{"total":54,"rows":[{"id":"2506.08889","title":"SeerAttention-R: Sparse Attention Adaptation for Long Reasoning","created":"2025-06-10","cited_by_count":30,"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":"2604.09852","title":"MEMENTO: Teaching LLMs to Manage Their Own Context","created":"2026-04-10","cited_by_count":18,"area":"lr"},{"id":"2605.22718","title":"WorldKV: Efficient World Memory with World Retrieval and Compression","created":"2026-05-21","cited_by_count":15,"area":"diffusion"},{"id":"2602.22603","title":"SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoning","created":"2026-02-26","cited_by_count":11,"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":"2510.02312","title":"KaVa: Latent Reasoning via Compressed KV-Cache Distillation","created":"2025-10-02","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":"2510.09883","title":"DELTA: Dynamic Layer-Aware Token Attention for Efficient Long-Context Reasoning","created":"2025-10-10","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":"2601.19001","title":"FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2605.08234","title":"When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression","created":"2026-05-07","cited_by_count":5,"area":"inference"},{"id":"2510.10964","title":"Not All Bits Are Equal: Scale-Dependent Memory Optimization Strategies for Reasoning Models","created":"2025-10-13","cited_by_count":4,"area":"lr"},{"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":"2605.18753","title":"DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention","created":"2026-05-18","cited_by_count":4,"area":null},{"id":"2604.17695","title":"MoE-nD: Per-Layer Mixture-of-Experts Routing for Multi-Axis KV Cache Compression","created":"2026-04-20","cited_by_count":2,"area":"moe"},{"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":"2608.01631","title":"Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache Compression","created":"2026-08-03","cited_by_count":2,"area":"inference"},{"id":"2608.15797","title":"KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving","created":"2026-08-16","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":"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":"2604.11288","title":"Transactional Attention: Semantic Sponsorship for KV-Cache Retention","created":"2026-04-13","cited_by_count":1,"area":"inference"},{"id":"2604.25080","title":"CacheFlow: Efficient LLM Serving with 3D-Parallel KV Cache Restoration","created":"2026-04-28","cited_by_count":1,"area":"rag"},{"id":"2605.19260","title":"AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees","created":"2026-05-19","cited_by_count":1,"area":"mllm"},{"id":"2605.23200","title":"Adaptive Mass-Segmented KV Compression for Long-Context Reasoning","created":"2026-05-22","cited_by_count":1,"area":"lr"},{"id":"2607.06523","title":"DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression","created":"2026-07-07","cited_by_count":1,"area":"inference"},{"id":"2607.24555","title":"LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2609.03430","title":"Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning","created":"2026-09-03","cited_by_count":1,"area":"lr"},{"id":"2610.00412","title":"EchoPress: Query-Agnostic KV Cache Pruning via Virtual Context Reconstruction","created":"2026-09-30","cited_by_count":1,"area":"inference"},{"id":"2610.06479","title":"Behavior-Preserving KV Cache Compression","created":"2026-10-05","cited_by_count":1,"area":"inference"},{"id":"2603.07917","title":"SageSched: Efficient LLM Scheduling Confronting Demand Uncertainty and Hybridity","created":"2026-03-09","cited_by_count":0,"area":"inference"},{"id":"2604.10900","title":"CASK: Core-Aware Selective KV Compression for Reasoning Traces","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2604.24820","title":"Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.14292","title":"Minimal-Intervention KV Retention via Set-Conditioned Diversity","created":"2026-05-14","cited_by_count":0,"area":"inference"},{"id":"2607.06519","title":"FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference","created":"2026-07-07","cited_by_count":0,"area":"inference"},{"id":"2608.07855","title":"CommitKV: Lifecycle-Aware KV Cache Compression via Commit Transitions for Multi-Turn Agents","created":"2026-08-08","cited_by_count":0,"area":"inference"},{"id":"2608.14003","title":"Batch-wise Adaptive Pruning: Periodic Neuron Activation-Aware Weight Pruning for Language Reasoning Model","created":"2026-08-14","cited_by_count":0,"area":"lr"},{"id":"2608.27128","title":"Small Frequency Corrections Can Change What Survives KV Cache Compression","created":"2026-08-27","cited_by_count":0,"area":"inference"},{"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":"2609.06663","title":"ECOKV: Geometry-Aware KV Cache Eviction via Complementary Diversity Metrics","created":"2026-09-06","cited_by_count":0,"area":"mllm"},{"id":"2609.14872","title":"AgentKV: Phase-Aware KV Eviction for Agentic LLMs","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.22158","title":"StepKV: Step-Aware KV Cache Compression for LLM Agents","created":"2026-08-26","cited_by_count":0,"area":"agents"},{"id":"2609.30738","title":"Beyond Mean Attention: Diversity-Aware, Layer-Wise Scoring for KV Cache Eviction","created":"2026-09-25","cited_by_count":0,"area":"inference"},{"id":"2609.39068","title":"SparseEngine: Sparse-First Inference Engine","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.02235","title":"CORE: COverage CAlibration and Evicted-Mass REdistribution for KV Cache","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2610.02713","title":"WakeKV: Reactive, Reversible KV Residency for Heads That Change Their Minds","created":"2026-10-02","cited_by_count":0,"area":"inference"},{"id":"2610.02815","title":"iS-KV: Online Low-Rank KV Cache Compression via Block-Incremental SVD","created":"2026-10-02","cited_by_count":0,"area":"inference"},{"id":"2610.03007","title":"AvoKV-E: Payload-Aware KV Cache Eviction for Long Reasoning","created":"2026-10-02","cited_by_count":0,"area":"inference"},{"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"},{"id":"2610.14754","title":"GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.17530","title":"TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language Models","created":"2026-10-13","cited_by_count":0,"area":"mllm"},{"id":"2610.19605","title":"PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference","created":"2026-10-14","cited_by_count":0,"area":"inference"}],"next_cursor":null}