Need","created":"2025-01-11","cited_by_count":31,"area":null},{"id":"2502.17599","title":"MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference","created":"2025-02-24","cited_by_count":31,"area":"mllm"},{"id":"2507.07990","title":"Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs","created":"2025-07-10","cited_by_count":31,"area":"inference"},{"id":"2504.02441","title":"Cognitive Memory in Large Language Models","created":"2025-04-03","cited_by_count":29,"area":null},{"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":"2505.19147","title":"Shifting AI Efficiency From Model-Centric to Data-Centric Compression","created":"2025-05-25","cited_by_count":29,"area":"mllm"},{"id":"2412.03131","title":"DiffKV: Differentiated Memory Management for Large Language Models with Parallel KV Compaction","created":"2024-12-04","cited_by_count":26,"area":"inference"},{"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":"2503.18292","title":"Jenga: Effective Memory Management for Serving LLM with Heterogeneity","created":"2025-03-24","cited_by_count":25,"area":"inference"},{"id":"2507.20198","title":"A Survey of Token Compression for Efficient Multimodal Large Language Models","created":"2025-07-27","cited_by_count":25,"area":"mllm"},{"id":"2509.23094","title":"d$^2$Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching","created":"2025-09-27","cited_by_count":25,"area":"inference"},{"id":"2502.12216","title":"Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs","created":"2025-02-17","cited_by_count":24,"area":"inference"},{"id":"2410.05589","title":"ParallelSpec: Parallel Drafter for Efficient Speculative Decoding","created":"2024-10-08","cited_by_count":22,"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":"2510.05069","title":"SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs","created":"2025-10-06","cited_by_count":22,"area":"lr"},{"id":"2510.01290","title":"ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models","created":"2025-10-01","cited_by_count":21,"area":"lr"},{"id":"2604.04921","title":"TriAttention: Efficient Long Reasoning with Trigonometric KV Compression","created":"2026-04-06","cited_by_count":21,"area":"lr"},{"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":"2503.00979","title":"Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLMs","created":"2025-03-02","cited_by_count":20,"area":"inference"},{"id":"2506.05344","title":"SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs","created":"2025-06-05","cited_by_count":20,"area":"mllm"},{"id":"2601.20499","title":"Efficient Autoregressive Video Diffusion with Dummy Head","created":"2026-01-28","cited_by_count":20,"area":"diffusion"},{"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":"2412.08890","title":"Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries","created":"2024-12-12","cited_by_count":17,"area":"inference"},{"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":"2502.01941","title":"Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression","created":"2025-02-04","cited_by_count":16,"area":"lr"},{"id":"2503.18893","title":"xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction","created":"2025-03-24","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":"2509.09754","title":"LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation","created":"2025-09-11","cited_by_count":16,"area":"inference"},{"id":"2510.10129","title":"CacheClip: Accelerating RAG with Effective KV Cache Reuse","created":"2025-10-11","cited_by_count":16,"area":"rag"},{"id":"2601.21896","title":"Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video Diffusion","created":"2026-01-29","cited_by_count":16,"area":"diffusion"},{"id":"2410.01805","title":"Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices","created":"2024-10-02","cited_by_count":15,"area":"inference"},{"id":"2410.03090","title":"UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective","created":"2024-10-04","cited_by_count":15,"area":"inference"},{"id":"2510.00231","title":"The Pitfalls of KV Cache Compression","created":"2025-09-30","cited_by_count":15,"area":"inference"},{"id":"2601.07891","title":"KVzap: Fast, Adaptive, and Faithful KV Cache Pruning","created":"2026-01-12","cited_by_count":15,"area":"inference"},{"id":"2608.07408","title":"Addressable Memory for Video World Models","created":"2026-08-07","cited_by_count":15,"area":"wm"},{"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":"2505.00315","title":"Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing","created":"2025-05-01","cited_by_count":14,"area":"moe"},{"id":"2509.17650","title":"Evict3R: Training-Free Token Eviction for Memory-Bounded Streaming Visual Geometry Transformers","created":"2025-09-22","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":"2602.10238","title":"Learning to Evict from Key-Value Cache","created":"2026-02-10","cited_by_count":14,"area":"inference"},{"id":"2407.15176","title":"ReAttention: Training-Free Infinite Context with Finite Attention Scope","created":"2024-07-21","cited_by_count":13,"area":null},{"id":"2410.00161","title":"KV-Compress: Paged KV-Cache Compression with Variable Compression Rates per Attention Head","created":"2024-09-30","cited_by_count":13,"area":"inference"},{"id":"2412.03409","title":"PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation","created":"2024-12-04","cited_by_count":13,"area":"lr"},{"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":"2601.04359","title":"PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache","created":"2026-01-07","cited_by_count":13,"area":"inference"},{"id":"2602.02579","title":"ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation","created":"2026-01-31","cited_by_count":13,"area":"rag"},{"id":"2410.13846","title":"LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation","created":"2024-10-17","cited_by_count":12,"area":"lr"},{"id":"2412.04652","title":"Cross-Self KV Cache Pruning for Efficient Vision-Language Inference","created":"2024-12-05","cited_by_count":12,"area":"inference"},{"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":"2501.12959","title":"Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference","created":"2025-01-22","cited_by_count":12,"area":"inference"},{"id":"2503.07518","title":"TokenButler: Token Importance is Predictable","created":"2025-03-10","cited_by_count":12,"area":"inference"},{"id":"2506.15724","title":"MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference","created":"2025-06-06","cited_by_count":12,"area":"mllm"},{"id":"2410.08391","title":"KV Prediction for Improved Time to First Token","created":"2024-10-10","cited_by_count":11,"area":"inference"},{"id":"2502.07861","title":"Streaming Attention Approximation via Discrepancy Theory","created":"2025-02-11","cited_by_count":11,"area":null},{"id":"2507.20030","title":"FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compression","created":"2025-07-26","cited_by_count":11,"area":"inference"},{"id":"2510.00536","title":"GUI-KV: Efficient GUI Agents via KV Cache with Spatio-Temporal Awareness","created":"2025-10-01","cited_by_count":11,"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":"2604.10098","title":"Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation","created":"2026-04-11","cited_by_count":11,"area":null},{"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":"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":"2502.00527","title":"PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration","created":"2025-02-01","cited_by_count":10,"area":"inference"},{"id":"2504.00557","title":"Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features","created":"2025-04-01","cited_by_count":10,"area":"mllm"},{"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":"2509.08315","title":"EvolKV: Evolutionary KV Cache Compression for LLM Inference","created":"2025-09-10","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"}],"next_cursor":"100"}