{"total":51,"rows":[{"id":"2510.00636","title":"Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution","created":"2025-10-01","cited_by_count":74,"area":"inference"},{"id":"2506.15745","title":"InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding","created":"2025-06-18","cited_by_count":58,"area":"inference"},{"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":"2512.03324","title":"Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs","created":"2025-12-03","cited_by_count":19,"area":"inference"},{"id":"2507.08143","title":"Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores","created":"2025-07-10","cited_by_count":17,"area":"inference"},{"id":"2510.00231","title":"The Pitfalls of KV Cache Compression","created":"2025-09-30","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":"2606.23525","title":"Self-Compacting Language Model Agents","created":"2026-06-22","cited_by_count":11,"area":"agents"},{"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":"2510.02312","title":"KaVa: Latent Reasoning via Compressed KV-Cache Distillation","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"id":"2509.04377","title":"PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference","created":"2025-09-04","cited_by_count":7,"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":"2605.25475","title":"IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference","created":"2026-05-25","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":"2606.01563","title":"MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference","created":"2026-06-01","cited_by_count":6,"area":"inference"},{"id":"2604.25975","title":"Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective","created":"2026-04-28","cited_by_count":5,"area":"lr"},{"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":"2606.11576","title":"AVIS: Adaptive Test-Time Scaling for Vision-Language Models","created":"2026-06-10","cited_by_count":4,"area":"lr"},{"id":"2602.08722","title":"QUOKA: Query-Oriented KV Selection For Efficient LLM Prefill","created":"2026-02-09","cited_by_count":3,"area":null},{"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":"2602.08343","title":"ManifoldKV: Training-Free KV Cache Compression via Euclidean Outlier Detection","created":"2026-02-09","cited_by_count":2,"area":"inference"},{"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":"2606.28831","title":"HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression","created":"2026-06-27","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":"2511.03728","title":"Efficient On-Device Agents via Adaptive Context Management","created":"2025-09-24","cited_by_count":1,"area":"inference"},{"id":"2602.00397","title":"Fast Forward: Accelerating LLM Prefill with Predictive FFN Sparsity","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.20732","title":"CHESS: Context-aware Hierarchical Efficient Semantic Selection for Long-Context LLM Inference","created":"2026-02-24","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":"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":"2512.07090","title":"Leveraging KV Similarity for Online Structured Pruning in LLMs","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2603.08899","title":"ConFu: Contemplate the Future for Better Speculative Sampling","created":"2026-03-09","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":"2605.20600","title":"Head-Aware Key-Value Compression for Efficient Autoregressive Image Generation","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.10944","title":"Express Language Modeling","created":"2026-06-09","cited_by_count":0,"area":null},{"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":"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":"2608.08878","title":"DistillCache: KL-Guided Adaptive KV-Cache Eviction for Memory-Efficient LLM Inference","created":"2026-08-09","cited_by_count":0,"area":"inference"},{"id":"2608.23296","title":"Sigmoid Attention as a Better Substrate for Learned KV Cache Eviction","created":"2026-08-24","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":"2609.06663","title":"ECOKV: Geometry-Aware KV Cache Eviction via Complementary Diversity Metrics","created":"2026-09-06","cited_by_count":0,"area":"mllm"},{"id":"2609.08131","title":"Jacap: Robust KV Cache Eviction via Jacobian-Based Nonlinear Information Capacity Preservation","created":"2026-09-08","cited_by_count":0,"area":"inference"},{"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":"2609.27470","title":"DeltaS: Reading the Gated Linear Attention State for KV Cache Eviction in Streaming Video","created":"2026-09-23","cited_by_count":0,"area":"inference"},{"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":"2610.02736","title":"TPBench: A Turning-Point Benchmark for Dialogue Compression","created":"2026-10-02","cited_by_count":0,"area":null},{"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":"2610.09051","title":"A Self-Pruning Transformer: Extreme KV-Cache Compression with Universal Attention","created":"2026-10-06","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":"2610.14754","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}],"next_cursor":null}