{"total":57,"rows":[{"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":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60,"area":"inference"},{"id":"2506.15745","title":"InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding","created":"2025-06-18","cited_by_count":58,"area":"inference"},{"id":"2508.15717","title":"StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding","created":"2025-08-21","cited_by_count":58,"area":"mllm"},{"id":"2506.08889","title":"SeerAttention-R: Sparse Attention Adaptation for Long Reasoning","created":"2025-06-10","cited_by_count":30,"area":"lr"},{"id":"2412.14468","title":"HashAttention: Semantic Sparsity for Faster Inference","created":"2024-12-19","cited_by_count":24,"area":null},{"id":"2502.13575","title":"ETS: Efficient Tree Search for Inference-Time Scaling","created":"2025-02-19","cited_by_count":16,"area":"lr"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2505.13109","title":"FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference","created":"2025-05-19","cited_by_count":14,"area":"inference"},{"id":"2506.13059","title":"Multipole Attention for Efficient Long Context Reasoning","created":"2025-06-16","cited_by_count":14,"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":"2504.00970","title":"SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching","created":"2025-04-01","cited_by_count":10,"area":"inference"},{"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":"2602.03152","title":"FASA: Frequency-aware Sparse Attention","created":"2026-02-03","cited_by_count":8,"area":"inference"},{"id":"2503.24358","title":"SQuat: Subspace-orthogonal KV Cache Quantization","created":"2025-03-31","cited_by_count":7,"area":"inference"},{"id":"2509.17396","title":"EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments","created":"2025-09-22","cited_by_count":7,"area":"inference"},{"id":"2506.00400","title":"Scaling Textual Gradients via Sampling-Based Momentum","created":"2025-05-31","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":"2508.15212","title":"SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning","created":"2025-08-21","cited_by_count":6,"area":"inference"},{"id":"2510.05688","title":"vAttention: Verified Sparse Attention","created":"2025-10-07","cited_by_count":6,"area":null},{"id":"2508.09001","title":"Retrospective Sparse Attention for Efficient Long-Context Generation","created":"2025-08-12","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":"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":"2512.17452","title":"KV Admission: Learning What to Write for Efficient Long-Context LLM Inference","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2604.05164","title":"Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning in Agents","created":"2026-04-06","cited_by_count":4,"area":"lr"},{"id":"2606.07577","title":"OmniMem: Perturbation-aware Memory Compression for Streaming Audio-Visual LLMs","created":"2026-05-26","cited_by_count":4,"area":null},{"id":"2505.05772","title":"Sparse Attention Remapping with Clustering for Efficient LLM Decoding on PIM","created":"2025-05-09","cited_by_count":3,"area":"inference"},{"id":"2602.06283","title":"SOCKET: SOft Collision Kernel EsTimator for Sparse Attention","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2510.00078","title":"Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey","created":"2025-09-30","cited_by_count":2,"area":"lr"},{"id":"2511.17923","title":"Towards Efficient LLM-aware Heterogeneous Graph Learning","created":"2025-11-22","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":"2607.00712","title":"Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption","created":"2026-07-01","cited_by_count":2,"area":"inference"},{"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":"2509.09199","title":"CCF: A Context Compression Framework for Efficient Long-Sequence Language Modeling","created":"2025-09-11","cited_by_count":1,"area":"inference"},{"id":"2509.10406","title":"Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2601.17833","title":"An Effective and Cost-Efficient Agentic Framework for Ethereum Smart Contract Auditing","created":"2026-01-25","cited_by_count":1,"area":"agents"},{"id":"2603.18446","title":"UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2605.06763","title":"Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache","created":"2026-05-07","cited_by_count":1,"area":"inference"},{"id":"2606.28379","title":"LEDGER: Scaling Agentic Document Editing with Dependency-aware Graph Retrieval","created":"2026-06-19","cited_by_count":1,"area":"agents"},{"id":"2607.12789","title":"AVQ-Attention: Adaptive Vector-Quantized Attention","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2607.27692","title":"Recall Before You Rank: Similarity-Guided Top-$K$ Reuse for Efficient Long-Context Attention","created":"2026-07-30","cited_by_count":1,"area":"inference"},{"id":"2609.16161","title":"LLM Inference in a Flash!","created":"2026-09-14","cited_by_count":1,"area":"inference"},{"id":"2603.24023","title":"Schema on the Inside: A Two-Phase Fine-Tuning Method for High-Efficiency Text-to-SQL at Scale","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2603.27960","title":"Towards Efficient Large Vision-Language Models: A Comprehensive Survey on Inference Strategies","created":"2026-03-30","cited_by_count":0,"area":"lr"},{"id":"2604.05012","title":"Comparative Characterization of KV Cache Management Strategies for LLM Inference","created":"2026-04-06","cited_by_count":0,"area":"inference"},{"id":"2604.17147","title":"ScenarioControl: Vision-Language Controllable Vectorized Latent Scenario Generation","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.18226","title":"Context Memorization for Efficient Long Context Generation","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.24168","title":"Inference Time Context Sparsity: Illusion or Opportunity?","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2608.05303","title":"EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding","created":"2026-08-05","cited_by_count":0,"area":"moe"},{"id":"2608.20853","title":"MGAL: A Multilingual Granularity-Aware Long-Context Benchmark","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.33746","title":"PQ-HSA: Reusing Product-Quantized Scores for Hybrid Sparse-Approximate Attention","created":"2026-09-27","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":"2610.00907","title":"STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.00928","title":"Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01230","title":"HHR: Hierarchical Hash Retrieval for Efficient LLM Generation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.19026","title":"Joint Subspace Sparse Attention for Efficient Long-Context Decoding","created":"2026-10-13","cited_by_count":0,"area":"inference"}],"next_cursor":null}