{"total":29,"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":"2410.19258","title":"Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning","created":"2024-10-25","cited_by_count":97,"area":"lr"},{"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":"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":"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":"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":"2510.24051","title":"Pie: A Programmable Serving System for Emerging LLM Applications","created":"2025-10-28","cited_by_count":14,"area":"lr"},{"id":"2601.10079","title":"Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts","created":"2026-01-15","cited_by_count":9,"area":"lr"},{"id":"2604.05546","title":"Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects","created":"2026-04-07","cited_by_count":9,"area":"lr"},{"id":"2512.00504","title":"G-KV: Decoding-Time KV Cache Eviction with Global Attention","created":"2025-11-29","cited_by_count":7,"area":"lr"},{"id":"2603.11504","title":"LongFlow: Efficient KV Cache Compression for Reasoning Models","created":"2026-03-12","cited_by_count":6,"area":"lr"},{"id":"2503.04973","title":"Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning","created":"2025-03-06","cited_by_count":4,"area":"lr"},{"id":"2603.08743","title":"Zipage: Maintain High Request Concurrency for LLM Reasoning through Compressed PagedAttention","created":"2026-03-01","cited_by_count":4,"area":"lr"},{"id":"2605.22106","title":"ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoning","created":"2026-05-21","cited_by_count":4,"area":"lr"},{"id":"2607.02509","title":"ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning","created":"2026-07-02","cited_by_count":4,"area":"lr"},{"id":"2604.05887","title":"HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference","created":"2026-04-07","cited_by_count":3,"area":"lr"},{"id":"2508.15806","title":"REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV Cache Compression","created":"2025-08-14","cited_by_count":2,"area":"lr"},{"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":"2605.14037","title":"Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility","created":"2026-05-13","cited_by_count":2,"area":"lr"},{"id":"2607.01237","title":"KARA: Efficient Reasoning LLM Serving via Sliding-Window KV Cache Compression","created":"2026-05-01","cited_by_count":2,"area":"lr"},{"id":"2607.18859","title":"PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents","created":"2026-07-21","cited_by_count":2,"area":"lr"},{"id":"2601.18383","title":"Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models","created":"2026-01-26","cited_by_count":1,"area":"lr"},{"id":"2605.23200","title":"Adaptive Mass-Segmented KV Compression for Long-Context Reasoning","created":"2026-05-22","cited_by_count":1,"area":"lr"},{"id":"2606.14782","title":"Last But Not Least: Boundary Attention CalibratiON for Multimodal KV Cache Compression","created":"2026-06-10","cited_by_count":1,"area":"lr"},{"id":"2609.03430","title":"Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning","created":"2026-09-03","cited_by_count":1,"area":"lr"},{"id":"2609.03494","title":"GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.27276","title":"DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2610.05685","title":"Spend Bytes on Breadth: Precision-Count Trade-offs for Decode-Time KV Compression in Long Chain-of-Thought Reasoning","created":"2026-10-05","cited_by_count":0,"area":"lr"}],"next_cursor":null}