KV-Cache Compression

Ask about this topic

Momentum

24 papers in the last four weeks, up 71% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 166

All topics
CardsList

  1. Practical Online KV Cache Compaction for LLM Agents: An Empirical Study

    Aug 2, 2026Yujian Liu, Jiabao Ji, Li An +4KV CachingKV-Cache Eviction

    UC Santa Barbara · LinkedIn

  2. S4^4R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching

    Aug 1, 2026Jialong Han, You Wu, Kewei TuKV CachingLong-Context Language Model Inference

    School of Information Science and Technology, ShanghaiTech University · Shanghai Engineering Research Center of Intelligent Vision and Imaging

  3. ResKV: Reconstructing Omitted Attention Contributions for Fixed-Budget KV Cache Compression

    Jul 31, 2026Yuhang Zhan, Lisi Chen, Shuo ShangSoftmax AttentionKV Caching

    University of Electronic Science and Technology of China

  4. DynaCalKV: Key-Value Cache Compression via Head Grouping and Adaptive Rank Allocation

    Jul 27, 2026Tan T. Nguyen, Quan V. DangKV CachingLow-Rank Approximation

    ∗Full Stack Data Science · †Department of Computer Science, University College London

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

    Jul 24, 2026Chao Fang, Jun Yin, Man Shi +1KV CachingMemory-Efficient Optimization

    ESAT-MICAS, KU Leuven, Leuven, Belgium · UC Berkley, CA, USA

  6. C2^2KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference

    Jul 20, 2026Chuheng Du, Junyi Chen, Hanlin Tang +7KV CachingLLM Inference Acceleration

    School of Computer Science Shanghai Jiao Tong University Shanghai, China · Alibaba Group Hangzhou, China

  7. PReM: Learning What to Preserve and When to Refresh for Context Compression

    Jul 15, 2026Bohan Yu, Lei Shen, Chenxi Zhou +5Memory-Augmented Language ModelsLong-Context Language Model Inference

    Alibaba Group

  8. A JoLT for the KV cache: Near-Lossless KV Cache Compression via Joint Rank-bit Allocation

    Jul 14, 2026Rahul Krishnan, Volker SchulzKV CachingLow-Rank Matrix Decomposition

    Universität Trier · Fachbereich IV, Mathematik, Universität Trier

  9. How Query Visibility Changes KV-Cache Compression Rankings: A Matched-Budget Audit

    Jul 11, 2026Daming Luo, Christy Liang, Junyu XuanKV CachingKV-Cache Reuse

    University of Technology Sydney

  10. What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents

    Jul 9, 2026Ashwin Gerard Colaco, Nada LahjoujiRate-Distortion TheoryLLM Memory

    University of California, Irvine Irvine, California, USA

  11. Fractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference

    Jul 8, 2026Vladimir GusevResidual VQKV Caching

    Independent Researcher

  12. Compress the Cache, Not the Speech Embedding: KV Compression for Efficient Speech LLMs

    Jul 7, 2026Ke-Han Lu, Keqi Deng, Ruchao Fan +2KV CachingAutomatic Speech Recognition

    Microsoft, USA · National Taiwan University, Taiwan

  13. DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression

    Jul 7, 2026Anna Cordoba, Adam Puente Tercero, Nerea Angulo Hijo +4KV CachingLong-Context Language Model Inference

    Instituto de Investigación en Visión Artificial

  14. FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference

    Jul 7, 2026Anna Córdoba, Adam Puente Tercero, Nerea Angulo Hijo +4KV CachingLong-Context Language Model Inference

    Instituto de Investigación en Visión Artificial

  15. KVpop -- Key-Value Cache Compression with Predictive Online Pruning

    Jul 6, 2026Lukas Hauzenberger, Niklas Schmidinger, Anamaria-Roberta Hartl +5KV CachingKV-Cache Eviction

    1NXAI · 2Johannes Kepler University Linz, Austria

  16. The risk of KV cache compression

    Jul 1, 2026Lukas Haverbeck, Carmen Amo Alonso, Andres Felipe Posada-Moreno +2Transformer InferenceKV Caching

    RWTH Aachen University · Stanford University

  17. Precomputing the Future-Offset Average in TriAttention

    Jul 1, 2026Amarnath MukherjeeLLM Inference EfficiencyKV Caching

    Hozhoke, Inc.

  18. MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache Compression

    Jul 1, 2026Sheng Qiang, Ruiwei Chen, Yinpeng Wu +5KV CachingLong-Context Language Model Inference

    Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China

  19. Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption

    Jul 1, 2026Xiaomeng Fu, Jia Li, Yiming Hu +5Long-Horizon Video GenerationStreaming Video Generation

    Institute of Information Engineering, Chinese Academy of Sciences · AMAP, Alibaba Group · The University of Hong Kong

  20. SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference

    Jun 30, 2026Amirhossein Abaskohi, Giuseppe Carenini, Peter West +1KV-Cache OffloadingKV Caching

    University of British Columbia · Microsoft Research

  21. HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression

    Jun 27, 2026Yuxuan Yang, Feiyang Ren, Bowen Zeng +4KV CachingLong-Context Language Model Inference

    The State Key Laboratory of Blockchain and Data Security, Zhejiang University

  22. Information-Aware KV Cache Compression for Long Reasoning

    Jun 25, 2026Jushi Kai, Zhuiri Xiao, Alexandra Birch +1KV CachingLong-Context Language Model Inference

    LUMIA Lab, School of Artificial Intelligence, Shanghai Jiao Tong University · Shanghai Jiao Tong University · School of Informatics, University of Edinburgh

  23. CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference

    Jun 23, 2026Xiaolin Lin, Jingcun Wang, Olga Kondrateva +3LLM Inference EfficiencyKV Caching

    Technical University of Darmstadt, Darmstadt, Germany · University of Notre Dame, Notre Dame, IN, USA · Technical University of Ilmenau, Ilmenau, Germany

  24. Dual Dimensionality for Local and Global Attention

    Jun 17, 2026Zhiyuan Wang, Xuan Luo, Sirui Zeng +1LLM CompressionDecoder-Only Language Models

    UC Santa Barbara

  25. AnchorKV: Safety-Aware KV Cache Compression via Soft Penalty with a Refusal Anchor

    Jun 16, 2026Ning Ni, Yingjie LaoKV CachingLLM Safety Alignment

    Department of Computer Science Tufts University · Department of Electrical and Computer Engineering Tufts University

  26. Ablation, Statistical Inference, and Validation for KV-Cache Compression

    Jun 14, 2026Paolo D'Alberto, Ashish Siarasao, Elliott Delaye +1KV CachingRotation-Based Quantization

    Advanced Micro Devices, Inc.

  27. Exploring a Layer-Wise Design Space for KV Cache Eviction

    Jun 13, 2026Chao Fei, Kaihua Liang, Hanzhi Hu +4KV CachingKV-Cache Eviction

    King Abdullah University of Science and Technology · Fudan University

  28. Last But Not Least: Boundary Attention CalibratiON for Multimodal KV Cache Compression

    Jun 10, 2026Tianhao Chen, Yuheng Wu, Kelu Yao +3KV CachingMultimodal Large Language Models

    KAIST · Zhejiang Laboratory · The Chinese University of Hong Kong +1

  29. ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models

    Jun 9, 2026Wenhao Liu, Hao Shi, Yunhe Li +7KV CachingMemory-Efficient Optimization

    1Tsinghua University · 2City University of Hong Kong · 3Peking University +2

  30. FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion

    Jun 9, 2026Yu Lu, Junjie Yang, Piotr Koniusz +2KV CachingLong-Horizon Video Generation

    Zhejiang University · University of New South Wales (UNSW) · Data61/CSIRO +1