{"total":95,"rows":[{"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":"2510.01290","title":"ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models","created":"2025-10-01","cited_by_count":21,"area":"lr"},{"id":"2603.18897","title":"Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Serving","created":"2026-03-19","cited_by_count":20,"area":"agents"},{"id":"2601.17668","title":"Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction","created":"2026-01-25","cited_by_count":16,"area":"inference"},{"id":"2601.07891","title":"KVzap: Fast, Adaptive, and Faithful KV Cache Pruning","created":"2026-01-12","cited_by_count":15,"area":"inference"},{"id":"2602.10238","title":"Learning to Evict from Key-Value Cache","created":"2026-02-10","cited_by_count":14,"area":"inference"},{"id":"2510.07651","title":"OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference","created":"2025-10-09","cited_by_count":10,"area":"inference"},{"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":"2512.14946","title":"EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving","created":"2025-12-16","cited_by_count":10,"area":"inference"},{"id":"2603.10899","title":"LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation","created":"2026-03-11","cited_by_count":10,"area":"inference"},{"id":"2602.08005","title":"ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference","created":"2026-02-08","cited_by_count":9,"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":"2512.00504","title":"G-KV: Decoding-Time KV Cache Eviction with Global Attention","created":"2025-11-29","cited_by_count":7,"area":"lr"},{"id":"2605.05971","title":"Training Transformers for KV Cache Compressibility","created":"2026-05-07","cited_by_count":7,"area":"inference"},{"id":"2602.08585","title":"Predicting Future Utility: Global Combinatorial Optimization for Task-Agnostic KV Cache Eviction","created":"2026-02-09","cited_by_count":6,"area":"inference"},{"id":"2606.04557","title":"Cartridges at Scale: Training Modular KV Caches over Large Document Collections","created":"2026-06-03","cited_by_count":6,"area":"inference"},{"id":"2606.17034","title":"KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing","created":"2026-06-15","cited_by_count":6,"area":"inference"},{"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":"2606.24187","title":"Towards Fast and Effective Long Video Understanding of Multimodal Large Language Models via Adaptive Quasi-Gaussian Sampling","created":"2026-06-23","cited_by_count":5,"area":"mllm"},{"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":"2604.22782","title":"Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing","created":"2026-04-03","cited_by_count":4,"area":null},{"id":"2605.23258","title":"A Simple Plug-in for Improving Eviction-Based KV Cache Compression","created":"2026-05-22","cited_by_count":4,"area":"inference"},{"id":"2606.07878","title":"Still: Amortized KV Cache Compaction in a Single Forward Pass","created":"2026-06-05","cited_by_count":4,"area":"inference"},{"id":"2606.09659","title":"End-to-End Context Compression at Scale","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"id":"2509.05165","title":"KVCompose: Efficient Structured KV Cache Compression with Composite Tokens","created":"2025-09-05","cited_by_count":3,"area":"inference"},{"id":"2602.02599","title":"RAP: KV-Cache Compression via RoPE-Aligned Pruning","created":"2026-02-01","cited_by_count":3,"area":"inference"},{"id":"2603.20397","title":"KV Cache Optimization Strategies for Scalable and Efficient LLM Inference","created":"2026-03-20","cited_by_count":3,"area":"inference"},{"id":"2606.05875","title":"QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving","created":"2026-06-04","cited_by_count":3,"area":"rag"},{"id":"2607.10582","title":"MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference","created":"2026-07-12","cited_by_count":3,"area":"agents"},{"id":"2607.28699","title":"WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization","created":"2026-07-30","cited_by_count":3,"area":"inference"},{"id":"2608.01247","title":"RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction","created":"2026-08-02","cited_by_count":3,"area":"inference"},{"id":"2512.07011","title":"Block Sparse Flash Attention","created":"2025-12-07","cited_by_count":2,"area":null},{"id":"2601.08743","title":"TableCache: Primary Foreign Key Guided KV Cache Precomputation for Low Latency Text-to-SQL","created":"2026-01-13","cited_by_count":2,"area":"inference"},{"id":"2602.07721","title":"ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs","created":"2026-02-07","cited_by_count":2,"area":"inference"},{"id":"2602.08686","title":"CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation","created":"2026-02-09","cited_by_count":2,"area":null},{"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":"2606.06302","title":"Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving","created":"2026-06-04","cited_by_count":2,"area":"inference"},{"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":"2608.01631","title":"Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache Compression","created":"2026-08-03","cited_by_count":2,"area":"inference"},{"id":"2609.35621","title":"Cartridges++: KV Cache Compression without Off-Context Derailment","created":"2026-09-28","cited_by_count":2,"area":"inference"},{"id":"2511.03728","title":"Efficient On-Device Agents via Adaptive Context Management","created":"2025-09-24","cited_by_count":1,"area":"inference"},{"id":"2602.08030","title":"Free(): Learning to Forget in Malloc-Only Reasoning Models","created":"2026-02-08","cited_by_count":1,"area":"lr"},{"id":"2604.11288","title":"Transactional Attention: Semantic Sponsorship for KV-Cache Retention","created":"2026-04-13","cited_by_count":1,"area":"inference"},{"id":"2605.16360","title":"ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2606.06453","title":"Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents","created":"2026-06-04","cited_by_count":1,"area":"agents"},{"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":"2607.20469","title":"DecodeShare: Tracing the Shared Subspace of LLM Decode-Time Decisions","created":"2026-05-21","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":"2607.27600","title":"Back from the Future: Key-Value Cache Management by Counter-Causal Surprise","created":"2026-07-30","cited_by_count":1,"area":"inference"},{"id":"2608.03276","title":"TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning","created":"2026-08-04","cited_by_count":1,"area":"inference"},{"id":"2608.09412","title":"KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models","created":"2026-08-10","cited_by_count":1,"area":"inference"},{"id":"2608.25230","title":"Trust the Mass: Forced Weights in KV-Cache Eviction","created":"2026-08-25","cited_by_count":1,"area":"inference"},{"id":"2609.24298","title":"KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation","created":"2026-09-21","cited_by_count":1,"area":"inference"},{"id":"2609.36835","title":"ARC-KV: Amortizing Anchor Search for Reconstruction-Based KV Cache Compaction","created":"2026-09-29","cited_by_count":1,"area":"inference"},{"id":"2609.37988","title":"KV-Kaizen: Learning Context-Adaptive Cache Compression Choices","created":"2026-09-29","cited_by_count":1,"area":"inference"},{"id":"2609.39329","title":"PatchKV: Weight-Space Compensation of KV Cache","created":"2026-09-30","cited_by_count":1,"area":"inference"},{"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":"2610.03198","title":"KV$^2$: A Self-Refining KV Cache","created":"2026-10-02","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":"2512.11851","title":"KV Cache Recycling to Expand Usable Context Capacity in Low Parameter LLMs","created":"2025-12-04","cited_by_count":0,"area":"inference"},{"id":"2604.16734","title":"Reducing Peak Memory Usage for Modern Multimodal Large Language Model Pipelines","created":"2026-04-17","cited_by_count":0,"area":"mllm"},{"id":"2604.16864","title":"HieraSparse: Hierarchical Semi-Structured Sparse KV Attention","created":"2026-04-18","cited_by_count":0,"area":"inference"},{"id":"2605.13080","title":"Learning to See What You Need: Gaze Attention for Multimodal Large Language Models","created":"2026-05-13","cited_by_count":0,"area":"mllm"},{"id":"2605.18226","title":"Context Memorization for Efficient Long Context Generation","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.20295","title":"Token-Operations-Oriented Inference Optimization Techniques for Large Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.01792","title":"PARTREP: Learning What to Repeat for Decoder-only LLMs","created":"2026-07-02","cited_by_count":0,"area":"inference"},{"id":"2607.11942","title":"How Query Visibility Changes KV-Cache Compression Rankings: A Matched-Budget Audit","created":"2026-07-11","cited_by_count":0,"area":"inference"},{"id":"2607.15498","title":"VarRate: Training-Free Variable-Rate KV Cache Compression for Long-Context LLMs","created":"2026-07-16","cited_by_count":0,"area":"inference"},{"id":"2607.22854","title":"Coordinated Networking for On-Device Agent-Augmented Real-Time Communication","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.00528","title":"S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.10545","title":"ImpactHO: Importance-Aware KV Cache Transfer for Multi-User Edge LLM Handover","created":"2026-08-11","cited_by_count":0,"area":"inference"},{"id":"2608.14555","title":"Discovering KV Cache Eviction Policies via LLM-Guided Program Evolution","created":"2026-05-12","cited_by_count":0,"area":"inference"},{"id":"2608.28911","title":"SemKV: Semantic Mixed-Precision KV Cache Quantization Guided by the Quality Cliff for Long-Context LLM Inference","created":"2026-08-28","cited_by_count":0,"area":"inference"},{"id":"2608.29934","title":"Compression-Aware Abstention: Teaching LLMs to Refuse When KV-Compression Masks Remove Answer Evidence","created":"2026-08-30","cited_by_count":0,"area":"inference"},{"id":"2609.03515","title":"What Matters for Aggressive Decoding-Time KV Eviction? Temporal Aggregation and Ranking Preservation","created":"2026-09-03","cited_by_count":0,"area":"inference"},{"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":"2609.13012","title":"Pixel Decodability Is Not a Compression Signal: Causally Evaluating Importance Proxies for Visual KV-Cache Eviction","created":"2026-07-27","cited_by_count":0,"area":"mllm"},{"id":"2609.23314","title":"ValueDiff: Value-Geometric KV Cache Eviction for Sink-Suppressed LLMs","created":"2026-09-20","cited_by_count":0,"area":"inference"},{"id":"2609.32046","title":"Receiver-Conditioned Latent Communication gives 94% CacheBack","created":"2026-09-25","cited_by_count":0,"area":"inference"},{"id":"2609.32663","title":"Distance-KV: Exploiting Relative Distance for Efficient Long-Context Inference","created":"2026-09-26","cited_by_count":0,"area":"inference"},{"id":"2609.33334","title":"When to Evict, Not What to Keep: Draft-Guided Eviction for Training-Free KV-Cache Compression","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"id":"2609.33503","title":"RelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse","created":"2026-09-27","cited_by_count":0,"area":"rag"},{"id":"2609.37587","title":"ReLMem: Learning Recurrent Memory for Longitudinal EHR Modeling","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.40118","title":"Persistent Context Graphs for Efficient Memory Compaction in LLM Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.02233","title":"Budgeted Cache Repair for Cross-Context KV-Cache Reuse","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.02953","title":"SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention","created":"2026-10-02","cited_by_count":0,"area":"inference"},{"id":"2610.03109","title":"Emergent Structure in the Marginal Attention Space of Language Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.05885","title":"The Optimization Landscape of Learning Compacted Context Models","created":"2026-10-05","cited_by_count":0,"area":"inference"},{"id":"2610.06927","title":"AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD","created":"2026-10-03","cited_by_count":0,"area":"inference"},{"id":"2610.12133","title":"Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.14475","title":"EdgeLLM-Nano: Auditing Polar-Guided Key-Cache Compression and Consistency-Anchored Pruning on a 33.6 MB On-Device Language Model","created":"2026-10-10","cited_by_count":0,"area":"inference"},{"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":"2610.16003","title":"PAIR: Memory-Efficient and Fast Inference with Reading--Reasoning Fusion","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.20582","title":"Latent Compaction with Test-Time Training","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}