{"total":65,"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":"2501.19324","title":"Reward-Guided Speculative Decoding for Efficient LLM Reasoning","created":"2025-01-31","cited_by_count":106,"area":"lr"},{"id":"2502.15589","title":"LightThinker: Thinking Step-by-Step Compression","created":"2025-02-21","cited_by_count":104,"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":"2406.09136","title":"Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs","created":"2024-06-13","cited_by_count":96,"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":"2412.03213","title":"ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression","created":"2024-12-04","cited_by_count":65,"area":"lr"},{"id":"2508.02558","title":"Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction","created":"2025-08-04","cited_by_count":65,"area":"lr"},{"id":"2502.12054","title":"PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning","created":"2025-02-17","cited_by_count":59,"area":"lr"},{"id":"2509.25911","title":"Mem-{\\alpha}: Learning Memory Construction via Reinforcement Learning","created":"2025-09-30","cited_by_count":55,"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":"2606.13392","title":"MiniMax Sparse Attention","created":"2026-06-11","cited_by_count":44,"area":"lr"},{"id":"2410.18517","title":"KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing","created":"2024-10-24","cited_by_count":41,"area":"lr"},{"id":"2503.14337","title":"PENCIL: Long Thoughts with Short Memory","created":"2025-03-18","cited_by_count":33,"area":"lr"},{"id":"2506.08889","title":"SeerAttention-R: Sparse Attention Adaptation for Long Reasoning","created":"2025-06-10","cited_by_count":30,"area":"lr"},{"id":"2502.14837","title":"Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs","created":"2025-02-20","cited_by_count":27,"area":"lr"},{"id":"2506.05345","title":"Inference-Time Hyper-Scaling with KV Cache Compression","created":"2025-06-05","cited_by_count":27,"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":"2505.13866","title":"Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning","created":"2025-05-20","cited_by_count":17,"area":"lr"},{"id":"2507.08806","title":"Think Clearly: Improving Reasoning via Redundant Token Pruning","created":"2025-06-17","cited_by_count":17,"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":"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":"2506.05333","title":"Kinetics: Rethinking Test-Time Scaling Laws","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2510.08525","title":"Which Heads Matter for Reasoning? RL-Guided KV Cache Compression","created":"2025-10-09","cited_by_count":10,"area":"lr"},{"id":"2512.01278","title":"Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding","created":"2025-12-01","cited_by_count":10,"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":"2602.08382","title":"Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning","created":"2026-02-09","cited_by_count":8,"area":"lr"},{"id":"2602.18493","title":"Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning","created":"2026-02-13","cited_by_count":8,"area":"lr"},{"id":"2606.03928","title":"Value-Aware Stochastic KV Cache Eviction for Reasoning Models","created":"2026-06-02","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":"2512.07993","title":"SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models","created":"2025-12-08","cited_by_count":5,"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":"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":"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":"2602.15843","title":"The Perplexity Paradox: Why Code Compresses Better Than Math in LLM Prompts","created":"2026-01-21","cited_by_count":2,"area":"lr"},{"id":"2604.18002","title":"Neural Garbage Collection: Learning to Forget while Learning to Reason","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2605.06850","title":"How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment","created":"2026-05-07","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":"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":"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":"2608.26070","title":"Prefix Sliding for efficient test-time scaling","created":"2026-08-26","cited_by_count":2,"area":"lr"},{"id":"2605.03644","title":"AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse","created":"2026-05-05","cited_by_count":1,"area":"lr"},{"id":"2605.06997","title":"Echo: KV-Cache-Free Associative Recall with Spectral Koopman Operators","created":"2026-05-07","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":"2510.05176","title":"PatternKV: Flattening KV Representation Expands Quantization Headroom","created":"2025-10-05","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":"2605.16439","title":"KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2606.05201","title":"State commitment learning: training language models to distinguish computation from memory","created":"2026-05-22","cited_by_count":0,"area":"lr"},{"id":"2608.24063","title":"VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference","created":"2026-08-25","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":"2609.04971","title":"BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference","created":"2026-09-04","cited_by_count":0,"area":"lr"},{"id":"2609.16055","title":"State of Thought Enables Endogenous Reasoning","created":"2026-09-13","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}