{"total":53,"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":"2502.15589","title":"LightThinker: Thinking Step-by-Step Compression","created":"2025-02-21","cited_by_count":104,"area":"lr"},{"id":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68,"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":"2510.05069","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":"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":"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":"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":"2510.02312","title":"KaVa: Latent Reasoning via Compressed KV-Cache Distillation","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"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":"2502.12962","title":"Infinite Retrieval: Attention Enhanced LLMs in Long-Context Processing","created":"2025-02-18","cited_by_count":7,"area":"lr"},{"id":"2505.12992","title":"Fractured Chain-of-Thought Reasoning","created":"2025-05-19","cited_by_count":7,"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":"2512.12008","title":"Hold Onto That Thought: Assessing KV Cache Compression On Reasoning","created":"2025-12-12","cited_by_count":6,"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":"2603.20586","title":"MKA: Memory-Keyed Attention for Efficient Long-Context Reasoning","created":"2026-03-21","cited_by_count":6,"area":"lr"},{"id":"2511.06029","title":"Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving","created":"2025-11-08","cited_by_count":5,"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":"2505.21670","title":"Rethinking the Outlier Distribution in Large Language Models: An In-depth Study","created":"2025-05-27","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":"2604.03679","title":"LightThinker++: From Reasoning Compression to Memory Management","created":"2026-04-04","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":"2503.23956","title":"AirCache: Activating Inter-modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference","created":"2025-03-31","cited_by_count":3,"area":"lr"},{"id":"2606.11164","title":"ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models","created":"2026-06-09","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":"2601.16986","title":"Crystal-KV: Efficient KV Cache Management for Chain-of-Thought LLMs via Answer-First Principle","created":"2026-01-05","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":"2606.26472","title":"Epiphany-Aware KV Cache Eviction Without the Attention Matrix","created":"2026-06-25","cited_by_count":2,"area":"lr"},{"id":"2606.26875","title":"Information-Aware KV Cache Compression for Long Reasoning","created":"2026-06-25","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":"2608.00902","title":"Practical Online KV Cache Compaction for LLM Agents: An Empirical Study","created":"2026-08-02","cited_by_count":2,"area":"lr"},{"id":"2608.04771","title":"Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning","created":"2026-08-05","cited_by_count":2,"area":"lr"},{"id":"2608.26070","title":"Prefix Sliding for efficient test-time scaling","created":"2026-08-26","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":"2602.11530","title":"PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based Large Language Models","created":"2026-02-12","cited_by_count":1,"area":"lr"},{"id":"2602.16839","title":"Training Large Reasoning Models Efficiently via Progressive Thought Encoding","created":"2026-02-18","cited_by_count":1,"area":"lr"},{"id":"2604.14889","title":"MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration","created":"2026-04-16","cited_by_count":1,"area":"lr"},{"id":"2605.09490","title":"Not All Thoughts Need HBM: Semantics-Aware Memory Hierarchy for LLM Reasoning","created":"2026-05-10","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":"2609.27373","title":"Attention Routing Stabilizes Early: Working-Set Inference for Recurrent Language Models","created":"2026-09-23","cited_by_count":1,"area":"lr"},{"id":"2602.00748","title":"HyperOffload: Graph-Driven Hierarchical Memory Management for Large Language Models on SuperNode Architectures","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"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":"2609.03494","title":"GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.23587","title":"On the Efficiency-Safety Dilemma in Large Reasoning Models","created":"2026-09-20","cited_by_count":0,"area":"lr"},{"id":"2610.00437","title":"JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces","created":"2026-09-30","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}