ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “key-value cache”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.DCcs.AIcs.LGEmpiricalRecentJun 19, 2026

Recency/Frequency Adaptive KV Caching for Large Language Model Serving

Yang Shen, Meghana Madhyastha, Robert Underwood, Bogdan Nicolae +1 more

The paper proposes adaptive caching for key-value (KV) caching in large language models, improving cache hit rate and reducing time to first token.

View →
cs.CRcs.AIcs.LGEmpiricalRecentJul 22, 2026

HijackKV: New Threat in Position-Independent KV Cache Reuse

Yichi Zhang, Zhiqi Wang, Huan Zhang, Yuchen Yang

This paper introduces HIJACKKV, the first attack framework to exploit the new threat of KV Cache Hijacking in large language models, achieving an average success rate of 94%.

View →
cs.CLRecentMay 29, 2026

GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs

Junjie Peng, You Wu, Haoyi Wu, Jialong Han +3 more

GRKV introduces a training-free KV-cache merging method that uses global regression to distribute information from evicted tokens, solving the over-merging problem inherent in span-based retention.

View →
cs.CRRecentMay 22, 2026

CachePrune: Privacy-Aware and Fine-Grained KV Cache Sharing for Efficient LLM Inference

Guanlong Wu, Zhaohan li, Yao Zhang, Zheng Zhang +3 more

CachePrune introduces a privacy-aware, fine-grained KV cache sharing mechanism that allows LLM inference systems to safely reuse cache entries across users' requests, significantly improving efficienc…

View →
cs.ARcs.CLcs.LGRecentJun 1, 2026

Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving

Chunan Shi, Yilei Chen, Yilin Chen, Xupeng Miao +1 more

The paper proposes AsymCache, a computation-latency-aware KV cache management system that optimizes LLM inference by aligning cache eviction decisions with GPU attention kernel performance, significan…

View →
cs.ARcs.DCEmpiricalRecentOct 24, 2026

ZipFusion: Fusing Lossless KV Decompression with Attention for Efficient LLM Decoding

Yuetao Chen, Peng Wang, Hong Xu

This paper presents ZipFusion, a method that enables attention to consume losslessly compressed key-value (KV) cache directly, improving model decode throughput and reducing memory-bandwidth bound.

View →
cs.CLcs.AIRecentMay 30, 2026

WaveFilter: Enhancing the Long-Context Capability of Diffusion LLMs via Wavelet-Guided KV Cache Filtering

Jinnan Yang, Yan Wang, Zhen Bi, Kehao Wu +4 more

WaveFilter is a novel, training-free framework that uses wavelet transforms to efficiently filter critical tokens in the KV cache, significantly improving the long-context performance of Diffusion LLM…

View →
cs.DCEmpiricalRecentOct 30, 2026

HiState: Hierarchical Prefix Cache Management for Hybrid LLM Serving in Agentic Workloads

Zaifeng Pan, Lucas Wang, Xinwei Qiang, Yanbo Zhou +4 more

This paper presents HiState, a prefix cache management system for hybrid models serving agent workloads to reduce inference costs.

View →
cs.CRcs.AIcs.CLRecentMay 26, 2026

Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?

Syed Huma Shah

The paper proposes GroundedCache, an evidence-validated cache router that significantly improves the safety of reusing cached semantic answers in RAG systems by requiring multiple gates to validate th…

View →
cs.DBcs.DSEmpiricalRecentJun 15, 2026

C^2: Cache-Conscious Succinct Tries with Adaptive Unary Path Compression

Kepan Zhang, Tiancheng Zhao, Helen Xu

This paper proposes C^2, a set of techniques to improve the spatial locality of succinct tries, resulting in faster query performance and reduced memory footprint.

View →
cs.IRcs.CLcs.LGEmpiricalRecentJun 18, 2026

Closing the Calibration Gap in Semantic Caching

Aditeya Baral, Radoslav Ralev, Iliya Sotirov Zhechev, Srijith Rajamohan +1 more

This paper introduces new metrics to evaluate semantic caching systems and shows that model selection is a calibration problem, not a ranking one.

View →
cs.DCcs.OSEmpiricalRecentJun 15, 2026

CacheWise: Understanding Workloads and Optimizing KVCache Management for Efficiently Serving LLM Coding Agents

Shubham Tiwari, Tapan Chugh, Nash Rickert, Simon Peter +2 more

This paper presents a new KVCache management layer called CacheWise that improves performance for coding agent workloads.

View →
cs.DCEmpiricalRecentJun 11, 2026

Skiplists with Foresight: Skipping Cache Misses

Tomer Cory, Niv Sulimany, Erez Petrank

This paper introduces Foresight, a cache-friendly skiplist optimization that improves performance in sequential and concurrent settings.

View →
cs.CLcs.LGEmpiricalRecentJun 15, 2026

KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing

Mufei Li, Shikun Liu, Dongqi Fu, Haoyu Wang +4 more

The paper presents KVEraser, a learned KV-cache editing method for efficient localized context erasing in long-context LLM applications.

View →
cs.ITTheoreticalRecentOct 9, 2026

Heterogeneous Demand-Private Coded Caching: Exact Characterization for Two Users and Two Files

Tati V D N Eswar, Jithin Ravi

The paper characterizes the memory-rate trade-off for demand-private coded caching with heterogeneous file sizes and cache capacities.

View →
cs.ARcs.AIcs.LGEmpiricalRecentJul 24, 2026

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding

Chao Fang, Jun Yin, Man Shi, Marian Verhelst

Proposed a novel algorithm-hardware co-design, HiKV, to tackle the memory bottleneck in long-context large language models by exploiting KV cache redundancy through hierarchical importance awareness,…

View →
cs.DBcs.DCcs.PFEmpiricalRecentJun 26, 2026

DiStash: A Disaggregated Multi-Stash Transactional Key-Value Store

Yiming Gao, Hieu Nguyen, Jun Li, Shahram Ghandeharizadeh

This paper introduces DiStash, a disaggregated transactional key-value store that enables an application to use a single transaction to manage key-value pairs across different pools of stashes, preven…

View →